• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    SUMMARY The invention relates to an automated cash register (1) comprising a classification device (2) for identifying goods (3). The classification device (2) comprises a weight sensor (4) for weighing the product (3), a memory unit (5) comprising information on one or more products and a processor (6) connected to the memory unit (5) and the weight sensor (4). The memory unit (5) comprises one or more first signatures (7) connected to the Classifying device (2) comprising a first NIR sensor (7) connected to from a NIR sensor a corresponding commodity identity. The processor (6) arranged to, when a commodity ( 3) placed before, on or after the weight sensor (4), create a second signature linked to the item (3). The processor (6) compares the second signature with the first signature to identify the item (3) as an item identity in the memory unit (5) and uses the weight and item identity of the item (3) to determine the price of the item (3). (Figure 3)
    公开号:SE1051090A1
    申请号:SE1051090
    申请日:2010-10-19
    公开日:2012-01-09
    发明作者:Magnus Toernvall；Carl Von Sydow；Johan Moeller；Erik Kooi；Hugo Boiten
    申请人:Itab Scanflow Ab；
    IPC主号:
    专利说明:

    Thus, classification devices for cash registers have long been known, but none of the previously known devices are automated to handle different types of goods such as fruit and packaging and at the same time arranged to provide an optimally high level of security with regard to identification but with minimal utilization. of sensor resources.
    DISCLOSURE OF THE INVENTION In the light of the prior art, there is a need for an improved cash register for automatic identification of goods where the number of incorrect identifications goes towards zero, but where the sensor resources are optimally utilized in order to save process power while maintaining a high process speed.
    The present invention aims to solve the problem by means of an automated cash register comprising a classification device for identifying goods.
    The classification device comprises a weight sensor for weighing the product, a memory unit comprising information about one or more products, a processor connected to the memory unit and the weight sensor, and a first hereinafter referred to as NIR sensor connected to the processor. The memory unit comprises one or more first signatures created infrared spectroscopy sensor, by the first NIR sensor or another NIR sensor, which first signature or signatures are each linked to a corresponding commodity identity. The first signatures can be created directly at the cash register by using the first NIR sensor, a second NIR sensor or by loading the memory with signatures created by a NIR sensor that is not connected to the cash register.
    When a NIR sensor is used on a particular type of product, e.g. a certain type of apple, a first signature is obtained which can be connected to the product and which in the memory unit can be named with a certain product identity which, e.g. the name of the product. Each type of item provides a unique first signature that can be linked to the item's identity. The first NIR sensor is arranged to, when an item is placed before, on or after the weight sensor, create a second signature connected to the item. The processor is then arranged to compare the second signature with the first signature in order to identify the product as a product identity present in the memory unit. The cash register is arranged to weigh the product via the weight sensor before, during or after the second signature has been created. The weight of the product is then used by the processor together with the product identity to determine the price of the product.
    An advantage of the invention is that the cash register can automatically identify all kinds of goods without the customer having to identify the goods before the cash register, e.g. by pasting on a barcode. The NIR sensor is particularly valuable for identifying fruit and vegetables, as well as certain types of bulk goods, as these goods previously required the customer to identify the product and then label it because sensors using cameras and imaging could not determine the product's identity.
    The weight sensor advantageously comprises a transport path which automatically transports the product and weighs it. The customer places the product on the conveyor belt, which either weighs and then transports, or transports, stops and weighs, and then transports the product further.
    As mentioned earlier, the first NIR sensor can be arranged at the checkout counter before, during or after weighing. The fastest way, however, is for the first NIR sensor to identify the product while the transport route is stationary and the product is being weighed.
    According to an embodiment of the invention, as a complement to the NIR sensor and the weighing unit, the cash register can be equipped with one or more additional sensors which, if used according to the invention, give the advantage of increasing security when identifying the product but with minimal use of resources and thus time and energy. It should be mentioned here that an item should be identified in less than a second in order for an automatic checkout counter to be perceived as user-friendly by customers. Thus, the present invention also aims to solve the problem of optimal utilization of resources at several sensors by utilizing the sensors according to certain predetermined combinations which provide high security in terms of identification of the product as well as high process speed.
    The combinations also give the advantage that when a given combination is fulfilled, i.e. that the sensor or sensors in the combination gives a positive effect on identification, the other sensors can be disconnected or steered towards identification of another product, which provides an optimization of the process resources.
    The embodiment with a plurality of sensors is thus built on a number of predetermined combinations, including subsets of existing sensors, where it is sufficient for one of the predetermined combinations to give a positive result. The sensors can be switched on, i.e. activated, in sequences to find advantageous combinations or subsets of or all sensors may be active until one of the combinations gives a positive result.
    By positive result is meant here that all sensors in the combination have detected and identified a predetermined property of a product, which properties in the combination together give an identity of a product. the identity can be determined by checking a database containing properties of a number of goods. Examples of properties are weight, size, color, shape, contour, marking with barcode and / or text and / or figure and / or pattern.
    According to always a weight sensor and a NIR sensor as above and one or more of an embodiment, the classification device comprises contour sensor and / or a bar code sensor and / or a symbol reading sensor using optical character recognition and (machine) text interpretation and / or a color texture sensor and / or a color histogram sensor and / or a VIS sensor The symbol reading sensor is hereinafter referred to as OCR, which is a commonly known abbreviation of the English "Optical Character Recognition". VIS sensor is a spectrometer comprising a light source and a VIS camera, hereinafter referred to as VIS sensor, the VIS sensor 10 senses wavelengths from about 200nm to 1100nm. The spectrum thus has an overlap with the wavelength of visible light ranging from 400nm to 660nm. In the device according to the invention, experiments have shown that and / or a color histogram sensor and a VIS sensor do not work satisfactorily as the VIS classification device comprising the color texture sensor sensor operates in the whole frequency range 200nm-1100nm because there is a connection between the color sensors and the VIS sensor light, ie 400nm-660nm.
    The VIS sensor according to the invention is therefore active in the ranges from 200nm to 400nm and from 660nm to 1100nm as the color texture sensor and / or the color histogram sensor. However, if the color texture sensor and combined with the color histogram sensor are disconnected, the VIS sensor can operate in the entire frequency range 200nm-1100nm as there will be no conflict. The processor is programmed to control the sensors to obtain optimal power of the classification device. The sensors interact in such a way that, depending on the product identified, if the sensors are activated in the following combinations, the remaining sensors, in addition to the weight sensor and the NIR sensor, are allowed or not activated: -weight sensor and contour sensor and OCR, or -contour sensor and OCR, or -weight sensor and OCR, or -weight sensor and color histogram sensor and contour sensor, or -weight sensor and contour sensor and OCR, or -weight sensor and color histogram sensor and contour sensor and color texture sensor , or IO 15 20 25 weight sensor and contour sensor and color texture sensor and OCR or weight sensor and bar code sensor, -OCR only, -VIS sensor in combination with any of the above combinations, or -VIS sensor only An advantage of the invention is that the combinations provides an optimally high level of security with minimal utilization of resources, v which will be explained below.
    The symbol reading sensor is connected to a computer / image processing unit that uses an algorithm that uses information from images from the camera or cameras in the device. For such goods that can be identified unambiguously by symbol reading, it is sufficient that the symbol reading sensor, OCR, identifies a symbol and / or text which in itself uniquely identifies the goods. Examples of such goods that can be identified with only the symbol reading sensor, OCR, are pre-packaged packaging where the customer does not have to perform any action such as filling or other action. As examples of such goods where the symbol reading sensor is not sufficient, can be mentioned certain loose weight goods where the quantity of the goods, i.e. weight, not known. Additional properties of the product may be necessary and may require Symbol reading and / or weight and / or color histogram and / or color texture and / or contour. It should be mentioned here that by "contour" is meant a two-dimensional projection of a three-dimensional object.
