![]() Methods for handwriting verification and for user authentication
专利摘要:
METHODS FOR MANUSCRIPT VERIFICATION AND USER AUTHENTICATION. Handwriting verification methods and related computer systems and user authentication methods based on handwriting and related computer systems are described. A handwriting verification method comprises obtaining a handwriting test sample that contains a plurality of available parameters, extracting geometric parameters, deriving biometric characteristics comprising an x-position value and a y-position value for each of a plurality of points. of feature on the test sample, perform feature correspondence between geometric features of the test sample and the reference sample, determine a manuscript verification result based, at least in part, on the characteristic match, and transmit the verification result of manuscript. The geometric features may additionally comprise values derived from the geometric parameters, such as direction and curvature values. The handwriting verification result can additionally be based on a count of unlinked feature points. Handwriting-based user authentication methods may employ such handwriting verification methods or other handwriting verification methods. 公开号:BR102014027735B1 申请号:R102014027735-8 申请日:2014-11-06 公开日:2022-02-15 发明作者:Nicholas Mettyear;Yoshitaka Nakayama;Jin Kon Ryu 申请人:Wacom Co., Ltd; IPC主号:
专利说明:
FUNDAMENTALS [0001] Electronic manuscript is increasingly important in a variety of contexts. For example, electronic handwriting is now commonly used in place of pen and paper to obtain an affirmation from the credit card holder of a credit card transaction. As electronic manuscript has become more common, the ability to verify the authenticity of electronic manuscript has also become more important. [0002] US Patent 6,487,310 describes an "elastic matching" method for comparing one signature with another, comprising the operations of creating a mapping between corresponding points in two signatures to be compared measured at different times after the start of writing of the signatures, which maximizes the correlation between the local spatial neighborhood of the measured points and, simultaneously, minimizes the curvature of the elastic spatial distortion of the mapping, providing quantitative measures of both the degree of spatial correlations and the degree of non-uniform spatial distortions in the mapping, thus, providing measures of similarity between signatures. [0003] Whatever the benefits of previous handwriting verification techniques may be, they do not have the advantages of the techniques and tools described below. SUMMARY [0004] This summary is provided to introduce a selection of concepts in a simplified form which are further described below in the Detailed Description. This summary is not intended to identify key features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter. [0005] In at least one aspect of the present disclosure, a handwriting verification method comprises obtaining a handwriting test sample that contains a plurality of available parameters, wherein the plurality of available parameters comprises geometric parameters and one or more non- geometric; extracting the geometric parameters from the plurality of available parameters; based on the geometric parameters, deriving geometric features comprising an x-position value and a y-position value for each of a plurality of feature points uniformly distributed in the handwriting test sample; perform first feature matching between geometric features of the handwriting test sample and geometric features of a reference sample; determine a handwriting verification result based, at least in part, on the characteristic match; and transmit the result of the handwriting verification. The geometric features may additionally comprise values derived from the geometric parameters, such as direction and curvature values. The determination of the handwriting check result can additionally be based on a count of unlinked feature points. [0006] The first feature match may include finding mappings between one or more of the evenly distributed feature points in the test sample and one or more uniformly distributed feature points in the reference sample. The first characteristic match may include a simulated annealing process. The simulated annealing process may include selecting a feature point on the reference sample; generate a pseudorandom value; compare the pseudorandom value to a constant; and, based on the comparison, determine whether to remove a link from a selected point in the reference sample or to define a new link between the selected feature point in the reference sample and a selected feature point in the reference sample. test. The determination step can be biased towards defining a new bond versus removing an existing bond based on the value of the constant. If a new link is defined, all previously existing links that are crossed by the new link can be removed. [0007] Second characteristic matching may also be performed, which may include the evaluation of a non-geometric parameter (eg a time-related parameter such as velocity or acceleration). The handwriting verification result can be additionally based on the second characteristic match. [0008] In another aspect, a handwriting verification method comprises performing feature matching between geometric features of a handwriting test sample and geometric features of a reference sample, wherein feature matching comprises defining one or more links between one or more evenly distributed feature points in the test sample and one or more uniformly distributed feature points in the reference sample; obtaining a count of consecutive unbound feature points in the test sample; and transmitting a handwriting verification result, wherein the handwriting verification result is based, at least in part, on feature matching and the count of consecutive unlinked feature points in the test sample. [0009] In another aspect, a Method for user authentication comprises receiving test signature data and a user device identifier (ID) from a user device; fetch an ID from the name associated with the test subscription data; get name ID; fetch a reference device ID associated with the name ID; compare the reference device ID with the user ID device; and providing authentication information (eg, an authentication result) to the user's device based on the comparison. Device IDs can be, for example, pen or style IDs associated with a pen or style. [00010] In another aspect, a Method for user authentication comprises receiving test signature data (e.g. encrypted test signature data), a device identifier and a service identifier from a user's device, where the service identifier refers to a service running on the user's device; comparing test signature data with reference signature data; based on a result of the comparison, obtain authentication information (eg, a user ID and password) associated with the service running on the user's device; and providing authentication information to the user's device. If the test signature data is consistent with the reference signature data, the test signature data can be added to the reference signature data (eg, as supplemental information for future authentications). BRIEF DESCRIPTION OF THE DRAWINGS [00011] FIGURE 1A is a high-level diagram of an illustrative cloud computing arrangement configured to verify the authenticity of sample manuscript data; FIGURE 1B is a functional block diagram of a manuscript data processing section FIGURE 2A is an illustration of a handwritten signature comprising a plurality of pen events; FIGURE 2B is a diagram of detectable rotation, altitude and azimuth parameters for a pen device; FIGURE 2C is a illustration of an example data structure that can be used to represent a pen event and a data sequence order of such pen events; FIGURE 3 is a functional block diagram of a handwriting verification service that can be implemented on a handwriting verification server; FIGURE 4 is a flowchart of an example dynamic handwriting verification process; FIGURE 5 is an illustration of character dots along a manuscript path; FIGURE 6 is a graph illustrating calculations of x-positions and y-positions of respective feature points; FIGURES 7A and 7B are illustrations depicting direction and curvature calculations, respectively, for a current point of feature based on the x and y positions of previous feature points and subsequent feature points; FIGURE 8 is diagram of mappings established between a test sample and a reference sample by a feature matching technique; FIGURE 9A is a flowchart of an example annealing process that can be used in a handwriting verification process; FIGURE 9B is a graph illustrating conditions to allow for the increase in energy during an annealing process used in a handwriting verification process ;FIGURE 9C is a flowchart of an example process by which a set of bonds can be changed in an annealing process not used in a handwriting verification process; FIGURE 9D is diagram of an illustrative change in a set of connections during an annealing process used in a handwriting verification process; FIGURE 9E is a flowchart of an example process by which annealing can be repeated in a verification process of handwriting; FIGURE 10 is a graph showing results of a test in which the proportion of features that are bound and the average binding energy for a large number of signatures has been graphically represented; FIGURE 11 is a flowchart of a process of sample matching that includes a count of consecutive unlinked feature points; FIGURES 12A and 12B are illustrations of a test sample and a reference sample, respectively, that can be processed according to a sample matching process which includes a count of consecutive unlinked feature points; FIGURE 13A is a graph illustrating comparison results of elapsed time values corresponding to feature points in two handwriting samples; FIGURE 13B is a graph illustrating a pressure-time diagram area from start of signature to characteristic i; FIGURE 13C is a graph illustrating results of comparing pressure-time values corresponding to characteristic points in two manuscript samples; FIGURE 14 is a flowchart of an example post-processing process that can be used after a determination has been made regarding whether a sample test is consistent or inconsistent with a reference sample; FIGURE 15 is a diagram of an illustrative computer system and process for verifying the authenticity of a signature; FIGURE 16 is an illustration of a table that can be used to search for a signature. reference signature based on one or more identifiers; FIGURE 17 is a diagram of a user authentication process based on illustrative handwriting in a properly configured computing system; FIGURE 18A is an illustration of a table that can be used to look up an identifier based on signature data; FIGURE 18B is an illustration of a table that can be used to look up a device identifier based on other identifiers; FIGURE 19A is a diagram of another illustrative handwriting-based user authentication process on a properly configured computing system; FIGURE 19B is an illustration of a data table that may be used in the process user authentication shown in FIGURE 19A; and FIGURE 20 is a block diagram illustrating aspects of an exemplary computing device suitable for use in accordance with embodiments of the present description. DETAILED DESCRIPTION [00012] The present description is, in general, directed to techniques and tools for verifying electronic signatures or other electronic manuscripts. [00013] Determining whether a signature is authentic poses many challenges. One challenge is that authentic signatures made by the same person will always have some degree of variability. Another challenge is that the degree of variability between authentic signatures will vary from person to person. Previously, a determination of the level of variability was made by combining several reference samples collected at different times into a template that can be used for verification. However, collecting multiple reference samples at different times does not sit well with many business processes. For example, banks have traditionally stored a single reference signature for comparison purposes. Thus, the ability to improve the accuracy of a verification process while using a single reference will be advantageous. [00014] In this manner, In described embodiments, a dynamic handwriting verification engine is configured to compare handwriting data associated with a handwriting test sample (e.g., a signature) with handwriting data associated with a reference sample for determine if the test sample is authentic. Although some of the modalities described herein pertain to the verification of signatures, it is understood that the modalities described herein can be used to verify manuscripts of all types, and are not limited to the verification of signatures. [00015] According to embodiments described here, a verification process involves matching geometric features in a test sample and a reference sample, while allowing for minor differences resulting from natural inconsistency between samples that are made by the same person. In addition to geometric characteristics, the verification process can also take into account more data that can be generated by current handwriting collection technology (e.g. movement of a pen between strokes, pen pressure, pen angles, and the like), the which can improve verification quality results. As different insertion