Settlement processing system and settlement processing method

Abstract

To easily identify securities such as securities and non-securities.SOLUTION: The settlement processing system 1 includes at least the POS register 20, the change machine 30, and the security processing apparatus 10, and the security processing apparatus 10 includes the image information acquisition unit 122 configured to acquire the first image information indicating the first image which is the image of the gift certificate GT to be identified, and the security processing apparatus 10 is configured to execute, on the first image, the processing of generating the feature vector indicating the feature value of the image. The commodity recognition apparatus includes the feature extraction section 124 configured to generate the feature vector of the first image, the distance calculation section 125 configured to calculate the inter-vector distance which is the distance between the feature vector of the first image and the feature vector of the second image which is the image of each of the plurality of reference gift certificates GT registered in advance, and the recognition section 126 configured to recognize the gift certificate GT to be recognized based on the inter-vector distance, and the POS register 20 and the change machine 30 execute the settlement processing of the commodity that the customer desires to purchase according to the recognition result in the recognition section 126.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a settlement processing system and a settlement processing method. [Background technology]

[0002] In addition to currency, retail stores such as supermarkets sometimes handle valuable securities such as gift certificates. For example, it has been proposed that a gift certificate deposit machine be connected to a POS register and a change dispenser, allowing store clerks to identify gift certificates received from customers and process payment for purchased goods (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-200938 Summary of the Invention [Problem to be solved by the invention]

[0004] In recent years, the use of semi-self-checkout registers and self-checkout registers when customers pay for purchased goods at retail stores and other establishments has been increasing. Therefore, there is a demand for faster and more accurate identification of securities such as gift certificates and service coupons. Furthermore, the number of types of securities circulating on the market, such as gift certificates and regional promotion coupons, is increasing, and the number of types of non-securities, such as service coupons and coupons, is also increasing. Hereinafter, securities and non-securities may be collectively referred to as securities.

[0005] In recent years, research into the use of AI (Artificial Intelligence) to identify gift certificates has progressed. For example, a commonly known method is to identify images of gift certificates using a model (hereinafter also referred to as an image recognition model) that has learned about the type of gift certificate, etc., using images of various gift certificates in circulation on the market as training data. This type of recognition method requires training using a large amount of training data to create the image recognition model. For this reason, conventional AI-based recognition methods that use image recognition models have had the problem of requiring a significant amount of time and effort for training using training data, and generating the information necessary to identify gift certificates requires a huge amount of effort.

[0006] Furthermore, conventional identification methods can take more than 10 seconds to identify gift certificates, making them difficult to introduce. This is particularly true for semi-self-checkouts and self-checkouts, which are forced to limit the identification time, and therefore require high accuracy and speed in identification. While it is possible to simply shorten the identification time, this poses the problem of reduced identification accuracy. [Means for solving the problem]

[0007] An information processing system according to a preferred embodiment of the present invention is a settlement processing system having at least a POS register, a settlement processing device, and a securities processing device, wherein the securities processing device comprises an acquisition unit that acquires first image information indicating a first image, which is an image of the inserted securities to be identified, a generation unit that generates a feature vector of the first image by executing a process on the first image to generate a feature vector indicating the features of the image, a calculation unit that calculates an inter-vector distance, which is the distance between the feature vector of a second image, which is an image of each of a plurality of reference securities that have been registered in advance, and the feature vector of the first image, and an identification unit that identifies the securities to be identified based on the inter-vector distance, and the POS register and the settlement processing device perform settlement processing for the products that the customer wishes to purchase according to the identification results of the identification unit.