    Some goods are thus more difficult to identify than others and depending on the product one or more of the classification devices included SGHSOFGFFIG are required. The weight sensor advantageously comprises a transport scale comprising a transport part and a weighted carriage connected thereto which automatically transports the goods, weighs them and sends information about the weight to the database. In this way, efforts from staff and customers that eliminate the need for manual transport of the product over the scales are eliminated. One or more sensors can be connected to the cash register for controlling the transport scale.
    The contour sensor comprises a camera for still images or moving images and can advantageously be a line camera which reads a horizontally projected surface or a line camera in combination with an object sensor which consists of a vertical light curtain for reading the vertical projection. The contour sensor is connected to a unit for image processing where the contour, i.e. a two-dimensional projection of a three-dimensional object, is checked against the properties of the database.
    The barcode sensor includes a camera for still images or moving images.
    The barcode sensor is connected to a unit for image processing where the barcode is checked against the properties in the database. The symbol reading sensor includes a camera for still images or moving images. The symbol reading sensor is connected to a device for image processing where the symbol is checked against the properties in the database.
    The color texture sensor includes a still or motion picture camera.
    The color texture sensor is connected to an image processing unit where the symbol is checked against the properties in the database. The image processing unit includes an algorithm that calculates where in the image a particular color is located. A common algorithm is the "Weibull color texture algorithm", but other algorithms may be considered.
    The color histogram sensor includes a camera for still images or moving images.
    The color conditions of the image are usually illustrated with the help of a representation, a so-called histogram. A histogram is generated by examining all the pixels in the image, and the number of pixels having a specific color value is added together.
    The above image processing devices may consist of one or more devices and may include one or more computers with software capable of performing the above analyzes. The classification device may comprise one or more cameras included in the above sensors. An example of an advantageous embodiment is that the contour sensor comprises a first camera positioned in such a way that the contour is read off when the product passes the camera. According to the invention, a line camera is suitable because the reading then takes place while the goods are being transported between two conveyor belts or over a transparent surface. It is also suitable that the classification device comprises a second camera and possibly cameras in order to be able to see the product from different angles in order to be able to obtain as much security as possible to detect bar code, text and images. The second camera, and if applicable the additional camera / cameras, is arranged to take a picture or pictures which the image processing unit uses for analysis of color histogram, color texture, OCR and bar code reading. A further alternative is that the classification device comprises only the first camera and the second camera where the second camera is optically connected to an image processing unit analyzing the images from corresponding different angles. number of lenses that see the product from different angles and where The previously mentioned line camera placed between the conveyor belts is, however, the only camera that can capture if the barcode is placed down on Vafan.
    The NIR sensor works in such a way that infrared light illuminates the product and the infrared light reflected from the product is analyzed with respect to phase shift due to surface conditions / surface properties and chemical bonds at the product, which gives rise to a reflection spectrum. NIR sensors are known per se by known technology. 10 15 20 25 30 As mentioned above, NIR is an abbreviation of the English “Near Infrared Spectroscopy” and includes a light source for near infrared light and an NIR camera that can detect near infrared light. Near infrared light is typically of wavelength 850-1750nm. The wavelength has been shown to be suitable for analysis of bulk materials, fruits and vegetables. By "NIR" is thus meant here both the light source and the NIR camera, i.e. the whole NIR device for analysis.
    By analyzing a known product with a NIR sensor, a unique reflection spectrum is obtained that can be connected to the product. The reflection spectrum can either be used directly as a signature linked to the product or the reflection spectrum is processed to give rise to the signature. An item in a store can look different on different occasions, e.g. then an item ages (fruit eventually rots) and the item may be wrapped in one or more plastic bags or the item may be alone or in a group, or be in different orientations; in addition, there are natural variations in the product, etc. In addition, the environment may be different for a checkout counter in different stores, e.g. different amount of light, color, etc. All these parameters mean that a NIR spectrum for a product in a certain environment at a certain time does not certainly look the same as another NIR spectrum for the product in a different environment at another time . In order to be able to use a NIR sensor at a cash register according to the invention, the first signature and the second signature must be so similar that the processor can identify the product in a comparison. It is thus an advantage if the first signature is created in the same environment as the second signature. Since the second signature is created at the cash register during use, it is an advantage if the first signature is created under the same conditions.
    The classification system according to the invention therefore has a self-learning function where the first signature is created by the memory unit being programmed with a commodity identity after which the commodity is run through the cash register under usage-like conditions, i.e. such conditions as apply to the cash register when used against the customer. In order to take account of the mentioned deviations, the product is run several times through the checkout counter and in different variants, e.g. with one or more bags and / or individually or in groups, etc. Each time the item is run through the cash register and a NIR sensor analyzes the item, a first signature is created, which means that each item identity can be linked to a large number. different first signatures so that the processor can thus identify the product by comparison with the second signature and one or more of the first signatures. During learning, the first NIR sensor can be arranged to perform the analyzes, or a second NIR sensor can be connected. learning does not have to be done exactly where the cash register can be used, but can be done elsewhere.
    In creating the first and second signatures, the environment is taken into account in the form of background spectrum, i.e. an empty cash register, or an empty conveyor belt. When analyzing the product, the background spectrum is then known and the processor can take this into account in various ways.
    The line camera in the contour sensor is advantageously used in combination with the NIR camera to provide information about where on the tape the article is located. The NIR camera is movable along the gap between two conveyor belts but needs time on the VIS sensor is a spectrometer that includes a light device suitable for the specified wavelengths and a VIS camera that can detect light in wavelengths between 200nm-1100nm. Like the NIR sensor, the VIS sensor takes advantage of the change in wavelength as the light is partially absorbed by reflected on a product. The VIS sensor is particularly good for analysis of different shades of brown, which makes it suitable for analysis of bread that is normally difficult to classify with any of the other sensors. The different shades of brown are detectable with the VIS sensor The "VIS sensor" thus refers to both the light source and the VIS camera, i.e. the whole VIS device for analysis.
    By analyzing a known product with a VIS sensor, a unique reflection spectrum, VIS spectrum, is obtained, which can be connected to the product.
    The reflection spectrum can either be used directly as a signature linked to the product or the reflection spectrum is processed to give rise to the signature. An item in a store can look different on different occasions, e.g. then an item ages (fruit eventually rots) and the item may be wrapped in one or more plastic bags or the item may be alone or in a group, or be in different orientations; in addition, there are natural variations in the product, etc.