devices can provide different types of data, the verification process can adapt to the types of data provided by particular devices, according to the modalities described herein. For example, if a test sample includes pressure information and a reference sample does not, the verification process may omit pressure analysis information and focus instead on comparisons of data that are common to the two samples. [00016] The detailed description given below in connection with the accompanying drawings, in which like reference numerals represent like elements, is intended as a description of various embodiments of the subject matter described and is not intended to represent the only embodiments. Each embodiment described in this specification is provided merely by way of example or illustration, and should not be construed as preferred or advantageous over other embodiments. The illustrative examples provided herein are not intended to be exhaustive or to limit the subject matter claimed in the precise forms described. [00017] In the following description, numerous specific details are presented in order to provide a thorough understanding of exemplary embodiments of the present description. It will be apparent to those skilled in the art, however, that many embodiments of the present disclosure can be practiced without some or all of the specific details. In some cases, well-known process steps have not been described in detail in order not to unnecessarily obscure various aspects of the present description. Additionally, it is understood that embodiments of the present disclosure may employ any combination of features described herein. [00018] FIGURE 1A is a high-level diagram of an illustrative cloud computing arrangement 1 configured to verify the authenticity of sample manuscript data in accordance with techniques described herein. In the example shown in FIGURE 1A, handwriting input devices 10, 12, and 14 provide handwriting data in various forms to a handwriting verification server 700 on a network 20 (eg, the Internet). Handwriting input devices 10, 12 and 14 can be implemented as dedicated handwriting collection devices or as general purpose devices such as properly configured smart phones or tablet computers. While handwriting insertion devices 10, 12 and 14 are referred to herein as "insertion devices," such devices are not limited to insertion collection and will typically also include other functionality (e.g. display functionality, transmission functionality of data, etc.). [00019] When a handwritten signature is made on paper, an ink pen leaves a continuous trail of ink that forms the signature. A digital version of a handwritten signature generally comprises a collection of discrete data points measured at regular time intervals. [00020] Again, referring to FIGURE 1A, any of the inserters 10, 12, 14 can use electromagnetic resonance (EMR) technology, in which a digitizer incorporates a sensor board that detects pen movement and energy is induced in the resonant circuit of the pen by a magnetic field generated by the surface of the sensor board. The pen's resonant circuit then makes use of this energy to return a magnetic signal to the surface of the sensor board. The board detects the coordinate position of the pen at regular time intervals even if the electronic pen does not touch the surface of the sensor board, as long as the pen remains in close enough proximity to the sensor board so that signals can still be transmitted. received from the pen (The effective signal range may vary depending on the particular technology being used, but is generally on the order of several millimeters.). [00021] Alternatively, another handwriting input technology can be used. For example, an electronic pen might use another wireless technology, or it might be cabled to a digitizer. As another example, an electronic pen may not be detectable far from the surface of a digitizer. As another example, an electronic pen can be energized or de-energized. Powered pens can be powered via a cable plugged into an external power source or via a built-in battery. As another example, you can enter handwritten data on an electronic pen (for example, via a style on a pressure-sensitive digital writing pad, a touchscreen, or some other input device that does not require an electronic pen). ). [00022] However, manuscript data may be collected, manuscript data provided by insertion devices 10, 12 and 14 may include pen event information, device information, and/or contextual information about the context in which the manuscript was done. In described embodiments, pen event information includes the x,y position of the pen tip on or above the surface of the digitizer and the time since the start of the handwriting. Additionally, pen event information may optionally include additional information subject to the capabilities of the inserters 10, 12 and 14, such as pressure (pen force), angles (azimuth, altitude and/or rotation) and pen-down state. Pen event information is typically collected at regular intervals during a subscription process. [00023] Device information may include information needed to convert from digitizer units to real world units. Contextual information for a signature may include the name of the person signing it; the date and time of signature; the reason for the subscription; the type and version of the operating system used on a host device; the type of scanner; the scanner device driver version; a unique identifier taken from the network interface controller (NIC) address of a host device; if a cryptographic hash function is used, information about the type of hash function; and/or supplementary data that may be added by a software application at the time of capture. Contextual information can also include information about the document that is signed, such as a cryptographic message compilation. [00024] Again, referring to FIGURE 1A, the handwriting verification server 700 performs a verification process that compares handwriting test samples with reference samples to determine whether the test samples are authentic. Results of the verification process may be transmitted by the handwriting verification server 700. In at least one embodiment, the handwriting verification server 700 performs the verification process illustrated in FIGURE 4 as described below in additional detail. In the example shown in FIGURE 1A, results of the verification process are provided by the handwriting verification server to a post-processing section 790 for further processing (e.g., formatting results for display, storing results, analyzing results, transmitting results for other devices, etc.). The post-processing section 790 may be implemented on the handwriting verification server 700 and/or on one or more other devices. [00025] Handwriting verification server 700 can verify the authenticity of handwriting input data provided in various forms (eg, embedded data, streaming data, raw pen event data). For example, as shown in FIGURE 1A, inserters 10 and 12 can transmit raw manuscript data to a manuscript data processing section 100, which can generate and transmit streaming data or embedded data to the server. handwriting verification 700 on network 20, as described in additional detail below. [00026] FIGURE 1B is a functional block diagram of an illustrative handwriting data processing section 100. Handwriting data processing section 100 may be implemented (e.g., as software or hardware) in an input device. handwriting or some other device that can communicate with the input device directly (for example, via a USB connection) or over a network. [00027] In the example shown in FIGURE 1B, the manuscript data processing section 100 comprises an insert handling section 101, a streaming section 200, a lossy data processing section 300, and a integration 400. The insert handling section 101 is responsible for forwarding the raw manuscript data for further processing, for example, through the streaming section 200 and the lossy data processing section 300. The input generation section streaming 200 receives raw handwriting data as input and generates streaming data (e.g., separate streams for x-coordinate, y-coordinate, and pressure information, along with header information). In at least one embodiment, the stream generation section 200 uses lossless encoding techniques to generate compressed stream transmitted data comprising a plurality of streams. [00028] In the example shown in FIGURE 1B, the lossy data processing section 300 also receives raw handwriting data as input. The lossy data processing section 300 may use lossy data processing techniques (that is, techniques that may involve data loss) to generate course data (which can be used to render the manuscript as an image) and/or or image data (for example, image data in a PNG format or some other image data format). For example, the lossy data processing section 300 may include an ink engine configured to perform data formatting and processing that may be required to render a visual representation of the manuscript (eg, a signature) for display. As an alternative to the arrangement shown in FIGURE 1B, in which course data and/or image data are generated based on the raw handwriting data, the lossy data processing section 300 may output based on the data transmitted in continuous flow provided by the continuous flow generation section 200. [00029] In the example shown in FIGURE 1B, the integration section 400 receives the streaming data and the course and/or image data as input and transmits the integrated handwriting data. The integration section 400 may transmit integrated data in a single output file (e.g. an image file) or it may separately transmit streaming data and/or course/image data. In at least one embodiment, streaming data may be converted to an encoded binary format, and the embedded data may take the form of a digital image with the encoded binary data steganographically inserted into the digital image. For more information, see US Provisional Patent Application 61/895,895, filed October 25, 2013, which is incorporated herein by reference. [00030] The arrangements shown in FIGURES 1A and 1B are examples only. Many other arrangements are possible. For example, although handwriting insertion and handwriting verification are described with respect to FIGURE 1A as occurring on different devices (e.g., on input devices and the handwriting verification server 700, respectively), handwriting entry and handwriting verification can also be performed on the same device. As another example, although handwriting input devices and a handwriting verification server are described with reference to FIGURE 1A as communicating in a cloud computing arrangement 1 over a wide area network, such as the Internet 20, input and the handwriting verification server may also communicate in some other way (for example, over a local area network). As another example, the details of how the handwriting data processing section 100 operates may vary depending on implementation and/or context. As another example, a manuscript data processing section 100 is not required to provide manuscript data to be verified in accordance with the techniques described herein. In the example shown in FIGURE 1A, the inserter 14 generates raw pen event data and transmits the raw pen event data on the network 20 to the handwriting verification server 700 without intermediate processing by a data processing section of manuscript 100. [00031] According to embodiments described herein, a manuscript sample to be verified (or "test sample") can be a handwritten signature (see FIGURE 2A) or any other type of manuscript, such as printed characters or a drawing artistic. [00032] In described embodiments, handwriting data may be represented as a sequence of pen events. Typically, a pen event records the position of the pen tip (eg, while on the surface of a digitizer, or within a limited range of a digitizer) at a particular time. In addition to x/y coordinate values, some handwriting input devices can also detect other information, such as pen angle, writing speed, writing pressure, etc. Depending on device capabilities, data from pen associated with pen events may include additional measurements, such as pen pressure and pen angles. In the example shown in FIGURE 2B, rotation, altitude, and azimuth are among the parameters that can be detected for a pen device (represented by a large black arrow). [00033] Again, with reference to FIGURE 2A, an illustrative handwritten signature 206A comprises a plurality of pen events that are detected by a pen device and a digitizer using technology (eg, EMR technology) that allows pen events to continue to be detected when the pen is raised from the surface of the digitizer, as long as the pen remains in range of the signal. In the example shown in FIGURE 2A, coordinates detected when the pen is up are represented as lighter points, and detected coordinates while the pen is down are represented as darker dots. [00034] FIGURE 2C is an illustration of an example data structure 210 that can be used to represent a pen event and a data sequence order 212 of such pen events. A sequence of pen events can be provided as input, for example, to a handwriting verification server 700, either in a raw form or in a preprocessed form (for example, through a data processing section of handwriting 100, which can be used to put pen event data in the form of streaming data and/or embedded data). In the example shown in FIGURE 2C, data structure 210 may be implemented as a "structure" or "class" type. Alternatively, data structure 210 may be implemented in some other way. In the described embodiments, pen events are provided in the order they occurred in the order of the data sequence 212. [00035] FIGURE 3 is a functional block diagram of a handwriting verification service 700A that may be implemented in a handwriting verification server (e.g., the handwriting verification server 700 shown in FIGURE 1A). In the example shown in FIGURE 3, the handwriting verification service 700A comprises a handwriting test sample data handling section 710 comprising subsections 720, 730, and 740 that are configured to process handwriting data in various ways. In the illustrated example, an embedded data handling subsection 720, a streaming data handling subsection 730, and a raw handwriting data handling subsection 740 are configured to receive embedded data, streaming data, and raw handwriting, respectively, as inputs, and generate pen event parameters as outputs. Some of the data handling sections may also be able to transmit other data. For example, in the example shown in FIGURE 3, the integrated data handling section 720 is configured to extract image data from the integrated data and transmit the image data to the post processing section 790A for further processing. [00036] In the example shown in FIGURE 3, a verification section 750 receives pen event parameters from the handwriting test sample data handling section 710 and receives a reference sample from a repository 760 (O repository 760 may be implemented on a device separate from the handwriting verification service 700A, as shown in FIGURE 3, or the repository may be implemented on the same device as the service 700A.). Verification section 750 verifies the authenticity of a handwriting test sample by comparing characteristics derived from pen event parameters with characteristics of the reference sample. [00037] An example dynamic handwriting verification process is shown in FIGURE 4. The verification process shown in FIGURE 4 can be performed by a handwriting verification server (eg, handwriting verification server 700 in FIGURE 1A) or by some other device. The verification process shown in FIGURE 4 may be performed on a cloud computing array (eg, cloud computing array 1 shown in FIGURE 1A) or on some other array. In described embodiments, the verification process uses geometric parameters of the manuscript in a test manuscript sample to derive characteristics of the manuscript that can be compared with characteristics in a reference sample. [00038] In the example shown in FIGURE 4, geometric parameters of the manuscript are chosen from the pen event parameters available in step S101. In this example, manuscript geometric parameters include x-coordinate values and y-coordinate values. The available pen event parameters from which the geometric parameters are chosen may include, in addition to x-coordinate and y-coordinate values, pressure values, angle values, time stamp information, or the like. The available pen event parameters may depend on factors such as the capabilities of the insertion device that was used to create the handwriting. [00039] Because the speed of ordinary handwriting varies, detection of x-coordinate and y-coordinate positions at regular time intervals results in variable spacing between detected positions. Again, relative to the signature example shown in FIGURE 2A, the 206B coordinate positions of pen events are detected at regular intervals (e.g., at a sample rate of 133 points per second, 200 points per second, or some other rate sample). Therefore, wider spacing between 206B coordinate positions indicates parts of the signature where the pen is moving faster, and narrower spacing indicates parts where the pen is moving slower. [00040] Again, referring to FIGURE 4, in order to facilitate the comparison of feature points in manuscript test samples and reference samples, feature points are derived from the manuscript's geometric parameters in step S103. Feature points derived in this way follow the path of the sample manuscript, but do not need to be colocated with pen events. In at least one embodiment, feature points are evenly distributed along the manuscript path. However, feature points can be distributed in other ways. [00041] FIGURE 5 represents illustrative spacing of feature points along a manuscript path. In the example shown in FIGURE 5, the feature points are evenly distributed. In general, decreasing the spacing tends to increase the number of feature points, which can lead to longer processing time. On the other hand, increasing spacing tends to decrease the number of feature points, which can lead to less precision and the omission of important features in the manuscript. In at least one embodiment, a regular spacing of 1 mm is used as a compromise to balance reasonable processing time with accurate detection of important manuscript features. [00042] The particular spacing that is used may vary depending on the implementation. For example, the spacing between feature points need not be uniform. According to an alternative approach, feature points can be positioned according to a density normalization process in which the spacing between densely packed pen events is expanded to the corresponding feature points. In an approach like this, feature points may or may not be colocalized with original pen events. The density normalization process may also include inserting feature points into parts of the manuscript path when pen events are sparse. The density normalization process can be applied to the test sample and the reference sample to resolve spot density differences between samples, while still allowing for some variation in the spacing between feature points, which can help to preserve information regarding the speed and acceleration of the manuscript. The density normalization process can help to provide comparable sets of feature points between samples taken by devices with different sampling rates. [00043] Again, referring to FIGURE 4, each of the feature points (see step S103) is associated with corresponding x-position and y-position computed at regular spatial intervals along the manuscript path. In at least one embodiment, the x positions and y positions of the respective feature points are calculated as shown in FIGURE 6. [00044] In the example shown in FIGURE 6, the x (X) position and y (Y) position of the feature points are defined as the proportion of the x coordinate value or the y coordinate value, respectively, with respect to a general value of the respective dimension (eg width (w) or height (h)) of the manuscript or some part of the manuscript (eg a course). [00045] In at least one embodiment, feature points are defined for the entire length of a sample manuscript, including areas from the pen upwards where the pen was not in contact with the tablet surface. In some circumstances, pen-up information will not be available between courses. This can occur, for example, when using a capture device that does not support pen-up data or when a pen is held at a distance from the digitizer such that pen-up data cannot be detected. If pen-up information is not available, feature points can be generated on the boundaries of pen-down events. [00046] Again, referring to FIGURE 4, in step S105, direction (D) and curvature (C) are derived from the x positions and y positions of the derived feature points. In this example, the direction and curvature values derived in step S105 are not based on the x/y coordinate values from the original pen events. In at least one embodiment, direction and curvature are derived for a current feature point based on the x positions and y positions of previous and subsequent feature points, as shown in FIGURES 7A and 7B. [00047] In the example shown in FIGURE 7A, the D direction for a current feature point 802 is calculated as the angle (relative to the horizontal, in radians) of the line between the previous feature point 804 and the next feature point 806 In the example shown in FIGURE 7B, the curvature C for a current characteristic point 802 is calculated as the angle (in radians) between the line connecting the current characteristic point 802 at the previous characteristic point 804 and the line connecting the current characteristic point 802 at the next characteristic point 806. [00048] Again, referring to FIGURE 4, in step S107, feature matching is performed using geometric features (eg x-position, y-position, direction, curvature) of the feature points. In this example, the objective of feature matching is to link corresponding geometric features in a manuscript sample to be verified (or test sample) and a reference sample, while providing flexibility to account for natural variation in authentic manuscript. The feature matching of step S107 can include more than one feature matching pass, as described in further detail below. [00049] FIGURE 8 is an illustration of mappings established between a test sample 810 and a reference sample 820 by a feature matching technique (eg, step S107 in FIGURE 4). In the example illustrated in FIGURE 8, the mappings comprise links (represented by dashed lines) established between corresponding feature points (represented by circles) in a test sample 810 and a reference sample 820. The consistency of the manuscript line at each end of the bond may be referred to as the "energy" of the bond. In this example, energy is measured in terms of the differences between the x-position (X), y-position (Y), direction (D), and curvature (C) values of the connected feature points. [00050] In at least one embodiment, energy is measured according to the following equation: ei = kx(Xr - Xt)2 + ky(Yr - Yt)2 + kd(Dr - Dt)2 + kc(Cr - Ct)2, where ei is the energy of the i-th bond, which connects a reference sample r with a test sample t; Xr, Yr, Dr and Cr are the values of the x, y and curvature directions for the reference sample; Xt, Yt, Dt and Ct are the values of the x, y and curvature directions for the test sample; and kx, ky, kd and kc are weighting factors for the different energy components. [00051] In at least one embodiment, an ideal set of bonds is one that achieves a minimum total energy (E) of the system, which can be defined according to the following equation: where ei is the energy of the i-th bond; ku is a constant representing the energy of an unbound characteristic; and nu is the number of unlinked features (if any). [00052] In at least one embodiment, numerical annealing is used to minimize differences between feature points at the ends of each bond and thereby minimize the energy E. In particular, In at least one embodiment, an annealing method simulated is used to make pseudorandom changes to the link, which can increase or decrease the total energy. [00053] In an example annealing process, which is now described in relation to FIGURES 9A - 9D, changes that result in a reduction in the total energy are always accepted and changes that result in an increase in energy may be accepted, depending on factors , such as the current system temperature, which can be progressively reduced. The term "temperature" as used herein refers to the mathematical energy of the system and does not refer to any actual thermal energy. Similarly, related terms such as "cooling" are used to refer to the reduction of mathematical energy and do not refer to any change in actual thermal energy. [00054] "Energy" and "temperature" are related terms that can be used to model the annealing process. In at least one embodiment, an objective of the annealing process is to discover the best set of links between corresponding features in two signatures. The relative merit of any of the possible bonding patterns can be determined by evaluating the similarity of geometric features, such as position, line direction, and curvature, at bonded feature points. The energy of a bond is a measure of the differences between the two characteristic points. Zero energy indicates a state of having identical characteristics, and energy increases as the differences become more substantial. [00055] The annealing process tries to minimize the total energy of the system by adjusting the bond set. However, if individual adjustments that increase the total energy had never been allowed, the probability of the annealing process being trapped in a minimum total energy location will increase. To address this situation, the annealing process can be designed to reduce the likelihood that the process will become trapped in a minimal location by allowing for some changes that result in an increase in energy, thereby allowing for the possibility that subsequent changes may achieve lower total energy. [00056] The system temperature can be used to control the probability of a change that increases the total energy. In at least one embodiment, the temperature is initially set to a relatively high value that allows the increase in energy to occur more frequently. The temperature is reduced as the annealing process proceeds. As the temperature drops, the probability of higher energy is reduced until stability in the system is achieved. [00057] Now, in relation to the example of the annealing process illustrated in FIGURE 9A, in step S201, the variables E (energy), T (temperature), I_step and I_cycle are initialized. In step S203, the link is changed. In this context, the term "link" is used to refer, in general, to the one or more links between the test sample and the reference sample. Therefore, in step S203, the set of connections between the test sample