[0008] In addition, a preferred embodiment of the present invention provides a settlement processing method that acquires first image information indicating a first image, which is an image of the inserted security to be identified, generates a feature vector indicating the image's features by performing a process on the first image to generate the feature vector of the first image, calculates a vector distance that is the distance between the feature vector of a second image, which is an image of each of a plurality of reference securities that have been registered in advance, and the feature vector of the first image, identifies the security to be identified based on the vector distance, and executes settlement processing for the product that the customer wishes to purchase using a POS register and a settlement processing device according to the identification result of the security to be identified. [Effects of the Invention]

[0009] According to the present invention, securities can be easily identified. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a conceptual diagram for explaining an overview of a settlement processing system according to a first embodiment. [Figure 2] 1 is a block diagram showing the configuration of a settlement processing system according to a first embodiment. [Figure 3] FIG. 3 is an explanatory diagram for explaining an example of a bill type table shown in FIG. 2. [Figure 4] 10 is a flowchart showing an example of the operation of the settlement processing system when registering a gift certificate in a certificate type table. [Figure 5] 10 is an explanatory diagram illustrating an example of a confirmation screen displayed on a display device when a gift certificate to be identified is read by an image input device. FIG. [Figure 6] 10 is a flowchart showing an example of the operation of the settlement processing system when a user uses a gift certificate to settle the payment for purchased goods. [Figure 7] 7 is a flowchart showing an example of the surface identification process shown in FIGS. 4 and 6. [Figure 8] FIG. 10 is an explanatory diagram for explaining an overview of a settlement processing system according to a first modified example. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Note that in each drawing, the dimensions and scale of each part are appropriately different from those of the actual parts. Furthermore, the embodiments described below are preferred examples of the present invention, and therefore various technically preferable limitations are applied. However, the scope of the present invention is not limited to these embodiments unless otherwise specified in the following description to the effect that the present invention is limited.

[0012] [1. First embodiment] First, an example of an overview of a settlement processing system 1 according to an embodiment will be described with reference to FIGS.

[0013] FIG. 1 is a conceptual diagram for explaining an overview of a settlement processing system 1 according to a first embodiment. In FIG. 1, the settlement processing system 1 includes a securities processing device 10 that processes securities such as gift certificates GT and service coupons, a POS register 20, and a change dispenser 30, which is a settlement processing device. The securities processing device 10 includes, for example, an input port INP and a return port REP. In the securities processing device 10 shown in FIG. 1, for example, securities are inserted into the securities processing device 10 by inserting the securities into the input port INP of the securities processing device 10. Furthermore, inserted securities can be removed from the return port REP as needed.

[0014] In this embodiment, a securities processing device 10 is communicatively linked to a POS register 20 (including self-checkouts and semi-self-checkouts) and a change dispenser 30 used to process payments for products purchased by customers at a store such as a supermarket, and the system identifies a security such as a gift certificate GT that the customer wishes to use, determines whether it can be used at the store, and executes the payment process. Note that the security processed by the payment processing system 1 of the present invention is not limited to a gift certificate GT, but may also be a security such as a regional promotion coupon, or a non-security security such as a service coupon, coupon, or discount coupon. Furthermore, the payment processing device is not limited to the change dispenser 30, and may be a payment processing device other than the change dispenser 30.

[0015] FIG. 2 is a block diagram showing the configuration of the settlement processing system 1 according to the first embodiment.

[0016] The settlement processing system 1 includes a securities processing device 10, a POS register 20, and a change dispenser 30. The securities processing device 10 is communicatively connected to the POS register 20, which in turn is communicatively connected to the change dispenser 30. The connection between the securities processing device 10 and the POS register 20, and the connection between the POS register 20 and the change dispenser 30, may be either a wired or wireless connection, or may be a combination of wired and wireless connections. The connection between multiple elements, including the securities processing device 10, may be via a network, as long as it allows the elements to communicate with each other. The network may include the Internet and a local area network.

[0017] In this embodiment, it is assumed that the securities processing device 10, the POS register 20, and the change dispenser 30 are installed in a retail store such as a supermarket that handles gift certificates GT.

[0018] Any information processing device can be used as the securities processing device 10. The securities processing device 10 includes, for example, a processing device 120 that controls each part of the securities processing device 10, a storage device 140 that stores various information, a communication device 160, and an image input device 130.