    In addition, the environment may be different for a checkout counter in different stores, e.g. different amount of light, color, etc. All these parameters mean that a VIS spectrum for a product in a certain environment at a certain time does not certainly look the same as another VIS spectrum for the product in a different environment at another time . In order to be able to use a VIS sensor at a cash register according to the invention, a third signature, which constitutes a background signature, and a fourth signature, comprising the background of the product, must be so similar that the processor can identify the product in a comparison. It is thus an advantage if the third signature is created in the same environment as the fourth signature. Since the fourth signature is created at the checkout counter during use, it is an advantage if the third Classification System according to the invention therefore has a self-learning that signature is created under the same conditions. function where the third signature is created by the memory unit being programmed with a commodity identity after which the commodity is run through the cash register under usage-like conditions, i.e. such conditions as apply to the cash register when used against the customer. In order to take account of the mentioned deviations, the product is run several times through the checkout counter and in different variants, e.g. with one or more bags and / or individually or in groups, etc. Each time the item is run through the checkout counter and the VIS sensor analyzes the item, a third signature is created, which means that each item identity can be linked to a large number of different third signatures for the processor in this way be able to identify the product by comparison with the fourth signature and one or more of the third signatures. During learning, the first VIS sensor can be arranged to perform the analyzes, or a second VIS sensor can be connected. learning does not have to be done exactly where the cash register can be used, but can be done elsewhere. 10 15 20 25 12 The VIS sensor may include a fiber cable that transmits light from the item to the VIS camera.
    The NIR sensor may include a fiber optic cable that transmits light from the product to the NIR camera.
    The VIS sensor and the NIR sensor can both be connected to separate fiber cables which are arranged to merge into a common fiber cable which transmits light from the product to the respective VIS camera and NIR camera.
    The classification device may comprise a hand-held bar code reader which is connected to the database. The hand-held bar code reader can be large for being driven on and can be used for goods that are for the transport device.
    Classification device may advantageously include a self-learning function which allows the system to become self-learning. By "self-learning" is meant that all the sensors of the classification device become active for identifying a product that passes the sensors for the first time. The sensors identify properties / characteristics of the product and enter the properties in the database. When the self-learning function is used, the product is already registered in a product register with a predetermined identity, e.g. EAN code, and possible price. The product register is either part of the database or a separate database linked to the database for the product's properties.
    The classification device can be supplemented with a bar code reader connected to the database and can be advantageously used in the self-learning function. The first time the product is run in the classification order, the fixed scanner reads a bar code that is guaranteed to identify the product, which means that the properties detected by the sensors are stored in the database under the correct product identity.
    The sensors can advantageously be placed in whole or in part in a tunnel-like construction which shields a part of the conveyor belt and thereby improves safety by preventing unauthorized persons from the possibility of influencing the classification process.
    DESCRIPTION OF THE FIGURES The invention will be described below in connection with a number of figures in which: Fig. 1 schematically shows a top view of a cash register according to a first example of the invention; Fig. 2 schematically shows a side view of the cash register according to Fig. 1; Fig. 3 schematically shows a top view of a cash register according to a second example of the invention; Fig. 4 schematically shows a side view of the cash register according to Fig. 3.
    Fig. 5 schematically shows a top view of a cash register according to a third example of the invention; Fig. 6 schematically shows a side view of the cash register according to Fig. 5, Fig. 7 schematically shows a top view of a cash register according to a fourth example of the invention; Fig. 8 schematically shows a side view of the cash register according to Fig. 7, DESCRIPTION OF EMBODIMENTS Fig. 1 schematically shows a top view of the cash register according to a first example of the invention. cash counter 1 identification of Figure 1 shows an automated including a classification device 2 for goods 3.
    The classification device 2 comprises a weight sensor 4 for weighing the item 3, a memory unit 5 comprising information about one or more products, a processor 6 connected to the memory unit 5 and the weight sensor 4, and a first infrared spectroscopy sensor 7, hereinafter referred to as NIR- sensor 7 connected to the processor 6. The memory unit 5 comprises one or more first signatures created by the first NIR sensor 7 or another NIR sensor (not shown), which first signature or signatures are each connected to a corresponding commodity identity . The first signatures can be created directly at the cash register by using the first NIR sensor or a second NIR sensor (not shown) or by loading the memory with signatures created by a NIR sensor that is not connected to the cash register 1.
    Figure 1 shows that the weight sensor 4 is placed before the first NIR sensor 7, which means that the first NIR sensor is arranged to create a second signature after the product has been weighed, i.e. placed on the weight sensor and then weighed. The processor 6 is then arranged to compare the second signature with the first signature in order to identify the product 3 as a product identity present in the memory unit 5. The weight of the product is used by the processor together with the product identity to determine the price of the product.
    As mentioned earlier, an advantage of the invention is that the cash register can automatically identify all kinds of goods without the customer having to identify the goods before the cash register, e.g. with a barcode. The NIR sensor is particularly valuable for identifying fruit and vegetables, as well as certain types of bulk goods, as these goods previously required the customer to identify the product and then label it because sensors using cameras and imaging could not determine the product's identity.
    The weight sensor 4 advantageously comprises a transport path 8 which automatically transports the goods and weighs them. The conveyor path 8 comprises a first conveyor belt 9 and a housing 10 on which the conveyor belt rests. The customer here places the goods on the first conveyor belt 9, the road unit 10 weighing the goods and where the first conveyor belt 9 then transports the goods 3 away.
    An alternative is that the first conveyor belt 9 transports the goods 3 to a suitable position, stops and weighs, and then transports the goods 3 further. At the checkout counter 1, sensors are arranged which provide information to the processor for controlling the first conveyor belt 9 and the weighing unit 10.
    The first NIR sensor 7, or a second NIR sensor (not shown) connected to the processor 6, may be arranged to read a product and create the first signature during a learning phase when the product 3 has already been identified in order to be able to be connected to it. first signature.
    Figure 1 shows that the checkout counter 1 comprises an interactive presentation unit 11 connected to the processor 6 for presentation of at least product identity.
    The presentation unit 11 is arranged to be used by a user to approve what is presented. If the first NIR sensor 7 identifies the item 3, an image or text is displayed on the presentation unit 11 and if the user considers that the item matches the item placed in the cash register 1, the user approves. Additional information can be presented, e.g. weight and price, whereby the user accepts what is presented if it is correct.
    Figure 1 shows in addition to the weight sensor 4, the first NIR sensor 7 and the presentation unit 11 a second conveyor belt 12, and a third conveyor belt 13 for transporting the goods 3. The direction of movement of the goods over the conveyor belts is shown in figures 1-8 with the reference letter x and an arrow points in the direction of the direction of movement. The point of several conveyor belts is that the product can be transported to a suitable end area where the product or products can be picked up by the user after payment. Another reason is that the cash register 1 may be designed in such a way that the weight sensor is placed after the first NIR sensor (see Figures 3-8) or that the first NIR sensor may be placed in such a way that the first NIR sensor can analyze the product at the same time as it is weighed. The latter is not shown because in the light of the examples shown in Figures 1-8 it should be obvious how such a placement of the first NIR sensor is made in relation to the weighing unit. Additional reasons for having several conveyor belts are if the cash register is equipped with more sensors. According to an embodiment of the invention, in addition to the first NIR sensor 7 and the weight sensor 4, the cash register 1 can be equipped with one or more additional sensors which, if used according to the invention, give the advantage of increasing the security when identifying the product but with minimal utilization of resources and thus time and energy. It should be mentioned here that an item 3 should be identified in less than a second in order for an automatic cash register to be perceived as user-friendly by customers.
    Thus, the present invention also aims to solve the problem of optimal utilization of resources at several sensors by utilizing the sensors according to certain predetermined combinations which provide high security in terms of identification of the product as well as high process speed.