and the reference sample is changed in some way (An example of a process by which the set of connections can be changed is described in detail below with reference to FIGURE 9C. ). [00058] In step S205, the total energy of the changed bond (E_new) is compared with the total energy of the previous state of the bond (E_prev). If E_new is less than or equal to E_prev, the link change is retained in step S207. If E_new is greater than E_prev, a determination is made in step S217 as to whether the binding change can still be accepted. [00059] In at least one embodiment, the increase in energy can be accepted, depending on a ratio involving the magnitude of the change (dE) and the actual temperature. In the example shown in FIGURE 9B, increases in energy (dE positive) are allowed when the following condition is satisfied: go swg W fi wo xcnqt fg fguxkq wpkfoimg pc hckzc fg 2 0 W 01.0, dE is the change in total energy resulting from the change in bond, and T is the current system temperature. A uniform deviation is used to generate one or more pseudorandom U values. A single uniform deviation generator is used for the full comparison between the test sample and the reference sample, and it is always initialized to the same seed. This ensures that the comparison of the test sample and the reference sample always returns the same result. [00060] An example process by which the link can be changed (see step S203 in FIGURE 9A) will now be described with respect to FIGURE 9C. In step S203-1, a characteristic point is selected in a reference sample. In step S203-2, a determination is made as to whether the uniform deviation value U is less than the constant K_RemoveLink. [00061] In at least one embodiment, step S203-2 is performed on each link change by pseudorandomly determining to either remove a link or define a new link by comparing the U value with the constant K_RemoveLink. The value of K_RemoveLink can be set to bias the determination towards either removing an existing link or defining a new link. Experiments indicate that it is desirable if about 30% of the changes consist of removing the link, in which case K_RemoveLink will be set to 0.3. The value of the K_RemoveLink constant may vary depending on the implementation. [00062] If U is less than K_RemoveLink, the link is removed from the characteristic point selected in step S203-3 (This step allows the annealing process to remove a link without inserting another link to replace it, to ensure that further changes possible on the link are achievable.). Otherwise, a characteristic point in the test sample is selected in step S203-4, and a link is inserted between the selected characteristic points in the reference sample and the test sample in step S203-5. In step S203-6, all previously existing links that are crossed by the newly inserted link are removed from the link. In the example shown in FIGURE 9D, a new link 830 crosses three previously existing links, which are removed from the link in accordance with the example process described in FIGURE 9C. [00063] Overall, it is desirable to ensure that sufficient changes are made to the bond to allow the minimum energy state to be reached and to ensure that the temperature is reduced sufficiently to allow the solution to settle to an ideal state. Again, referring to FIGURE 9A, steps S209-S215 are used to determine if the annealing process has reached its end. In the example shown in FIGURE 9A, I_cycle is incremented in step S211 until a maximum value (Max_cycles) is reached (see step S209) and I_step is incremented in step S215 until a maximum value (Max_steps) is reached (see step S213). When I_step is increased in step S215, the temperature (T) of the overall system is also reduced by multiplying T by a cooling factor (K_cool). The number of steps is the number of temperature changes that are made, with the temperature being reduced by the cooling factor at each stage. The number of cycles is the number of changes that are attempted at each temperature level. Values such as Max_cycles, Max_steps and K_cool may vary depending on the implementation. [00064] The annealing process can be made more precise, at the possible expense of processing speed, by using a greater number of cycles and more gradual temperature reductions. In at least one embodiment, annealing parameters (eg, number of cycles, cooling factor for temperature drops) are chosen to acquire adequate accuracy quickly in most cases. However, this can occasionally result in poor bonding between two samples that would otherwise have acceptable bonding if proper annealing had been done. [00065] To help determine whether weak binding is a result of dissimilarity between samples or an inaccurate initial annealing process, a second annealing process can be performed with a different initial seed. An example of a process by which annealing can be repeated is illustrated in FIGURE 9E. In step S301, a uniform deviation is initialized to a fixed value. In step S303, an annealing process is carried out, such as the process shown in FIGURE 9A. In step S305, if a good match is found between the two samples, a determination is made in step S311 that the samples are consistent. Other attributes (eg time values, pressure values, angle values) can also be checked in step S315 to confirm sample consistency. [00066] If a good match is not found at step S305, a check is performed at step S307 to determine whether another annealing attempt will be made. The verification performed at step S307 may involve comparing the number of annealing steps already performed to a maximum value. For example, In at least one embodiment, if 2 annealing attempts have not yet been made, annealing step S303 is repeated without resetting the uniform deviation generator to ensure that the same random sequence is not used in the subsequent annealing step. . Otherwise, with 2 annealing attempts already made, a determination is made at step S313 that the samples are inconsistent. [00067] After annealing has been performed, the resulting bond will include a set of bonds, each with a known energy. However, not all feature points will be linked unless the samples are identical or nearly identical. The bond quality can be evaluated by calculating a proportion (Pl) of the feature points that are bonded and the average bond energy (Em) according to the following equations: where Pl is the proportion of features that are linked, nl is the total number of links, nr is the number of features in the reference sample, and nt is the number of features in the test sample. In modalities that use the above equations to assess link quality, consistent signatures will have high Pl values and low Em values. Conversely, dissimilar samples will have low Pl values and high Em values. [00068] The expected difference in the values of Pl and Em for consistent signatures and inconsistent signatures can be measured empirically. In FIGURE 10, results are shown from a test in which the ratio Pl and the average bond energy Em for a large number of signatures were graphically represented. Each of the plot points in region 1010 in the dashed line is associated with a comparison of samples that are from different people and therefore likely to be inconsistent. Each of the plot points in region 1020 on the dotted line is associated with a comparison of samples that are from the same person and therefore likely to be consistent. [00069] In the example shown in FIGURE 10, a vast majority of data points in region 1010 reflect Pl and Em values associated with inconsistent samples, and a vast majority of data points in region 1020 reflect Pl and Em values associated with consistent samples . There is some overlap between regions 1010 and 1020 in an area labeled "divider line", where the Pl and Em values do not clearly indicate whether the samples are consistent or inconsistent. However, the results in FIGURE 10 show that it is possible, in many cases, to make an initial assessment of whether the test sample and the reference sample are consistent based on manuscript geometry. In at least one embodiment, test samples that are identified as inconsistent at this stage are automatically given a verification score of 0, and no further processing is done to determine whether the test sample is consistent with the reference sample. [00070] While Pl and Em values are effective in measuring link quality in many scenarios, they may not reflect significant differences between a test sample and a reference sample if a substantial portion of the samples are very similar. You can increase the accuracy of the handwriting check by performing an additional check to determine if there is a significant section of unlinked feature points between the test sample and the reference sample. [00071] Again, referring to FIGURE 4, in step S109, a determination is made whether the test sample and the reference sample are a sufficient match. In the example shown in FIGURE 4 if it is determined that the test sample and the reference sample are a sufficient match, in step S109 then further processing is performed (see step S111, described in additional detail below) before transmitting a result of the check in step S113. However, if it is determined that the test sample and the reference sample are not a sufficient match, in step S109, a result that shows the samples as inconsistent can be passed in step S113 without further processing. [00072] The output produced in step S113 can be any output that is suitable for indicating a check result, such as a Boolean value. Alternatively, a different value that allows to indicate more than just a binary or true/false result can be used. In at least one embodiment, the output produced in step S113 comprises a floating point value ranging from 0 (which indicates that the test sample and the reference sample are very different) to 1.0 (which indicates that the test and the reference sample are very similar). [00073] FIGURE 11 illustrates an example of the matching process S109 that includes a count of consecutive unlinked feature points. In the example shown in FIGURE 11, at step S109-1, an initial measurement of binding quality is performed by determining Pl and Em values for binding between a test sample and a reference sample. As mentioned above with respect to FIGURE 10, in step S109-2, if the values of Pl and Em indicate that the test sample and the reference sample are not consistent, process S109 returns a result that indicates that the test sample and the reference sample are not a good match (not consistent), in step S109-5, and further processing in the matching process S109 can be omitted. However, if the values of Pl and Em indicate that the test sample and the reference sample are consistent, in step S109-3 consecutive unbound characteristic points are counted. [00074] FIGURES 12A and 12B represent a test sample and a reference sample, respectively, which can be processed according to the S109 matching process illustrated in FIGURE 11. FIGURE 12A represents an example test sample that has a "Z" shape and FIGURE 12B depicts an example reference sample that has a similar "Z" shape but with an additional loop. Substantial parts of the two samples depicted in FIGURES 12A and 12B are identical or very similar. Thus, a high proportion of the features depicted in FIGURES 12A and 12B can be bound at very low binding energies. The additional loop in the reference sample shown in FIGURE 12B may be unbound, but the overall binding and binding energy may be similar to what would be expected in natural variations between authentic signatures. [00075] The samples represented in FIGURES 12A and 12B are illustrative of a scenario in which the values of Pl and Em may indicate that the test sample and the reference sample are consistent, despite a significant feature missing from the test sample. An additional check for consecutive unbound feature points (as illustrated in FIGURE 11) can be used to increase the accuracy of the matching process. In the illustrative scenario depicted in FIGURES 12A and 12B, the matching process illustrated in FIGURE 11 can be used to determine that the respective samples are not consistent due to the missing feature. [00076] Again, referring to FIGURE 11, in step 109-4, a determination is made whether the unbound feature points are significant. If the unlinked characteristic points are significant, process S109 returns a result that indicates that the test sample and the reference sample are not a good match (not consistent) in step S109-5. If the unbound characteristic points are not significant, process S109 returns a result that indicates that the test sample and the reference sample are a good match (consistent) in step S109-6. [00077] In at least one embodiment, determining whether unbound feature points are significant includes determining whether the count of consecutive unbound feature points in an unbound section is greater than a predetermined NU value. Counts that are greater than NU can be added, and the total length of these counts can be represented as a proportion (referred to as "no proportion" or Pf) of the overall sample length. Counts that are less than or equal to NU can be ignored. The value of NU may vary depending on the implementation. Samples with a value of Pf that exceeds a predetermined value can be considered inconsistent. [00078] Again, referring to FIGURE 4, if a test sample and a reference sample are initially determined to be a sufficient match, in step S109, based on manuscript geometry, further evaluation is performed in step S111 using other