[0019] The image input device 130 is, for example, an optical device such as a camera, an image scanner, etc. For example, the image input device 130 captures an image of the gift certificate GT to generate image information indicating an image of the gift certificate GT.

[0020] The storage device 140 may include, for example, one or both of a volatile memory such as a random access memory (RAM) that functions as a working area for the processing device 120, and a non-volatile memory such as an electrically erasable programmable read-only memory (EEPROM) that stores various information such as the control program PG1. The storage device 140 may be detachable from the securities processing device 10. Specifically, the storage device 140 may be a storage medium such as a memory card that is detachable from the securities processing device 10. The storage device 140 may also be, for example, a storage device (e.g., online storage) that is communicatively connected to the securities processing device 10 via a network or the like.

[0021] In this embodiment, the storage device 140 stores a note type table TBL in addition to the control program PG1. The note type table TBL will be described later with reference to FIG.

[0022] The communication device 160 is hardware for communicating with an external device such as a POS register 20 that exists outside the securities processing device 10 .

[0023] The processing device 120 is a processor that controls the entire securities processing device 10, and is configured to include, for example, one or more CPUs (Central Processing Units). For example, the processing device 120 executes a control program PG1 stored in the storage device 140 to function as an image information acquisition unit 122, a surface identification unit 123, a feature extraction unit 124, a distance calculation unit 125, and an identification unit 126.

[0024] The POS register 20 performs a settlement process for the purchased items of the customer in accordance with the identification result by the securities processing device 10. The control program PG1 may be transmitted from another device via a network.

[0025] When an employee or customer (an employee or customer is also referred to as a user) of a retail store in which the image input device 130 is installed identifies a gift certificate GT and processes a settlement, the processing device 120 causes the image input device 130 to read the gift certificate GT to be identified. The image input device 130 generates image information showing an image of the read gift certificate GT (image of the gift certificate GT to be identified) and transmits the generated image information to the processing device 120. The image input device 130 may store the image information in a shared memory (not shown). In this case, the processing device 120 may read the image information from the shared memory.

[0026] Furthermore, for example, when the processing device 120 is configured to include multiple CPUs, some or all of the functions of the processing device 120 may be realized by the multiple CPUs operating cooperatively in accordance with a program such as the control program PG1. Furthermore, the processing device 120 may be configured to include hardware such as a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), or an FPGA (Field Programmable Gate Array) in addition to one or more CPUs, or instead of some or all of the one or more CPUs. In this case, some or all of the functions of the processing device 120 may be realized by hardware such as a DSP.

[0027] Thus, in this embodiment, the control program PG1 includes application programs for causing the processing device 120 to function as the image information acquisition unit 122, the surface identification unit 123, the feature extraction unit 124, the distance calculation unit 125, and the identification unit 126. Note that the control program PG1 may also include, for example, an operating system program for the processing device 120 to control each unit of the securities processing device 10. The image information acquisition unit 122 is an example of an "acquisition unit," the feature extraction unit 124 is an example of a "generation unit," and the distance calculation unit 125 is an example of a "calculation unit."

[0028] The image information acquisition unit 122 acquires, for example, first image information indicating a first image, which is an image of the gift certificate GT to be identified, from the image input device 130. Note that if the image input device 130 stores the first image information in a shared memory (not shown), the image information acquisition unit 122 may acquire the first image information from the shared memory. Also, the image information acquisition unit 122 may acquire first side image information indicating an image of the first side of the gift certificate GT to be identified, and second side image information indicating an image of the second side opposite the first side of the gift certificate GT to be identified. Note that one of the first and second sides of the gift certificate GT corresponds to the front side of the gift certificate GT, and the other of the first and second sides corresponds to the back side of the gift certificate GT. In this embodiment, it is assumed that the image information acquisition unit 122 acquires first side image information and second side image information.