    The combinations also give the advantage that when a given combination is fulfilled, i.e. that the sensor or sensors in the combination gives a positive effect on identification, the other sensors can be disconnected or steered towards identification of another product, which provides an optimization of the process resources. Although the invention is mainly based on a weight sensor 4 and a NIR sensor 7 as above, Figure 1 shows that the cash register includes a plurality of sensors connected in such a manner a number of predetermined combinations including subsets of existing sensors, sufficient for positive reading, i.e. identification of the product 3. It should be pointed out that the embodiment with additional sensors gives a large number of combinations and is therefore not shown in separate figures for the reason that it would only lead to a large number of figures without a corresponding increased understanding of the invention.
    The sensors can be switched on, i.e. activated, in sequences to find advantageous combinations or subsets of or all of the sensors may be active until one of the combinations gives a positive result, whereby one or more of the redundant sensors are disconnected. By positive result is meant here that all sensors in the combination have detected and identified a predetermined property of a product, which properties in the combination together give an identity of a product. The identity can be determined by checking a database containing properties of a number of goods.
    The database can be stored in the memory unit as previously described. Examples of properties are weight, size, color, shape, contour, marking with barcode and / or text and / or figure and / or pattern.
    According to the embodiment, the classification device comprises, a weight sensor 4, a first NIR sensor 7, a contour sensor 14 and / or a bar code sensor 15 and / or a symbol reading sensor 16 using optical character recognition and (machine) text interpretation and / or a color texture sensor 17 and / or a color histogram sensor 18. The symbol reading sensor 16 is hereinafter referred to as OCR, which is a commonly known abbreviation of the English "Optical Character Recognition". The sensors cooperate in such a way that, depending on the product identified, if the sensors are activated in the following combinations, it is allowed that the remaining sensors can be deactivated or not activated; weight sensor 4 and contour sensor 14 and OCR 16, or contour sensor 14 and OCR 16, or weight sensor 4 and OCR 16, or weight sensor 4 and color histogram sensor 18 and contour sensor 14, or weight sensor 4 and contour sensor 14 and OCR 16, or - weight sensor 4 and color histogram sensor 18 and contour sensor 14 and color texture sensor 17 and OCR 16 and bar code sensor 15, or weight sensor 4 and contour sensor 14 and color texture sensor 17 and OCR 16 or weight sensor 4 and bar code sensor 15, or -OCR only 16. 10 15 20 25 30 The contour sensor 14 may include a still or motion picture camera, but may also include an object sensor. In Figure 1, the contour sensor 14 is shown as an line camera 19 placed in the gap between the first conveyor belt and the second conveyor belt reading a horizontally projected surface, in combination with an object sensor 20 consisting of a vertical light curtain for reading the vertical projection. The contour sensor 14 is connected to a unit for image processing where the contour, i.e. a two-dimensional projection of a three-dimensional object, is checked against the properties of the database.
    Figure 1 shows the object sensor 20 comprising a light curtain device standing vertically at the gap between the first conveyor belt and the second conveyor belt 12. The light curtain device comprises a number of diodes with transmitters on one side of the light curtain device and receivers on the other side.
    Empirically, it has been found that in the order of 32 diodes are suitable and that infrared diodes give a good result. However, the invention is not limited to 32 diodes based on infrared light, but any number and frequency could work as long as the mutual rays of the light curtain are refracted at different heights depending on what the product looks like in order to give information about the shape of the product. As the product moves through the light curtain, a three-dimensional image can be created by reading the light curtain at appropriate times.
    Figure 1 shows that the bar code sensor 15 comprises a still or moving image camera, and that the symbol reading sensor 16 includes a still or moving image camera, and that the color texture sensor 17 includes a still or moving image camera, and that the color histogram sensor 18 includes a still image camera or moving images. The invention is not limited to the use of one or more cameras as long as the corresponding sensors can provide the processor with information which can provide information about the identity of the product.
    A cash register 1 according to any one of the preceding claims, wherein classification device 2 comprises an initial sensor 21 which identifies the product with 100% and which can be used to teach the system by first identifying the classification device 2 where all sensors identify properties 3 and then run the item 3 through the item which is then stored in a database for properties of items.
    In Figure 1, the initial sensor 21 is shown as the bar code reader 15, which is intended for manual use. The initial sensor 21 may, however, consist of some other device which can provide correct information to the memory unit. For example, a user can manually enter the product's product name and other information for each product, e.g. price and / or price per weight. However, the barcode reader or other sensor allows systems to be self-learning in the way that the goods are provided with a barcode or other identifier and then fed into the system that automatically reads the identity and then lets other sensors create their own signatures / recognition markers for the product.
    Figure 1 shows that the classification device comprises a hand-held sensor 22 which identifies the product with 100% and which can be used for products which are too large for the other classification device. The hand-held sensor can advantageously be a bar code reader intended for manual use.
    Fig. 2 schematically shows a side view of the cash register according to Fig. 1.
    Fig. 3 schematically shows a top view of a cash register according to a second example of the invention. Figure 3 shows the same devices as in Figure 1, but with a difference in order of the weight sensor 4 and the first NIR sensor 7. Figure 3 shows that the weight sensor 4 is placed after the first NIR sensor 7. Referring to Figure 1 and 2 shows in figure 3 that the different conveyor belts in the direction of movement of the conveyor belts are arranged one after the other in the following order; the second conveyor belt 12, the third conveyor belt and the first conveyor belt 9 with the road unit. In figure 3, the presentation unit 11, as in figures 1 and 2, is placed adjacent to the weight sensor 4 so that a user can approve the item in connection with the weighing. This is an advantage because the weight of the product is important for the price, which means that the customer perceives a price error in connection with the weighing. The price error could be due to the product being incorrectly identified and the user has at this placement of the weight sensor 4 the opportunity to change to the right product through the presentation unit 11 and then get the right price through new or continued weighing linked to the correct product identity. In Figure 3, the contour sensor 14 is placed between the second 12 and the third conveyor belt 13 and the first NIR sensor 7 between the third conveyor belt 13 and the first conveyor belt 9.
    Fig. 4 schematically shows a side view of the cash register according to Fig. 3.
    Fig. 5 schematically shows a top view of a cash register according to a third example of the invention. Figure 5 shows the same devices as Figures 3 and 4, but with the addition that a camera 23 is placed adjacent to the weighing unit 10 in order to be able to take a picture of the product. The image must be able to be presented to the customer via the presentation unit 11 so that the customer can actively decide whether the first NIR sensor 7 has identified the product correctly. The image can also be used to be presented to a remote controller who can determine if the first NIR sensor has read correctly. In the event that more sensors are connected to the cash register 1, the same reasoning applies that the image can be used by the customer or inspector to see if speeding up robustly, the classification device may include a function in case of uncertainty if the goods' sensors have identified the goods correctly. To process the identification and also make it more identity, where several options are presented to the customer via the presentation unit. The customer can then choose the correct alternative via the presentation unit. In this context, the above image can be used in conjunction with the presentation of the various options to facilitate identification as the stored images of the product may be easier to compare with the image of the item than with the item placed in the checkout counter.
    Fig. 6 schematically shows a side view of the cash register according to figure 5. Fig. 7 schematically shows a top view of a cash register according to a fourth example of the invention. Figure 7 shows the same devices as Figures 5 and 6, but with the addition that a VIS sensor 24 is placed between the first conveyor belt 9 and the second conveyor belt 13 in order to be able to identify the product by spectroscopy. Figure 7 shows that the VIS sensor 24 and the first NIR sensor 7. Both the VIS sensor 24 and the first NIR sensor 7 The VIS sensor may comprise a fiber cable which transmits light from the product to the respective sensor. The VIS sensor and the NIR sensor can both be connected to separate fiber cables which are arranged to merge into a common fiber cable which transmits light from the product to the respective VIS camera and NIR camera. The VIS sensor 24 may be arranged at a cash register according to any one of Figures 1-6 and may be located at the first conveyor belt 9, the second conveyor belt 12 or the third conveyor belt 13.