parameters of the pen event that are not limited to manuscript geometry. [00079] In at least one embodiment, the further evaluation performed in step S111 comprises non-geometric characteristic matching, which may include analysis of time-related pen event parameters, such as writing speed. Individuals tend to develop a habitual rhythm in the way they write with a pen, which means that pen speed and acceleration tend to be very similar (though not identical) to handwriting (e.g. signatures) done by the same person. Thus, time-related pen event parameters, which differ from geometric features that are analyzed in other steps, can be useful in a handwriting verification process (for example, as an adjunct to geometric feature matching). In at least one embodiment, geometric features can be extracted from raw manuscript data, along with elapsed time corresponding to the respective features, which allows comparison of elapsed time values. [00080] FIGURE 13A is a graph illustrating results of comparing elapsed time values corresponding to feature points in two manuscript samples. The results are illustrated in FIGURE 13 as a graphical representation of elapsed time for linked feature points. Each point in the graphical representation corresponds to a link and represents the elapsed time to a feature point on a reference sample (horizontal geometry axis) and the elapsed time to a connected feature point on a test sample (vertical geometry axis). For signatures that are consistent, the time elapsed since the start of the signature must be similar for each pair of linked feature points. [00081] In the example shown in FIGURE 13, the points are graphically represented inside a rectangle that represents the general consistency (by the diagonal slope of the rectangle or by the angle in relation to the horizontal) and the variability (by the narrowest dimension of the rectangle, as indicated by the perpendicular arrows) of the velocity. General consistency, in this context, refers to the total average elapsed time (and therefore the velocity) of the respective samples. In this example, the slope of the rectangle of approximately 1:1 indicates that the samples have a consistent average velocity. Variability, in this context, refers to differences in local changes in velocity. Acceptable limits on overall consistency and velocity variability can be measured by testing signature samples that are known to have been made by the same person. [00082] Again, referring to FIGURE 4, the additional evaluation performed in step S111 may also include the analysis of other parameters, such as pen pressure or pen angles. Pen pressures can be reliably compared by evaluating the state (eg rising, falling or stationary) of the pressure at each characteristic point. Pressure consistency can be calculated as a proportion Pp of connections that have the same pressure state at each end of the connection. An acceptable value of Pp can be determined by measuring the pressure variation on a large number of signature samples that are known to be the same person. [00083] Typically, pen pressures are measured as relative values rather than absolute force values. Pressure values are device dependent, with variations in sensitivity occurring even between devices of the same model due to factors such as differences in pen construction, hysteresis and aging materials. Thus, in general, it is not possible to make reliable comparisons between samples using absolute force values, particularly if the same person may have used different insertion devices to provide the samples.<First Pen Pressure Value Comparison Method> [00084] In one example, pen pressures can be compared by evaluating the state of pressure at each characteristic, ie, whether the pressure is increasing, decreasing, or stationary at each point. Consistency is then calculated by the proportion Pp of bonds that have the same pressure state at each end. [00085] <Second Pen Pressure Value Comparison Method> [00086] In practice, the first method has been found to be inadequate when the pressure is close to constant for significant periods. When this occurs, it is possible that slight differences will be discovered as different signal gradients, resulting in large errors. [00087] Pen pressures can be reliably compared by calculating Pi, the pressure diagram area - time from signature start to characteristic i, normalized as a ratio of pressure area - overall time to signature integrity , according to the following equation: where Pi is the pressure-time diagram ratio to characteristic i, p is the pen pressure, t is the time from signature start to characteristic i, and T is the total signature time. FIGURE 13B is a diagram explaining the above equation. The X axis shows the elapsed time since the signature started and the Y axis shows the pressure recorded by the pen tip. The filled region in a dotted circle area shows the sum of pen pressure p(t) from time 0 to time t. [00088] FIGURE 13C is a graph illustrating results of comparing pressure - time values corresponding to characteristic points in two samples of the manuscript. The results are illustrated in FIGURE 13C as a graphical representation corresponding to pressure - time values for linked feature points. Each point in the graphical representation corresponds to a link and represents the ratio of the pressure-time graph to a characteristic point on a reference sample (horizontal geometric axis) and the ratio of the pressure-time graph to a characteristic point linked in a test sample (vertical geometric axis). For signatures that are consistent, the pressure-time graph ratio should be similar for each pair of linked feature points. Please note that the last point of the graph, by definition, will always be (1.0, 1.0). [00089] FIGURE 14 is a flowchart of an example post-processing process that can be used after a determination has been made regarding whether a test sample is consistent or inconsistent with a reference sample. In the example process illustrated in FIGURE 14, if a test sample is determined to be consistent with a reference sample at step S401, the test sample can be added to a repository as another reference sample at step S403. When a test sample is found to be consistent with a reference sample, the test sample can be used to supplement existing reference samples and potentially increase the accuracy of future verification processes. Additionally, in the example process illustrated in FIGURE 14, at step S405, the verification result can be transmitted together with separate image data that can be rendered for display. For example, if the manuscript data for the test sample is integrated with image data, an image of the manuscript can be displayed along with an indicator of the result of the verification process (eg whether the manuscript has been verified or not). [00090] FIGURE 15 is a diagram of an illustrative computer system and process for verifying the authenticity of a signature. The particular signature verification techniques that may be used in the system and process depicted in FIGURE 15 may vary from those described herein, depending on the implementation. In the example shown in FIGURE 15, signing is done on a contract in a banking context. [00091] As shown in FIGURE 15, a server 1510 provided by ABC Bank provides an original contract document to a manuscript inserter 10 for signature. Inserter 10 generates signature data in response to a user's signature of the contract and integrates the signature data with an image of the signed contract. Inserter 10 provides the embedded file to a signature verification server 700B on a network 20 (eg, the Internet). The handwriting input device 10 may be implemented as a dedicated handwriting collection device or as a general purpose device such as a suitably configured smart phone or tablet computer with pen input capability. [00092] In the example shown in FIGURE 15, server 1510 (or some other server controlled by ABC Bank) provides a user ID to signature verification server 700B. The 700B signature verification server uses the user ID to select an appropriate reference signature from the 760 repository for use in a verification process. [00093] FIGURE 16 represents a table 1690 that the signature verification server 700B can use to look up a reference signature based on one or more identifiers (e.g., a service ID (which identifies the entity that provided the document). for signature) and the user ID provided by the 1510 server). The service ID may be provided by server 1510, inserter 10, or some other entity. As shown in table 1690, the reference signature can be in any language, and more than one reference signature can be available to a single user. [00094] Again, referring to FIGURE 15, the signature verification server 700B verifies the signature provided by the inserter 10 by comparing the signature with the reference signature. The signature verification server 700B returns a verification result to the inserter 10, which indicates whether the signature is verified ("OK") or unverified ("NG"). [00095] FIGURE 17 is a diagram of an illustrative computer system and handwriting-based user authentication process that can be used to authenticate a user based on the user's signature. The computer system and user authentication process based on illustrative handwriting depicted in FIGURE 17 may use handwriting verification techniques described herein or other handwriting verification techniques for user authentication, depending on the implementation. [00096] In the example shown in FIGURE 17, an inserter 10 generates test signature data in response to a user attempting to sign into a computer system by signing with a pen/style device 11. Inserter 10 provides subscription data along with a user device ID (e.g. a style ID associated with pen/style device 11) to a subscription registration service 1720 on a network 20 (e.g. the Internet) . [00097] In the example shown in FIGURE 17, the subscription registration service 1720 fetches a "Name ID" based on the test signature data provided by the insertion device 10. The subscription registration service 1720 may use a process verification process to determine whether the test signature data provided by inserter 10 is consistent with corresponding reference signature data associated with one or more reference signatures stored in database 1730. [00098] FIGURE 18A is an illustration of a table that can be used to look up an identifier (eg, in database 1730) based on signature data. In particular, FIGURE 18A depicts a table 1890 that the subscription registration service 1720 can use to look up a name ID (e.g., a location ID combined with a service ID) based on the subscription data provided by the device. 10. The location ID can be associated with a user and the service ID can be associated with a 1710 device ID service (see FIGURE 17). [00099] Again, referring to FIGURE 17, the subscription enrollment service 1720 sends the User Device ID and Name ID (e.g. Location ID plus Service ID) to the Device ID Service 1710 FIGURE 18B is an illustration of a table that can be used to look up a reference device ID (eg, a style ID) based on other identifiers. In particular, FIGURE 18B represents a table 1892 that the device ID service 1710 can use to look up a reference device ID that corresponds to the name ID provided by the subscription registration service 1710. If the reference device ID in the table entry matches the user's device ID sent by the subscription registration service 1720, the device ID service 1710 can resend authentication information to the inserter 10. In the example shown in FIGURE 17, the authentication information includes a "success" or "failure" authentication result. In addition to the success/failure result, the authentication information transmitted in this example may include (for example, in the case of "success") a user ID and password that may be required to complete the login process. [000100] FIGURE 19A is a diagram of another illustrative handwriting-based user authentication process on a properly configured computing system. In this example, the user authentication process is a login process that is used to provide access to a social networking service called "Book+"; however, other services can be accessed in a similar manner. [000101] As shown in FIGURE 19A, a handwriting input device 10 activates a login process associated with a service (e.g., by browsing a web page associated with the service using a browser application or by activation of a dedicated application associated with the service). Device 10 captures signature data (e.g., in a signature area 1902), which can be generated in response to a user signing with a pen/style device (not shown). Device 10 sends the signature data as test signature data to be verified. Test subscription data is sent along with a device ID associated with the device 10 and/or a pen/style device and a service ID (e.g. "Book+") associated with the service to a registration service by subscription 1920 on a network 20 (for example, the Internet). [000102] In the example shown in FIGURE 19A, subscription registration service 1920 verifies test signature data (e.g., by comparing test signature data with reference signature data in accordance with techniques described herein or other techniques) and obtains authentication information (eg, user ID and password information) based at least in part on the verification results. The 1920 subscription registration service is implemented as a "one-pass" registration service that allows a user to be