[0029] The front surface identification unit 123 identifies the front and back surfaces of the gift certificate GT to be identified based on the number of contours included in the image of the first surface indicated by the first surface image information and the number of contours included in the image of the second surface indicated by the second surface image information. For example, the front surface identification unit 123 identifies the first or second surface with the fewest contours as the front surface of the gift certificate GT, and identifies the surface with the most contours as the back surface of the gift certificate GT. The front surface identification unit 123 then identifies the image information showing the image of the front surface of the first surface image information or the second surface image information as the first image information. Note that the number of contours included in an image can be calculated using, for example, a known method for detecting edges included in an image (e.g., the Canny algorithm).

[0030] The feature extraction unit 124 generates a feature vector indicating the feature amounts of an image by executing a process for generating a feature vector on the first image (an image of the front side of the gift certificate GT to be recognized) indicated by the first image information acquired by the image information acquisition unit 122. The feature extraction unit 124 then generates feature information indicating the feature vector of the first image. The process for generating a feature vector includes, for example, multiple convolution layers and pooling layers in a convolutional neural network. In this embodiment, for example, the feature extraction unit 124 generates the feature vector of the first image using a model that has been trained (metric learning) to reduce the distance between feature vectors of multiple images of the same note type and increase the distance between feature vectors of multiple images of different note types. In this way, in this embodiment, a model that has undergone metric learning specifically for gift certificates is used.

[0031] The distance calculation unit 125 calculates the inter-vector distance, which is the distance between the feature vector of the second image, which is an image of the reference gift certificate GT, and the feature vector of the first image. Here, the reference gift certificate GT is, for example, a gift certificate GT in which the feature vector of the image (second image) of the front of the gift certificate GT and the type (denomination) of the gift certificate GT are associated with each other and registered in the denomination table TBL. For example, the reference gift certificate GT is associated with denomination information indicating the type of gift certificate GT and feature information indicating the feature vector of the image of the front of the gift certificate GT.

[0032] The recognition unit 126 recognizes the gift certificate GT to be recognized based on the inter-vector distance. For example, the recognition unit 126 determines whether the inter-vector distance is equal to or less than a first distance. If the inter-vector distance is equal to or less than the first distance, the recognition unit 126 determines that the first image and the second image are the same or similar (highly related), and if the inter-vector distance is greater than the first distance, the recognition unit 126 determines that the first image and the second image are different (lowly related).

[0033] Here, for example, the first distance is set to a value that allows the types of the two gift certificates GT shown by the first image and the second image to be considered to be the same if the distance between the feature vectors of the first image and the feature vectors of the second image (inter-vector distance) is equal to or less than the first distance. Therefore, in this embodiment, when a second image in which the inter-vector distance is equal to or less than the first distance is identified, the recognition unit 126 determines that the type of the gift certificate GT to be recognized is the same as the type of the reference gift certificate GT represented by the second image in which the inter-vector distance is equal to or less than the first distance. In other words, when a second image in which the inter-vector distance is equal to or less than the first distance is identified, the recognition unit 126 identifies the denomination information of the reference gift certificate GT represented by the identified second image as the denomination information of the gift certificate GT to be recognized.

[0034] The first distance can be set arbitrarily, but setting the first distance large increases the percentage of identifiable gift certificates GT, but at the same time increases the risk of misrecognition. On the other hand, setting the first distance small decreases the percentage of identifiable gift certificates GT, but reduces the risk of misrecognition. Therefore, it is preferable to set the first distance appropriately according to the required standards. Furthermore, by setting the first distance to "1.0," "10," or "100" for convenience, it is possible to make the judgment criteria easier to understand.

[0035] When the recognition unit 126 identifies a second image in which the inter-vector distance is less than the first distance, the control unit 220 of the POS register 20 reflects this in the settlement process via the communication device 160 depending on the type of gift certificate GT identified.