    When the VIS sensor 24 is switched on, it is set to operate in the range from 200nm to 400nm and from 660nm to 1100nm if used in combination with the color texture sensor 17 and / or the color histogram sensor 18, but is set to operate in the range from 200nm to 1100nm when the color texture sensor 17 and the color histogram sensor 18 is turned off. The processor 6 is arranged to control the range of the VIS sensor depending on whether the color texture sensor 17 and / or the color histogram sensor 18 is switched on or off. The VIS sensor 24 can be used in combination with any of the combinations of sensors indicated in Figures 1-6, or only together with the weight sensor 4 and the first NIR sensor 7.
    The VIS sensor 24 is connected to the processor 6 and the memory unit 5.
    The memory device includes one or more third signatures created by the VIS sensor 24 or another VIS sensor (not shown). The third signature or signatures are each linked to a corresponding commodity identity. The third signatures can be created directly at the checkout counter by using the VIS sensor 24 or a second VIS sensor (not shown) or by loading the memory with third signatures created by a VIS sensor not connected to checkout counter 1.
    Figure 1 shows that the weight sensor 4 is placed before the VIS sensor 24, which means that the VIS sensor 24 is arranged to create a fourth signature after analysis of the product 3 after the product has been weighed, i.e. placed on the weight sensor 4 and then weighed. The processor 6 is then arranged to compare the fourth signature with the third signature in order to identify the product 3 as a product identity present in the memory unit 5. The weight of the item 3 is used by the processor together with the product identity to determine the price of the item 3.
    Fig. 8 schematically shows a side view of the cash register according to Fig. 7.
    It should be noted that the examples shown in Figures 1-8 are not limiting of the invention, but only examples of locations of sensors and conveyor belts. The cash register according to the invention may comprise one or more conveyor belts. In the case of several conveyor belts, they can be angled towards each other and / or arranged to divide a flow of goods into substreams, etc. Adding more sensors than the first NIR sensor and the weight sensor to the cash register according to the invention should be seen as further possibilities for improved identification and is thus a complementing the preferred embodiment with the first NIR sensor and the weight sensor. The additional sensors can be placed in a large number of ways in addition to those in Figures 1-8 to give acceptable results within the scope of the invention, but they are not shown here.
    权利要求:
    Claims (19)
    [1]
    An automated cash register (1) comprising a classification device (2) for identifying goods (3), the classification device (2) comprising a weight sensor (4) for weighing the goods (3), a memory unit (5) comprising information about a or more products, the classification device (2) comprising a processor (6) connected to the memory unit (5) and the weight sensor (4), characterized in that the memory unit (5) comprises one or more first signatures which first signature or signatures are each connected to a corresponding commodity identity, which first signature is created by an infrared spectroscopy sensor (7), hereinafter referred to as NIR sensor (7), the classification device (2) comprising a first NIR sensor (7) coupled to the processor (6), wherein it the first NIR sensor (7) is arranged to, when an item (3) is placed before, on or after the weight sensor (4), create a second signature connected to the item (3), the processor (6) being arranged to compare the second s the signature with the first signature to identify the product (3) as a product identity present in the memory unit (5), the cash register (1) being arranged to weigh the product (3) via the weight sensor (4) before, during or after the second signature created, wherein the processor (6) is arranged to use the weight and commodity identity of the commodity (3) to determine the price of the commodity (3).
    [2]
    A cash register (1) according to claim 1, wherein the weight sensor (4) comprises a transport path (8) which automatically transports the goods (3) and weighs them.
    [3]
    A cash register (1) according to claim 1 or 2, wherein the classification device (2) comprises a contour sensor (14) and / or a bar code sensor (15) and / or a symbol reading sensor (16) using optical character recognition and machine text interpretation and / or a color texture sensor (17) and / or a color histogram sensor (18) cooperating with the first NIR sensor (7) and the weight sensor (4) in such a way that if the sensors together with the first NIR sensor (7) and the weight sensor (4) is activated in the following combinations, the remaining sensors are allowed to be deactivated or not activated, depending on which item has been identified: - weight sensor (4) and contour sensor (14) and symbol reading sensor (16), or contour sensor (14) and symbol reading sensor (16), or weight sensor (4) and symbol reading sensor (16), or weight sensor (4) and color histogram sensor (18) and contour sensor (14), or weight sensor (4) and contour sensor (14) and color texture sensor (17 ) and symbol reading sensor (16) or weight sensor (4) and bar code sensor (15), or - only symbol reading sensor (16). color histogram sensor (18) and color texture sensor (17), or color histogram sensor (18), or color texture sensor (17),
    [4]
    A cash register (1) according to any one of the preceding claims, wherein the classification device (2) comprises an initial sensor (21) which identifies with 100% the product (3) and is arranged to be used in training the system by first identifying the product (3). ) and then run the product through the classification device (2) where all sensors identify properties of the product (3) which are then stored in a database of properties of goods.
    [5]
    A cash register (1) according to claim 4, wherein the initial sensor is a bar code reader (15) intended for manual use.
    [6]
    A cash register (1) according to any one of the preceding claims, wherein the classification device comprises a tunnel-like structure which shields a part of the cash register and at least some of the sensors completely or partially, in order thereby to prevent unauthorized persons from the possibility of influencing the classification process.
    [7]
    A cash register (1) according to any one of claims 1-6, wherein the first NIR sensor (7) is arranged to read the item (3) and create the first signature during a learning phase.
    [8]
    A cash register (1) 1-6, the classification device (2) comprises a second NIR sensor arranged to read the product (3) according to any one of the claims and create the first signature during a learning phase.
    [9]
    A cash register counter (1) according to any one of the preceding claims, wherein the cash register counter (1) comprises an interactive presentation unit (11) connected to the processor (6) for presentation of product identity, weight and price, which presentation unit (11) is arranged to be used by a user to feel good about what is presented.
    [10]
    A cash register (1) according to any one of the preceding claims, wherein the classification device (2) comprises a contour sensor (14) and / or one (15 (and / or (16) using optical character recognition and machine text interpretation bar code sensor a symbol reading sensor and / or a color texture sensor (17) and / or a color histogram sensor (18), and / or a spectroscopy sensor, hereinafter referred to as VIS sensor, operating in the range from 200nm to 400nm and from 660nm to 1100nm in combination with the color texture sensor (17) and / or the color histogram sensor (18) but operating in the range from 200nm to 1100nm when the color texture sensor (17) and the color histogram sensor (18) are disconnected, cooperating with the first NIR sensor (7) and the weight sensor (4) in such a way that if the sensors together with the first NIR sensor (7) and the weight sensor (4) are activated in the following combinations it is allowed that the remaining sensors, in addition to the first NIR sensor and the weight sensor, are deactivated or not depending on the item identified: - weight sensor (4) and contour sensor (14) and symbol reading sensor (16), or contour sensor (14) and symbol reading sensor (16), or weight sensor (4) and symbol reading sensor (16), or weight sensor (4) and color histogram sensor (18) and contour sensor (14), or weight sensor (4) and contour sensor (14) and color texture sensor (17) and symbol reading sensor (16) or weight sensor (4) and barcode sensor (15), or - only symbol reading sensor (16). -color histogram sensor (18) and color texture sensor (17), or -color histogram sensor (18), or -color texture sensor (17), or -VIS sensor in combination with any of the above combinations, or -only the VIS sensor
    [11]
    A method of an automated cash register (1) comprising a classification device (2) for identifying goods (3), wherein the classification device (2) comprises a weight sensor (4) for weighing the goods, a memory unit (5) comprising information about a or more products, the classification device (2) comprising a processor (6) connected to the memory unit (5) and the weight sensor (4), characterized in that the memory unit (5) comprises one or more first signatures which first signature or signatures are each connected to a corresponding commodity identity, which first signature is created by an infrared spectroscopy sensor (7), hereinafter referred to as NIR sensor (7), the classification device (2) comprising a first NIR sensor (7) coupled to the processor (6), wherein it the first NIR sensor (7), when an item is placed before, on or after the weight sensor (4), reads the item (3) and creates a second signature connected to the item, whereby the processor (6) compares the the second signature with the first signature to identify the product (3) as a product identity present in the memory unit (5), the weight sensor (4) weighing the product (3) before, during or after the second signature is created, the processor (6) uses the weight (3) of the item (3) to determine the price of the item (3).