authenticated using a single instance of user input (a signature), rather than requiring multiple instances of user input (for example, a user ID and password) are provided by the device 10. [000103] FIGURE 19B represents a 1990 table illustrating information that can be provided to a subscription registry service (e.g., 1920 registry service) to authenticate a user, along with authentication information (e.g., user ID and password) which can be returned from the subscription registration service if user authentication is successful. In the example shown in FIGURE 19B, a pen/device ID, signature data associated with a test signature to be verified, and a service ID (e.g. "Book+") can be received from a user device ( for example, insertion device 10) and used to authenticate a user of the user device against the service identified by the service ID. [000104] Again, referring to FIGURE 19A, the subscription registration service 1920 can use information, such as the device ID and service ID, to look up one or more reference subscriptions associated with a user in the database 1930. The signature record service 1920 can then use a handwriting verification process to determine whether the signature data provided by the inserter 10 is consistent with the referencing signature(s). Once the user has been authenticated with the subscription registration service 1920, the service 1920 can transmit the user ID and password to device 10. The user ID and password can then be used to complete the process of login. For example, device 10 can automatically fill in the username (eg, an e-mail address) and password in appropriate fields in a user interface. [000105] In practice, any collection of information that allows a user to be reliably authenticated by a subscription registry service (eg, 1920 subscription registry service) can be used for user authentication. The particular information that can be used to search a particular user in a database (e.g., 1930 database) may vary depending on factors such as the information that is transmitted to the subscription registration service, the information that is stored in the database and the way the database is designed. [000106] For security purposes, any information regarding handwriting verification and related to user authentication processes (e.g. handwriting data, device identifiers, service identifiers, authentication information, etc.) may be encrypted (e.g. using symmetric (e.g. shared secret key) or asymmetric (e.g. public key) encryption). Encrypted information can be decrypted before further processing is performed on the basic information. For example, encrypted test signature data can be decrypted before comparing test signature data with reference signature data. [000107] Unless otherwise specified in the context of specific examples, techniques and tools described may be implemented by any suitable computing devices, including but not limited to laptop computers, desktop computers, smart phones, tablet computers and/or congeners. For example, while handwriting data generation in some examples described herein may require certain hardware characteristics, such as an electronic pen, the raw data generated by an electronic pen can be transmitted to suitably configured general-purpose computing devices and processed. by them, including, but not limited to, laptop computers, desktop computers, smart phones, tablet computers and/or the like. [000108] Some of the features described here can be implemented in the context of a client-server relationship. In this context, server devices may include suitable computing devices configured to provide information and/or services described herein. Server devices may include any suitable computing devices, such as dedicated server devices. Server functionality provided by server devices may, in some cases, be provided by software (eg, compute instances or virtualized application objects) running on a computing device that is not a dedicated server device. The term "client" may be used to refer to a computing device that obtains information and/or accesses services provided by a server over a communication link. However, designating a particular device as a client device does not necessarily require the presence of a server. At various times, a single device can act as a server, a client, or both a server and a client, depending on context and configuration. Actual physical locations of clients and servers are not necessarily important, but locations can be described as "local" for a client and "remote" for a server to illustrate a common usage scenario in which a client is receiving information provided by a server. in a remote location. [000109] FIGURE 20 is a block diagram illustrating aspects of an exemplary computing device 2000 suitable for use in accordance with embodiments of the present description. The following description is applicable to servers, personal computers, cell phones, smart phones, tablet computers, embedded computing devices and other devices currently available or not yet developed that can be used in accordance with embodiments of the present description. [000110] In its most basic configuration, the computing device 2000 includes at least a processor 2002 and a system memory 2004 connected by a communication bus 2006. Depending on the exact configuration and device type, the system memory 2004 can be volatile or non-volatile memory, such as read-only memory ("ROM"), random access memory ("RAM"), EEPROM, flash memory, or other memory technology. Those of skill in the art and still others will recognize that system memory 2004 typically stores data and/or program modules that are immediately accessible and/or are actually operated by processor 2002. In this particular, processor 2002 may serve as a computing center of computing device 2000 for instruction execution support. [000111] As further illustrated in FIGURE 20, computing device 2000 may include a network interface 2010 comprising one or more components for communicating with other devices on a network. Embodiments of the present description can access basic services that use the 2010 network interface to perform communications using common network protocols. Network interface 2010 may also include a wireless network interface configured to communicate via one or more wireless communication protocols, such as WiFi, 2G, 3G, 4G, LTE, WiMAX, Bluetooth and/or the like. [000112] In the exemplary embodiment shown in FIGURE 20, the computing device 2000 also includes a storage medium 2008. However, services can be accessed using a computing device that does not include a device for persisting data to a local storage medium. Therefore, the 2008 storage media depicted in FIGURE 20 is optional. In any event, 2008 storage media may be volatile or non-volatile, removable or non-removable, implemented using any technology capable of storing information, such as, but not limited to, a hard disk, solid state drive, CD ROM, DVD , or other disk storage, magnetic tape, magnetic disk storage and/or the like. [000113] As used herein, the term "computer readable media" includes volatile and nonvolatile and removable and nonremovable media implemented in any method or technology capable of storing information, such as computer readable instructions, data structures, modules program or other data. In this regard, system memory 2004 and storage media 2008 depicted in FIGURE 20 are examples of computer readable media. [000114] For ease of illustration, and by virtue of not being important to an understanding of the claimed subject matter, FIGURE 20 does not show some of the typical components of many computing devices. In this regard, computing device 2000 may include input devices such as a keyboard, numeric keypad, mouse, trackball, microphone, video camera, touch pad, touch screen, style and/or the like. Such inserters may be coupled to the computing device 2000 by wired or wireless connections, including RF, infrared, serial, parallel, Bluetooth, USB, or other suitable connection protocols using wireless or physical connections. [000115] In any of the examples described, data may be captured by input devices and transmitted or stored for further processing. Processing may include encoding streams of data, which may subsequently be decoded for presentation by transmission devices. Media data may be captured by multimedia input devices and stored by saving streaming media data as files on computer-readable storage media (for example, in memory or persistent storage on a client device, server, administrator device, or some other device). Insertion devices may be separate from and communicatively coupled to the computing device 2000 (e.g., a client device), or they may be integral components of the computing device 2000. In some embodiments, multiple inserters may be combined into a single device. multi-function insert (for example, a video camera with a built-in microphone). Any suitable insertion device both currently known and developed in the future can be used with the systems described herein. [000116] The computing device 2000 may also include transmission devices such as a display, speakers, printer, etc. Streaming devices may include video streaming devices, such as a viewfinder or touch screen. Streaming devices may also include audio streaming devices, such as external speakers or headphones. The transmission devices may be separate and communicatively coupled to the computing device 2000, or they may be integral components of the computing device 2000. In some embodiments, multiple transmission devices may be combined into a single device (e.g., a display with loudspeakers). built-in speakers). Any suitable transmission device both currently known and developed in the future can be used with the systems described. [000117] Overall, the functionality of the computing devices described here can be implemented in computing logic embedded in hardware or software instructions, which can be written in a programming language, such as C languages. E--. EQDQN. LCXC™. RJR Perl, JVON. EU. LcxcUetkrV. VBUetkrV, CURZ. OketquqhV oPGV™. Vcku like C# and/or the like. Computer logic can be compiled into executable programs or written in interpreted programming languages. In general, the functionality described here can be implemented as logic modules that can be duplicated to provide greater processing power, merged with other modules or divided into submodules. Computing logic may be stored on any type of computer-readable media (for example, non-temporary media, such as memory or storage media) or computer storage device and be stored and executed by one or more computer processors. general-purpose or special-purpose, thereby creating a special-purpose computing device configured to provide the functionality described herein. Extensions and Alternatives [000118] Many alternatives to the systems and devices described here are possible. For example, individual modules or subsystems can be separated into additional modules or subsystems or combined into fewer modules or subsystems. As another example, modules or subsystems may be omitted or supplemented with other modules or subsystems. As another example, functions that are indicated to be performed by a particular device, module or subsystem may instead be performed by one or more other devices, modules or subsystems. While some examples of the present disclosure include descriptions of devices that comprise specific hardware components in specific arrangements, techniques and tools described herein may be modified to accommodate different hardware components, combinations or arrangements. Additionally, while some examples of the present description include descriptions of specific usage scenarios, the techniques and tools described herein may be modified to accommodate different usage scenarios. Functionality that is described as implemented in software may instead be implemented in hardware, or vice versa. [000119] Many alternatives to the techniques described here are possible. For example, processing stages in the various techniques can be separated into additional stages or combined into fewer stages. As another example, processing stages in the various techniques may be omitted or supplemented with other processing techniques or stages. As another example, processing stages that are described as occurring in a particular order may instead occur in a different order. As another example, processing stages that are described as being performed in a series of steps may instead be handled in a parallel manner, with multiple software modules or processes concurrently handling one or more of the illustrated processing stages. As another example, processing stages that are indicated to be performed by a particular device or module may instead be performed by one or more other devices or modules. [000120] The principles, representative modalities and modes of operation of the present description have been described in the exposed description. However, aspects of the present disclosure that are intended to be protected should not be construed as limited to the particular embodiments described. Additionally, the embodiments described herein should be considered illustrative rather than restrictive. It will be appreciated that variations and changes may be made by others, and equivalent employees, without departing from the spirit of the present description. Accordingly, it is expressly intended that all such variations, changes and equivalents fall within the spirit and scope of the claimed subject matter.