[0036] The POS register 20 has a display device 210 and a control unit 220. The display device 210 is an output device such as a display, and also functions as an operation panel, which is an input device for the POS register 20. As described above, in this embodiment, it is assumed that the display device 210 is integrated with an operation device (e.g., a touch panel) that accepts operations by an administrator of the securities processing device 10. The control unit 220 performs the settlement process for normal purchased products, and the display device 210 displays and inputs information associated with the settlement process. Furthermore, when a new gift certificate GT or the like is registered in the securities processing device 10, the display device 210 displays an image such as a confirmation screen SC shown in FIG. 5, which will be described later, under the control of the control unit 220. Here, the control unit 220 may be realized by a processor (not shown) executing a program, or may be realized by hardware.

[0037] The configuration of the settlement processing system 1 is not limited to the example shown in FIG.

[0038] The settlement processing system 1 may identify the gift certificate GT by having an existing application call an API (Application Programming Interface) related to the processing of each of the image information acquisition unit 122, surface identification unit 123, feature extraction unit 124, distance calculation unit 125, identification unit 126, and control unit 220.

[0039] Furthermore, the processing device 120 and storage device 140 of the securities processing device 10 may be provided outside the securities processing device 10, rather than inside the securities processing device 10, and may be communicatively connected to the image input device 130 via a network such as a LAN (Local Area Network). In this case, the securities processing device 10 may function as a server for identifying gift certificates GT.

[0040] Next, an example of the bill type table TBL will be described with reference to FIG.

[0041] Fig. 3 is an explanatory diagram for explaining an example of the certificate type table TBL shown in Fig. 2. The certificate type table TBL has, for example, one or more records. In the example shown in Fig. 3, the certificate type table TBL has multiple records that correspond one-to-one to the multiple types of gift certificates GT registered in the certificate type table TBL.

[0042] Each record in the denomination table TBL includes, for example, denomination information, information indicating the storage location of image information, and information indicating the storage location of feature information. The denomination information also includes, for example, identification information, information indicating the denomination name, and information indicating the face value. The identification information is information for identifying each type of gift certificate GT from among multiple types. The denomination name is the name of the type of gift certificate GT corresponding to the identification information. For example, the denomination name is displayed on a confirmation screen SC shown in Figure 5, which will be described later, so that employees of a retail store where the display device 210 is installed can easily recognize the type of gift certificate GT used at the retail store. The face value is the amount written on the gift certificate GT.

[0043] Here, the types of gift certificates GT are classified, for example, by a combination of the issuer and face value of the gift certificate GT. Therefore, for example, three gift certificates GT corresponding to three types of certificates with identification information "001", "002", and "003" have the same issuer of the gift certificate GT but are of different types because their face values ​​are different. Also, for example, three gift certificates GT corresponding to three types of certificates with identification information "003", "006", and "022" have the same face value but are of different types because their issuers are different.

[0044] The types of gift certificates GT are not limited to a combination of the issuer and face value of the gift certificate GT. For example, the types of gift certificates GT may be categorized by the issuer of the gift certificate GT. Alternatively, for example, if a single company that issues gift certificates GT issues multiple different brands of gift certificates GT, the types of gift certificates GT may be categorized by a combination of the issuer, face value, and brand of the gift certificate GT. Brands of gift certificates GT may include nationwide gift certificates GT and regional gift certificates GT.

[0045] The storage location of the image information is, for example, an address indicating a memory area in which image information showing an image of the front side and an image of the back side of the gift certificate GT corresponding to the denomination indicated by the identification information is stored. Also, the storage location of the feature information is, for example, an address indicating a memory area in which feature information showing a feature vector of the image of the front side of the gift certificate GT corresponding to the denomination indicated by the identification information is stored. Note that one or both of the image information and the feature information may be stored in the memory device 140 in which the denomination table TBL is stored, or may be stored in a memory device different from the memory device 140.