    [12]
    A method according to claim 11, wherein the weight sensor (4) comprises a transport path (8) which automatically transports the goods and weighs them.
    [13]
    A method according to claim 11 or 12, wherein the classification device (2) comprises a contour sensor (14) and / or a bar code sensor (15 (and / or a symbol reading sensor (16) using optical character recognition and (machine) text interpretation and / or or a color texture sensor color texture sensor (17) and / or a color histogram sensor (18) cooperating with the first NIR sensor (7) and the weight sensor (4) in such a way that if the sensors together with the first NIR sensor (7) and the weight sensor (4) activated in the following combinations allowed the remaining sensors to be deactivated or not activated, depending on the item identified: -weight sensor (4) and contour sensor (14) and symbol reading sensor (16), or -contour sensor (14) and symbol reading sensor (16) , or weight sensor (4) and symbol reading sensor (16), or weight sensor (4) and color histogram sensor (18) and contour sensor (14), or weight sensor (4) and contour sensor (14) and color texture sensor (17) and symbol reading sensor (16) or weight sensor (4) and bar code sensor (15), or - only symbol reading sensor (16). color histogram sensor (18) and color texture sensor (17), or color histogram sensor (18), or color texture sensor (17).
    [14]
    A method according to any one of claims 11-13, wherein the classification device (2) comprises an initial sensor (21) which identifies with 100% the product (3) and which is used in training the system by first identifying the product (3) and then driving the product through the classification device (2) where all sensors identify properties of the product (3) which are then stored in a database for properties of goods.
    [15]
    A method according to claim 14, wherein the initial sensor is a bar code reader (15) intended for manual use.
    [16]
    A method according to any one of claims 11-15, wherein the first NIR sensor (7) reads the item (3) and creates the first signature during a learning phase.
    [17]
    A method according to any one of claims 11-15, wherein the classification device (2) comprises a second NIR sensor which reads the product (3) and creates the first signature during a learning phase.
    [18]
    A method according to any one of claims 11-17, wherein the cash register (1) comprises (11) coupled to the presentation of product identity, weight and price, which presentation unit (11) an interactive presentation unit the processor (6) is used by a user to approve what is presented.
    [19]
    A method according to any one of claims 11-18, wherein the classification device (2) comprises a contour sensor (14) and / or a bar code sensor (15 (and / or a symbol reading sensor (16) using optical character recognition and machine text interpretation and / or a color texture sensor (17) and / or a color histogram sensor (18) and / or a spectroscopy sensor, hereinafter referred to as VIS sensor operating in the range from 200nm to 400nm and from 660nm to 1100nm in combination with the color texture sensor (17) and / or the color histogram sensor ( 18) but operating in the range from 200nm to 1100nm when the color texture sensor (17) and the color histogram sensor (18) are disconnected, cooperating with the first NIR sensor (7) and the weight sensor (4) in such a way that if the sensors together with the first NIR sensor (7) and the weight sensor (4) are activated in the following combinations it is allowed that the remaining sensors, in addition to the weight sensor and the weight sensor, are deactivated or not activated, depending on which item is identified: -weight sensor (4) and contour sensor (14) and symbol reading sensor (16), or -contour sensor (14) and symbol reading sensor (16), or weight sensor (4) and symbol reading sensor (16), or weight sensor ( 4) and color histogram sensor (18) and contour sensor (14), or weight sensor (4) and contour sensor (14) and color texture sensor (17) and symbol reading sensor (16) or weight sensor (4) and barcode sensor (15), or symbol reading sensor only (16). color histogram sensor (18) and color texture sensor (17), or color histogram sensor (18), or color texture sensor (17), or VIS sensor in combination with any of the above combinations, or VIS sensor only.
    类似技术:
    公开号 | 公开日 | 专利标题
    SE1051090A1|2012-01-09|checkout counter
    CN105611859B|2019-08-02|Conveyor system for checkout counter
    WO2012005661A1|2012-01-12|A checkout counter
    SE1050766A1|2012-01-09|checkout counter
    KR101708150B1|2017-02-20|The method and apparatus for recognizing an identification code of a product
    EP3474181A1|2019-04-24|Device for automatic recognition of products
    US11069203B2|2021-07-20|Commodity information reading apparatus and program
    KR20220025337A|2022-03-03|Product classification method and system to prevent misclassification
    EP3913526A1|2021-11-24|Platform detection
    US20200124484A1|2020-04-23|Product identification system and method
    EP3776419A1|2021-02-17|A checkout counter, and a classification system
    同族专利:
    公开号 | 公开日
    RU2589387C2|2016-07-10|
    KR20130045350A|2013-05-03|
    AU2011277076A1|2013-02-07|
    RU2013101991A|2014-08-20|
    KR101926201B1|2018-12-06|
    JP2013531312A|2013-08-01|
    SE535853C2|2013-01-15|
    CN103052342A|2013-04-17|
    US20150062560A1|2015-03-05|
    CA2803510C|2017-11-21|
    CA2803514C|2017-07-18|
    US9301626B2|2016-04-05|
    JP6087813B2|2017-03-01|
    WO2012005660A1|2012-01-12|
    JP2016042363A|2016-03-31|
    EP2590536A1|2013-05-15|
    US9173508B2|2015-11-03|
    US20130235368A1|2013-09-12|
    AU2011277075A1|2013-02-07|
    KR101928111B1|2018-12-11|
    AU2011277075B2|2016-06-09|
    CN103052343A|2013-04-17|
    RU2568169C2|2015-11-10|
    JP6282253B2|2018-02-21|
    CA2803510A1|2012-01-12|
    AU2011277076B2|2016-05-26|
    EP2590536A4|2016-08-10|
    EP2590535A1|2013-05-15|
    JP2013529824A|2013-07-22|
    CN103052342B|2016-11-23|
    KR20130139853A|2013-12-23|
    WO2012005659A1|2012-01-12|
    EP2590535A4|2016-08-10|
    CN108078295A|2018-05-29|
    RU2013101992A|2014-08-20|
    CA2803514A1|2012-01-12|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    US731990A|1903-01-09|1903-06-23|William D Wilson|Cotton chopper and cultivator.|