权利要求:
Claims (7) [0001] 1. A method for verifying handwriting performed on a computer system comprising: obtaining a test sample (810) of handwriting that contains a plurality of available parameters, wherein the plurality of available parameters comprises geometric parameters and one or more non-geometric parameters to extract the geometric parameters of the plurality of available parameters; based on the geometric parameters, deriving geometric features comprising an x-position value and a y-position value for each of a plurality of uniformly distributed feature points in the test sample (810) of manuscript; perform first feature correspondence between geometric features of the test sample (810) of manuscript and geometric features of a reference sample (820); determine a result of the manuscript verification based, at least in part, on the feature match ; and transmit the handwriting check result, wherein the first feature match comprises discovering mappings between one or more of the evenly distributed feature points in the test sample (810) and one or more uniformly distributed feature points in the reference sample (820). ), wherein the mappings comprise links established between corresponding feature points in a test sample (810) and a reference sample (820) characterized by the fact that the first feature match additionally includes an initial measure of link quality by determining of Pl and Em values for bonding between a test sample and a reference sample, where Pl is the proportion of features that are bonded and Em is the average bond energy, where bond energy is measured in terms of the differences between values of position x and position y of the linked feature points, where, if the value of the ratio (Pl) and the average binding energy (Em) indicate that the test sample (810) and the reference sample (820) are consistent, where consistent samples have high Pl values and low Em values, counting a further number of consecutive unlinked feature points and wherein the determination is further based on the number of consecutive unlinked feature points, wherein the method further comprises a second feature match (S111) comprising evaluating an unlinked parameter geometric, wherein the handwriting check result is further based on the second feature match (S111), wherein the non-geometric parameter comprises a time-related parameter that includes at least one velocity, acceleration, or pen pressure value. [0002] 2. Method according to claim 1, characterized in that the geometric parameters include x coordinate values, y coordinate values, and in which the geometric features further comprise direction values and/or curvature values. [0003] 3. Method according to claim 1 or 2, characterized in that the first characteristic match comprises a simulated annealing process. [0004] 4. Method according to claim 3, characterized in that the simulated annealing process comprises: defining a new connection (830) between a characteristic point selected in the reference sample (820) and a characteristic point selected in the sample test (810); and remove all previously existing links that are crossed by the new link (830). [0005] 5. Method according to claim 3 or 4, characterized in that the simulated annealing process comprises: selecting a characteristic point in the reference sample (820); generating a pseudorandom value; comparing the pseudorandom value with a constant; and based on the comparison, determine whether (a) a link is removed from a selected point in the reference sample (820), or (b) a new link is defined between the selected feature point in the reference sample (820) and a characteristic point selected on the test sample (810). [0006] 6. Method according to claim 5, characterized in that the determination step is biased towards the definition of a new bond (830) in relation to the removal of an existing bond based on the value of the constant. [0007] Method according to claim 1, characterized in that the time-related parameter comprises a pen pressure value, and wherein the second characteristic correspondence additionally includes a step of comparing an area of a pressure diagram - time from a starting point of the reference sample to an i-th point of the reference sample (820) and from an area of a pressure diagram - time from a starting point of the test sample (810 ) to an i-th point of the test sample (810).
类似技术:
公开号 | 公开日 | 专利标题 BR102014027735B1|2022-02-15|Methods for handwriting verification and for user authentication US10015166B2|2018-07-03|Gesture-based signature authentication EP3069297B1|2019-01-02|Identity authentication by using human biological characteristics US8942420B2|2015-01-27|Detecting embossed characters on form factor CN105100108B|2018-04-13|A kind of login authentication method based on recognition of face, apparatus and system US9619697B2|2017-04-11|Identity authentication platform US9202035B1|2015-12-01|User authentication based on biometric handwriting aspects of a handwritten code JP6667800B2|2020-03-18|Handwritten signature authentication system and method JP6480710B2|2019-03-13|Handwritten data verification method and user authentication method Khan et al.2015|Multi-factor authentication on cloud US10552596B2|2020-02-04|Biometric authentication US10878071B2|2020-12-29|Biometric authentication anomaly detection JP2019117579A|2019-07-18|Biometric authentication system Gonçalves et al.2015|Time/space based biometric handwritten signature verification Wang et al.2016|A Password System Based on Sketches JP2017217094A|2017-12-14|Attribution guarantee system, electronic pen, attribution guarantee device, and attribution guarantee method CN113177850A|2021-07-27|Method and device for multi-party identity authentication of insurance Mallasvik2010|Observation-Resistant Multifactor Multimodal Authentication
同族专利:
公开号 | 公开日 US20150131874A1|2015-05-14| US20160070951A1|2016-03-10| US9235748B2|2016-01-12| HK1204820A1|2015-12-04| EP2874099B1|2018-07-18| EP2874099A1|2015-05-20| BR102014027735A2|2015-09-15| CN104636715A|2015-05-20| US9747491B2|2017-08-29| SG10201407479UA|2015-06-29| CN104636715B|2020-01-03|
引用文献:
公开号 | 申请日 | 公开日 | 申请人 | 专利标题 US4453267A|1979-03-19|1984-06-05|Ncr Corporation|Signal compression apparatus and method| US4495644A|1981-04-27|1985-01-22|Quest Automation Public Limited Company|Apparatus for signature verification| JPH0145666B2|1982-04-12|1989-10-04|Mitsubishi Electric Corp| JPS59192A|1982-06-25|1984-01-05|Tokyo Shibaura Electric Co|Private collator| US4656662A|1983-07-18|1987-04-07|Ncr Corporation|Personal identification method and apparatus| US4701960A|1983-10-28|1987-10-20|Texas Instruments Incorporated|Signature verification| JPH0527915B2|1985-07-03|1993-04-22|Oki Electric Ind Co Ltd| US4724542A|1986-01-22|1988-02-09|International Business Machines Corporation|Automatic reference adaptation during dynamic signature verification| GB2200233B|1987-01-20|1990-10-10|Nat Res Dev|Method and apparatus for capturing information in drawing or writing| US5054088A|1989-09-20|1991-10-01|International Business Machines Corporation|Signature verification data compression for storage on an identification card| US5109426A|1989-11-10|1992-04-28|National Research Development Corporation|Methods and apparatus for signature verification| US5091975A|1990-01-04|1992-02-25|Teknekron Communications Systems, Inc.|Method and an apparatus for electronically compressing a transaction with a human signature| US5038392A|1990-02-12|1991-08-06|International Business Machines Corporation|Method and apparatus for adaptive image processing by recognizing a characterizing indicium in a captured image of a document| US5101437A|1991-02-11|1992-03-31|Ecole Polytechnique|Method and apparatus for comparing a test handwritten signature with a reference signature by using information relative to curvilinear and angular velocities of the signature| US5285506A|1991-04-30|1994-02-08|Ncr Corporation|Method of recording a handwritten message| US5111512A|1991-05-14|1992-05-05|At&T Bell Laboratories|Method for signature verification| US6487310B1|1991-09-06|2002-11-26|Penop Ltd.|Signature matching| US6128409A|1991-11-12|2000-10-03|Texas Instruments Incorporated|Systems and methods for handprint recognition acceleration| JP2800538B2|1992-03-23|1998-09-21|日本電気株式会社|Variable-length bit string processor| US5699445A|1992-04-10|1997-12-16|Paul W. Martin|Method for recording compressed data| EP0567680B1|1992-04-30|1999-09-22|International Business Machines Corporation|Pattern recognition and validation, especially for hand-written signatures| WO1994004992A1|1992-08-20|1994-03-03|Communication Intelligence Corporation|A method for dynamic reconstruction of handwritten data| US5528699A|1992-11-24|1996-06-18|Nippondenso Co., Ltd.|Information medium recognition device| JPH06162268A|1992-11-24|1994-06-10|Nippondenso Co Ltd|Sign recognizing device| US5454046A|1993-09-17|1995-09-26|Penkey Corporation|Universal symbolic handwriting recognition system| US5434928A|1993-12-06|1995-07-18|At&T Global Information Solutions Company|Method for verifying a handwritten signature entered into a digitizer| EP0737342A4|1993-12-17|1996-11-06| US5699456A|1994-01-21|1997-12-16|Lucent Technologies Inc.|Large vocabulary connected speech recognition system and method of language representation using evolutional grammar to represent context free grammars| US5577135A|1994-03-01|1996-11-19|Apple Computer, Inc.|Handwriting signal processing front-end for handwriting recognizers| GB9409773D0|1994-05-13|1994-07-06|Atomic Energy Authority Uk|Identification system| US5687254A|1994-06-06|1997-11-11|Xerox Corporation|Searching and Matching unrecognized handwriting| US5544255A|1994-08-31|1996-08-06|Peripheral Vision Limited|Method and system for the capture, storage, transport and authentication of handwritten signatures| US6091835A|1994-08-31|2000-07-18|Penop Limited|Method and system for transcribing electronic affirmations| US5528003A|1994-12-14|1996-06-18|International Business Machines Corporation|Data compression for pen stroke input| US5828772A|1995-12-27|1998-10-27|Lucent Technologies Inc.