[0046] In this way, in the certificate type table TBL, the type of gift certificate GT, the image, and the feature vector are associated with each other.

[0047] [How to register] Next, a method for registering a new gift certificate TG in the certificate type table TBL will be described with reference to the flowchart of FIG.

[0048] FIG. 4 is a flowchart showing an example of the operation of the settlement processing system 1 when registering a gift certificate GT in the certificate type table TBL. A store employee or the like can register a gift certificate GT using the display device 210. The first gift certificate GT to be registered will be described as a 1000 yen XX gift card with identification information "001" in the certificate type table TBL of FIG. 3. In the following, the nth gift certificate GT may be referred to as a gift certificate GTn. For example, in FIG. 4, the 1000 yen XX gift card with identification information "001" shown in FIG. 3, i.e., the first gift certificate GT to be registered, is also referred to as gift certificate GT1. The gift certificate TG registered in the certificate type table TBL by the operation shown in FIG. 4 corresponds to a "reference security." In this embodiment, registering a gift certificate GT corresponds to storing multiple pieces of information related to the gift certificate GT (such as the identification information, certificate type name, face value, storage location of image information, and storage location of characteristic information of the gift certificate GT1) in association with each other in the storage device 140. In addition, in this embodiment, storing multiple pieces of information related to the gift certificate GT in correspondence with each other in a memory such as the storage device 140 may be referred to as storing multiple pieces of information related to the gift certificate GT in correspondence with each other in the certificate type table TBL.

[0049] When registration is started using the display device 210, first, in step S51, the processing device 120 functions as the image information acquisition unit 122 and acquires first side image information and second side image information, which respectively show images of the first and second sides of the gift certificate GT to be registered, from the image input device 130.

[0050] Next, in step S52, the processing device 120 functions as the front side identification unit 123 and executes a front side identification process to identify which of the first and second sides is the front side of the gift certificate GT. Details will be explained in Figure 7, but for example, the front side identification unit 123 identifies the image of the front side of the gift certificate GT1 based on the number of contours in the image of the first side and the number of contours in the image of the second side. Note that if the front side of the gift certificate has been identified in step S51, step S52 can be omitted by acquiring only the image of the front side.

[0051] Next, in step S53, the processing device 120 functions as the feature extraction unit 124 and calculates a feature vector indicating the feature quantities of the image (second image) of the front of the gift certificate GT1 identified in step S52. That is, the feature vector of the second image is calculated by the processing of step S53. A model trained by the aforementioned metric learning is used to calculate the feature vector. The feature vector of the gift certificate GT1 to be initially registered is positioned in a certain region (first region) in a specific space.

[0052] Next, in step S54, the processing device 120 stores the image information of the front side of the gift certificate GT1 identified in step S52 in the image information storage location "ab123" shown in Figure 3. In addition, the processing device 120 stores the feature vector calculated in step S53 in the feature information storage location "tke98" shown in Figure 3. The processing device 120 may store the image information of the front side of the gift certificate GT1 immediately after step S52.

[0053] Next, in step S55, the processing device 120 stores the identification information, denomination name, face value, storage location of image information, and storage location of characteristic information of the gift certificate GT1 in the denomination table TBL in association with each other. Identification information is automatically issued each time a new gift certificate TG is registered. The employee confirms the gift certificate TG to be registered, inputs the denomination name and face value, for example, via the display device 210, and stores them in the storage device 140. Note that the issuance of the identification information and the input of the denomination name and face value may be performed before step S51, in which image information of the gift certificate GT is acquired, rather than step S55. Furthermore, the denomination name and face value may be read from the image information acquired in step S51 using OCR (Optical Character Recognition) processing or the like, and stored in the storage device 140, rather than being input by the employee. The registration of the gift certificate GT1 is completed by storing the identification information, denomination name, face value, storage location of image information, and storage location of feature information of the gift certificate GT1 in correspondence with each other in the denomination table TBL.