    SU2108A1|1925-09-07|1926-12-31|В.А. Зиновьев|Control device to machines for the sale of various items|
    US3819012A|1970-03-20|1974-06-25|Rca Corp|Merchandise handling and identifying system|
    US3867041A|1973-12-03|1975-02-18|Us Agriculture|Method for detecting bruises in fruit|
    US4792018A|1984-07-09|1988-12-20|Checkrobot Inc.|System for security processing of retailed articles|
    US4676343A|1984-07-09|1987-06-30|Checkrobot Inc.|Self-service distribution system|
    US4964053A|1988-04-22|1990-10-16|Checkrobot, Inc.|Self-checkout of produce items|
    CA2054851C|1991-11-01|1999-06-29|Howard Schneider|Automated point-of-sale machine|
    JPH05231914A|1992-02-24|1993-09-07|Tokyo Electric Co Ltd|Check-out apparatus|
    JP2926065B2|1992-08-10|1999-07-28|株式会社大阪造船所|Packaging metal container and manufacturing method thereof|
    DE4241250C2|1992-12-08|1996-04-11|Rwe Entsorgung Ag|Method for identifying objects and device for carrying out the method|
    JPH06180785A|1992-12-11|1994-06-28|Casio Comput Co Ltd|Sale data processor|
    JPH06333065A|1993-05-20|1994-12-02|Casio Comput Co Ltd|Data processor|
    US5497314A|1994-03-07|1996-03-05|Novak; Jeffrey M.|Automated apparatus and method for object recognition at checkout counters|
    JPH07320148A|1994-05-30|1995-12-08|Tec Corp|Self-scanning checkout device|
    US5883968A|1994-07-05|1999-03-16|Aw Computer Systems, Inc.|System and methods for preventing fraud in retail environments, including the detection of empty and non-empty shopping carts|
    US6069696A|1995-06-08|2000-05-30|Psc Scanning, Inc.|Object recognition system and method|
    CA2179338C|1995-08-07|2000-04-25|Gordon Albert Thomas|Apparatus and method for spectroscopic product recognition and identification|
    US6075594A|1997-07-16|2000-06-13|Ncr Corporation|System and method for spectroscopic product recognition and identification|
    US6363366B1|1998-08-31|2002-03-26|David L. Henty|Produce identification and pricing system for checkouts|
    US6332573B1|1998-11-10|2001-12-25|Ncr Corporation|Produce data collector and produce recognition system|
    JP2000155767A|1998-11-10|2000-06-06|Ncr Internatl Inc|Bar code data gathering unit and merchandise checkout device equipped with merchandise data gathering unit|
    US6155489A|1998-11-10|2000-12-05|Ncr Corporation|Item checkout device including a bar code data collector and a produce data collector|
    US6260023B1|1999-06-14|2001-07-10|Ncr Corporation|Transaction processing system including a networked produce recognition system|
    US6408279B1|1999-06-28|2002-06-18|Ncr Corporation|Method and apparatus for operating a self-service checkout terminal and a remote supervisor terminal of a retail system|
    US6529855B1|1999-07-28|2003-03-04|Ncr Corporation|Produce recognition system and method|
    US6431446B1|1999-07-28|2002-08-13|Ncr Corporation|Produce recognition system and method|
    AUPQ607100A0|2000-03-07|2000-03-30|Colour Vision Systems Pty Ltd|Spectral assessment of fruit|
    BR0109219A|2000-03-13|2004-06-22|Autoline Inc|Apparatus and method and techniques for measuring and correlating fruit with visible / near infrared spectra|
    EP1154262A1|2000-05-10|2001-11-14|Dsm N.V.|Apparatus for identifying articles which are at least partly made from at least one polymer|
    US6601767B1|2000-08-16|2003-08-05|Ncr Corporation|Ambient light sensing apparatus and method for a produce data collector|
    US6606579B1|2000-08-16|2003-08-12|Ncr Corporation|Method of combining spectral data with non-spectral data in a produce recognition system|
    US6412694B1|2000-09-20|2002-07-02|Ncr Corporation|Produce recognition system and method including weighted rankings|
    US6668078B1|2000-09-29|2003-12-23|International Business Machines Corporation|System and method for segmentation of images of objects that are occluded by a semi-transparent material|
    US6577983B1|2000-10-06|2003-06-10|Ncr Corporation|Produce recognition method|
    US6510994B1|2000-10-06|2003-01-28|Ncr Corporation|Triggering method for a produce recognition system|
    US6497362B2|2001-02-15|2002-12-24|New Check Corporation|Method and apparatus for wireless assistance for self-service checkout|
    US6837428B2|2001-03-02|2005-01-04|Mike Lee|Self-checkout apparatus|
    WO2003005313A2|2001-07-02|2003-01-16|Psc Scanning, Inc.|Checkout system with a flexible security verification system|
    NL1018512C1|2001-07-11|2001-11-02|Beheermij Van Der Loo B V|Automatic cash register system.|
    US20030058441A1|2001-09-20|2003-03-27|Metso Paper Automation Oy,|Method and apparatus for optical measurements|
    US7797204B2|2001-12-08|2010-09-14|Balent Bruce F|Distributed personal automation and shopping method, apparatus, and process|
    US7218395B2|2003-04-16|2007-05-15|Optopo Inc.|Rapid pharmaceutical identification and verification system|
    EP1473657A1|2003-04-29|2004-11-03|Sicpa Holding S.A.|Method and device for the authentication of documents and goods|
    US7248754B2|2003-05-05|2007-07-24|International Business Machines Corporation|Apparatus and method for determining whether machine readable information on an item matches the item|
    US7118026B2|2003-06-26|2006-10-10|International Business Machines Corporation|Apparatus, method, and system for positively identifying an item|
    US7337960B2|2004-02-27|2008-03-04|Evolution Robotics, Inc.|Systems and methods for merchandise automatic checkout|
    WO2006060785A2|2004-12-01|2006-06-08|Datalogic Scanning, Inc.|Triggering illumination for a data reader|
    US7229015B2|2004-12-28|2007-06-12|International Business Machines Corporation|Self-checkout system|
    DE102005014626B4|2005-03-23|2018-06-21|Bizerba SE & Co. KG|Libra|
    US7909248B1|2007-08-17|2011-03-22|Evolution Robotics Retail, Inc.|Self checkout with visual recognition|
    DE102007057921A1|2007-12-01|2009-06-04|Oerlikon Textile Gmbh & Co. Kg|Method and device for automated identification of bobbins|
    US8462212B1|2008-12-04|2013-06-11|Stoplift, Inc.|Correlating detected events with image data|
    US7434663B1|2008-01-21|2008-10-14|International Business Machines Corporation|Retail checkout station including a plurality of selectively deployable barriers for intra-order separation of purchased items|
    US8322621B2|2008-12-26|2012-12-04|Datalogic ADC, Inc.|Image-based code reader for acquisition of multiple views of an object and methods for employing same|
    US8113427B2|2008-12-18|2012-02-14|Ncr Corporation|Methods and apparatus for automated product identification in point of sale applications|