|Method and apparatus for parametric signature verification using global features and stroke-direction codes| US5892824A|1996-01-12|1999-04-06|International Verifact Inc.|Signature capture/verification systems and methods| US6512840B1|1996-05-30|2003-01-28|Sun Microsystems, Inc.|Digital encoding of personal signatures| NO963903D0|1996-09-18|1996-09-18|Gary A Mcconnell|Method of registering validation of a personal signature, compilation of databases for use in the method, an electronic writing device for signature registration and the use of methods and devices| JP3492874B2|1996-12-26|2004-02-03|株式会社デンソーウェーブ|Signature verification system| JPH10240866A|1997-02-24|1998-09-11|Mitsubishi Electric Corp|Character recognition device| WO1999017255A1|1997-10-01|1999-04-08|Cadix Inc.|Method and apparatus for authenticating ic card| US6055592A|1998-02-09|2000-04-25|Motorola, Inc.|Smart card authentication system comprising means for converting user identification and digital signature to pointing device position data and vice versa using lut| US6011873A|1998-04-29|2000-01-04|Penware, Inc.|Method and apparatus for lossless compression of signature data| JP2000163514A|1998-09-25|2000-06-16|Sanyo Electric Co Ltd|Character recognizing method and device and storage medium| US6307955B1|1998-12-18|2001-10-23|Topaz Systems, Inc.|Electronic signature management system| WO2000042563A2|1999-01-13|2000-07-20|Computer Associates Think, Inc.|Signature recognition system and method| US7106888B1|1999-05-25|2006-09-12|Silverbrook Research Pty Ltd|Signature capture via interface surface| WO2001003016A1|1999-06-30|2001-01-11|Silverbrook Research Pty Ltd|Method and system for sensing device registration| US7397949B2|2000-06-21|2008-07-08|Microsoft Corporation|Serial storage of ink and its properties| US6975750B2|2000-12-01|2005-12-13|Microsoft Corp.|System and method for face recognition using synthesized training images| US6549675B2|2000-12-20|2003-04-15|Motorola, Inc.|Compression of digital ink| JP4346814B2|2000-12-27|2009-10-21|キヤノン株式会社|Information processing apparatus and method, computer-readable memory, and program| US6741749B2|2001-01-24|2004-05-25|Advanced Digital Systems, Inc.|System, device, computer program product, and method for representing a plurality of electronic ink data points| US7197167B2|2001-08-02|2007-03-27|Avante International Technology, Inc.|Registration apparatus and method, as for voting| AUPR890201A0|2001-11-16|2001-12-06|Silverbrook Research Pty. Ltd.|Methods and systems | CA2363372A1|2001-11-20|2003-05-20|Wayne Taylor|System for identity verification| US7391906B2|2001-12-05|2008-06-24|Microsoft Corporation|Methods and system for providing image object boundary definition by particle filtering| US6694045B2|2002-01-23|2004-02-17|Amerasia International Technology, Inc.|Generation and verification of a digitized signature| EP1345163B2|2002-03-15|2010-12-29|Computer Sciences Corporation|Methods for analysis of writing in documents| JP2003271966A|2002-03-19|2003-09-26|Fujitsu Ltd|Device, method and program for authentication of hand- written input| JP2003271967A|2002-03-19|2003-09-26|Fujitsu Prime Software Technologies Ltd|Program, method and device for authentication of hand- written signature| JP2003271965A|2002-03-19|2003-09-26|Fujitsu Ltd|Program, method and device for authentication of hand- written signature| GB0223074D0|2002-10-04|2002-11-13|Motion Touch Ltd|Recording writing movements| EP1668670A4|2003-08-22|2009-04-15|Richard C Kim|Method and apparatus for capturing and authenticating biometric information from a writing instrument| AU2004271639B2|2003-09-05|2010-09-23|Gannon Technologies Group|Systems and methods for biometric identification using handwriting recognition| JP4357935B2|2003-11-14|2009-11-04|株式会社東芝|Information processing apparatus and signature data input program| US7190815B2|2004-05-26|2007-03-13|Topaz Systems, Inc.|Method for authenticating an electronic signature| DE102004057157A1|2004-08-21|2006-04-27|Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.|Method and device for detecting a personally executed signature or signature and for recognizing the authenticity of the signature or signature| US7389117B2|2004-10-06|2008-06-17|Sybase 365, Inc.|System and method for message-based access| US20060136731A1|2004-12-21|2006-06-22|Signaturelink, Inc.|System and method for providing an online electronic signature| DE112005003281B4|2004-12-30|2012-02-16|Topaz Systems Inc.|Electronic signature security system| RO121497B1|2005-02-09|2007-06-29|Softwin S.R.L.|Information system and method for the acquisition, analysis and authentication of holograph signature| US7917761B2|2005-03-21|2011-03-29|Microsoft Corporation|Digitally signing an electronic document with a user-entered signature image| WO2006111979A2|2005-04-18|2006-10-26|Belal Lehwany|Apparatus and method for incorporating signature into electronic documents| US8732025B2|2005-05-09|2014-05-20|Google Inc.|System and method for enabling image recognition and searching of remote content on display| JP2006352628A|2005-06-17|2006-12-28|Viva Computer Co Ltd|Digital image generating/transmitting/receiving apparatus and distribution and reproducing system thereof| US7474770B2|2005-06-28|2009-01-06|Beigi Homayoon S M|Method and apparatus for aggressive compression, storage and verification of the dynamics of handwritten signature signals| US20070065021A1|2005-07-14|2007-03-22|David Delgrosso|System for encoding signatures for compressed storage using a signature encoding algorithm| US7529391B2|2005-12-29|2009-05-05|Microsoft Corporation|Signature verification| US8090161B2|2006-06-19|2012-01-03|Christiane Kaplan|Systems and method for signature verification| US20080019575A1|2006-07-20|2008-01-24|Anthony Scalise|Digital image cropping using a blended map| TWI336854B|2006-12-29|2011-02-01|Ibm|Video-based biometric signature data collecting method and apparatus| RO126248B1|2009-10-26|2012-04-30|Softwin S.R.L.|System and method for assessing the authenticity of dynamic holograph signature| WO2013093864A1|2011-12-23|2013-06-27|Prosense Technology Limited|Electronic signature authentication method and system| CN102789576B|2012-06-29|2015-09-09|鸿富锦精密工业(深圳)有限公司|Signature character extraction system and method| CN103258157B|2013-04-18|2016-09-07|武汉汉德瑞庭科技有限公司|A kind of online handwriting authentication method based on finger information and system|US10032065B2|2013-10-25|2018-07-24|Wacom Co., Ltd.|Dynamic handwriting verification, handwriting-based user authentication, handwriting data generation, and handwriting data preservation| WO2015059930A1|2013-10-25|2015-04-30|Wacom Co., Ltd.|Dynamic handwriting verification, handwriting-baseduser authentication, handwriting data generation, and handwriting data preservation| CN105447433B|2014-09-01|2020-01-31|阿里巴巴集团控股有限公司|identity registration method and device| TWI569176B|2015-01-16|2017-02-01|新普科技股份有限公司|Method and system for identifying handwriting track| CN105868590B|2015-01-19|2019-09-10|阿里巴巴集团控股有限公司|A kind of handwriting data treating method and apparatus| JP6828014B2|2015-10-07|2021-02-10|株式会社ワコム|A computer implementation performed by a local computing device communicatively connected to one or more signing devices.| KR101739098B1|2015-12-28|2017-05-24|주식회사 피노텍|Certification system and method using electronic signature in plural terminals| JP6111346B1|2016-01-08|2017-04-05|株式会社スカイコム|Electronic document terminal, signature authentication system, signature authentication method, and program for electronic document terminal| CN105631297A|2016-01-13|2016-06-01|青岛海信移动通信技术股份有限公司|Method and device for multi-user unlocking| JP3205397U|2016-05-12|2016-07-21|協立技研株式会社|Drying bracket support| US11095639B2|2017-05-11|2021-08-17|Synergex Group|Methods, systems, and media for authenticating users using biometric signatures| US11017258B2|2018-06-05|2021-05-25|Microsoft Technology Licensing, Llc|Alignment of user input on a screen| CN110069969B|2018-07-03|2021-10-19|电子科技大学|Authentication fingerprint identification method based on pseudorandom integration| JP2020067696A|2018-10-22|2020-04-30|株式会社ワコム|Signature verification apparatus, system, method and program| US20200327307A1|2019-04-11|2020-10-15|Ricoh Company, Ltd.|Handwriting input apparatus, handwriting input method, program, and input system|
法律状态:
2015-09-15| B03A| Publication of a patent application or of a certificate of addition of invention [chapter 3.1 patent gazette]| 2018-11-06| B06F| Objections, documents and/or translations needed after an examination request according [chapter 6.6 patent gazette]| 2020-04-22| B06U| Preliminary requirement: requests with searches performed by other patent offices: procedure suspended [chapter 6.21 patent gazette]| 2021-12-28| B09A| Decision: intention to grant [chapter 9.1 patent gazette]| 2022-02-15| B16A| Patent or certificate of addition of invention granted [chapter 16.1 patent gazette]|Free format text: PRAZO DE VALIDADE: 20 (VINTE) ANOS CONTADOS A PARTIR DE 06/11/2014, OBSERVADAS AS CONDICOES LEGAIS. |
优先权:
[返回顶部]
申请号 | 申请日 | 专利标题 US14/080,723|US9235748B2|2013-11-14|2013-11-14|Dynamic handwriting verification and handwriting-based user authentication| US14/080,723|2013-11-14| 相关专利
Sulfonates, polymers, resist compositions and patterning process
Washing machine
Washing machine
Device for fixture finishing and tension adjusting of membrane
Structure for Equipping Band in a Plane Cathode Ray Tube
Process for preparation of 7 alpha-carboxyl 9, 11-epoxy steroids and intermediates useful therein an
国家/地区
|