    US8118226B2|2009-02-11|2012-02-21|Datalogic Scanning, Inc.|High-resolution optical code imaging using a color imager|
    US8874472B2|2009-09-30|2014-10-28|Ncr Corporation|Methods and apparatus for produce identification using time resolved reflectance spectroscopy|
    JP4995291B2|2010-02-10|2012-08-08|東芝テック株式会社|Product registration system and method|
    SE535853C2|2010-07-08|2013-01-15|Itab Scanflow Ab|checkout counter|
    US9412050B2|2010-10-12|2016-08-09|Ncr Corporation|Produce recognition method|
    JP5799593B2|2011-06-07|2015-10-28|株式会社寺岡精工|Product search device, product information processing device, and label issuing device|
    US8498903B2|2011-09-29|2013-07-30|Ncr Corporation|System and method for performing a security check at a checkout terminal|SE535853C2|2010-07-08|2013-01-15|Itab Scanflow Ab|checkout counter|
    CN104040309B|2011-11-03|2019-06-07|威利食品有限公司|Inexpensive spectrometric system for end user's food analysis|
    JP2014052800A|2012-09-06|2014-03-20|Toshiba Tec Corp|Information processing apparatus and program|
    GB2543655B|2013-08-02|2017-11-01|Verifood Ltd|Compact spectrometer comprising a diffuser, filter matrix, lens array and multiple sensor detector|
    SE537684C2|2013-10-09|2015-09-29|Itab Scanflow Ab|A conveyor belt system for a check-out counter|
    CN103699911A|2013-11-21|2014-04-02|苏州斯普锐智能系统有限公司|Automatic settlement system with bottom scanning device|
    EP3090239A4|2014-01-03|2018-01-10|Verifood Ltd.|Spectrometry systems, methods, and applications|
    CN105303204A|2014-07-23|2016-02-03|Ncr公司|Quick article identification|
    JP2016033694A|2014-07-30|2016-03-10|東芝テック株式会社|Object recognition apparatus and object recognition program|
    US9493308B2|2014-08-11|2016-11-15|Datalogic ADC, Inc.|Cross-belt system and automated item diversion|
    US20160110791A1|2014-10-15|2016-04-21|Toshiba Global Commerce Solutions Holdings Corporation|Method, computer program product, and system for providing a sensor-based environment|
    CN107250739A|2014-10-23|2017-10-13|威利食品有限公司|The annex of Handheld spectrometer|
    WO2016125164A2|2015-02-05|2016-08-11|Verifood, Ltd.|Spectrometry system applications|
    WO2016125165A2|2015-02-05|2016-08-11|Verifood, Ltd.|Spectrometry system with visible aiming beam|
    WO2016162865A1|2015-04-07|2016-10-13|Verifood, Ltd.|Detector for spectrometry system|
    US10066990B2|2015-07-09|2018-09-04|Verifood, Ltd.|Spatially variable filter systems and methods|
    EP3159858B1|2015-10-19|2021-07-14|Wincor Nixdorf International GmbH|Recording system for recording objects|
    US10203246B2|2015-11-20|2019-02-12|Verifood, Ltd.|Systems and methods for calibration of a handheld spectrometer|
    JP6801676B2|2016-01-21|2020-12-16|日本電気株式会社|Information processing equipment, information processing methods, and programs|
    CN106204045A|2016-02-18|2016-12-07|唐超科技有限公司|Self-checkout loss prevention method of calibration, system and electronic scale module thereof|
    US10254215B2|2016-04-07|2019-04-09|Verifood, Ltd.|Spectrometry system applications|
    US10791933B2|2016-07-27|2020-10-06|Verifood, Ltd.|Spectrometry systems, methods, and applications|
    WO2018112431A1|2016-12-16|2018-06-21|Datalogic Usa, Inc.|Imaging barcode scanner with three-dimensional item reconstruction|
    US10366379B2|2017-01-30|2019-07-30|Ncr Corporation|Remote weigh station with delayed fraud intervention|
    CN107103413B|2017-04-12|2018-09-14|王碧群|A kind of adaptive cashier management method|
    JP6903524B2|2017-09-01|2021-07-14|東芝テック株式会社|Weighing device|
    DE102017130909A1|2017-12-21|2019-06-27|Weber Maschinenbau Gmbh Breidenbach|Optical measuring device|
    KR101850315B1|2018-01-22|2018-05-31|주식회사 엑사스코프|Apparatus for self-checkout applied to hybrid product recognition|
    US10507360B2|2018-02-21|2019-12-17|William Schroeder|Posture correction and weight balance apparatus|
    DE102018105170A1|2018-03-07|2019-09-12|Ait Goehner Gmbh|Scanning device and method for this|
    US11097561B2|2018-03-23|2021-08-24|Citic Dicastal Co., Ltd|Automatic hub type identifying device|
    WO2019190388A1|2018-03-28|2019-10-03|Itab Scanflow Ab|A checkout counter, and a classification system|
    CN110432714B|2019-08-20|2021-01-12|江苏柯德展示道具有限公司|Lifting device for exhibition and display service|
    CN110726730A|2019-11-05|2020-01-24|韩向东|Self-adaptive transmission detection device|
    WO2021101159A1|2019-11-22|2021-05-27|한화테크윈 주식회사|Automatic payment apparatus|
    RU2737600C1|2020-03-19|2020-12-01|Общество с ограниченной ответственностью «ИНСПЕКТОР КЛАУД»|Method of collecting marked data set|
    法律状态:
    优先权:
    申请号 | 申请日 | 专利标题
    SE1050766A|SE534989C2|2010-07-08|2010-07-08|checkout counter|
    SE1051090A|SE535853C2|2010-07-08|2010-10-19|checkout counter|SE1051090A| SE535853C2|2010-07-08|2010-10-19|checkout counter|
    CN201180033868.6A| CN103052342B|2010-07-08|2011-06-23|Cashier|
    PCT/SE2011/050840| WO2012005661A1|2010-07-08|2011-06-23|A checkout counter|
    KR1020137003421A| KR101926201B1|2010-07-08|2011-06-23|A Checkout Counter|
    KR1020137003420A| KR101928111B1|2010-07-08|2011-06-23|A Checkout Counter|
    JP2013518330A| JP6087813B2|2010-07-08|2011-06-23|Checkout counter|
    RU2013101991/08A| RU2589387C2|2010-07-08|2011-06-23|Point-of-sale terminal|
    US13/808,833| US9301626B2|2010-07-08|2011-06-23|Checkout counter|
    US13/808,814| US9173508B2|2010-07-08|2011-06-23|Checkout counter|
    PCT/SE2011/050838| WO2012005659A1|2010-07-08|2011-06-23|A checkout counter|
    JP2013518329A| JP2013531312A|2010-07-08|2011-06-23|Checkout counter|
    EP11803891.8A| EP2590536A4|2010-07-08|2011-06-23|A checkout counter|
    CN2011800338775A| CN103052343A|2010-07-08|2011-06-23|A Checkout Counter|
    AU2011277076A| AU2011277076B2|2010-07-08|2011-06-23|A checkout counter|
    AU2011277075A| AU2011277075B2|2010-07-08|2011-06-23|A checkout counter|
    PCT/SE2011/050839| WO2012005660A1|2010-07-08|2011-06-23|A checkout counter|
    CA2803514A| CA2803514C|2010-07-08|2011-06-23|A checkout counter|
    EP11803890.0A| EP2590535A4|2010-07-08|2011-06-23|A checkout counter|
    CA2803510A| CA2803510C|2010-07-08|2011-06-23|A checkout counter|
    CN201810070898.8A| CN108078295A|2010-07-08|2011-06-23|Cashier|
    RU2013101992/12A| RU2568169C2|2010-07-08|2011-06-23|Point-of-sale terminal|
    JP2015201266A| JP6282253B2|2010-07-08|2015-10-09|Checkout counter|
    [返回顶部]