[0054] Next, in step S56, the processing device 120 checks whether there are any gift certificates to be subsequently registered, and if there are no gift certificates to be subsequently registered, the registration is completed. If there are any gift certificates to be subsequently registered, the second gift certificate GT2 is registered.

[0055] The second gift certificate GT2 to be registered is a 5,000 yen XX gift card whose identification information is "002" in the certificate type table TBL of FIG. 3. The processing device 120 executes a series of processes from step S51 to step S55, just like with the gift certificate GT1. Image information on the front of the gift certificate GT2 is stored in the image information storage location "kh296" shown in FIG. 3. The feature vector calculated in step S53 is stored in the feature information storage location "raw47" shown in FIG. 3.

[0056] The calculation of the feature vector of the front image of the gift certificate GT2 in step S53 is performed in an area (second area) that is distant from the first area that indicates the feature vector of the already registered gift certificate GT1.

[0057] Similarly, in step S53, the feature vectors of the nth gift certificate GTn from the third onwards are positioned in an area (nth area) that is distant from each of the n-1 areas of the n-1 gift certificates already registered.

[0058] In this way, the denomination table TBL stores the identification information, denomination name, face value, storage location of image information, and storage location of feature information of each gift certificate TGn.

[0059] This method of registering a new gift certificate TG in the certificate type table TBL involves reading in one gift certificate TG to be registered, and using Metric Learning (distance learning), positioning it in the spatial domain of the feature vector of an already registered gift certificate GT and in the spatial domain of a feature vector that is a predetermined distance away.

[0060] 4 may be executed by a server communicatively connected to the securities processing device 10. Furthermore, the configuration of the note type table TBL is not limited to the example shown in FIG. 3. For example, each record in the note type table TBL may include the characteristic information itself instead of information indicating the storage location of the characteristic information. Furthermore, for example, each record in the note type table TBL may include the image information itself instead of information indicating the storage location of the image information.

[0061] The bill type table TBL stored in the storage device 140 can also be read by the control unit 220 and displayed on the display device 210 for confirmation and correction.

[0062] [Identification method] Settlement process Next, with reference to FIGS. 5 and 6, a method for identifying the gift certificate TG to be used when a customer purchases a product and for settlement using the POS register 20 and the change dispenser 30 will be described.

[0063] Fig. 5 is an explanatory diagram illustrating an example of a confirmation screen SC displayed on the display device 210 when the gift certificate TG to be identified is read by the image input device 130. Fig. 5 shows a screen that is displayed on the display device 210 when a store employee confirms the gift certificate GT that a customer wishes to use, using the confirmation screen SC, when the POS register 20 is a normal face-to-face register or a semi-self-service register. When the POS register 20 is a self-service register, the confirmation screen SC is not displayed on the display device 210.

[0064] For example, when the securities processing device 10 performs the operation shown in Fig. 6 described below, the display device 210 displays a confirmation screen SC including the recognition result by the processing device 120 of the securities processing device 10. For example, the gift certificate GT to be identified is identified as a denomination of the multiple denominations registered in the denomination table TBL, the denomination having an inter-vector distance that is equal to or less than a first distance.

[0065] The confirmation screen SC displays, for example, the reading order, the denomination, the face value, the reference image RIMG, the read image, and a plurality of buttons BT for a GUI (Graphical User Interface).

[0066] The reading order is, for example, the reading order when the image input device 130 reads multiple gift certificates GT to be identified. The denomination name is the name of the type of the gift certificate GT to be identified. For example, of the multiple denominations registered in the denomination table TBL, the denomination name of the denomination whose inter-vector distance is equal to or less than a first distance is identified as the denomination name of the gift certificate GT to be identified. The face value is the face value of the gift certificate GT to be identified. For example, of the face values ​​of the multiple denominations registered in the denomination table TBL, the face value of the same denomination as the gift certificate GT to be identified is identified as the face value of the gift certificate GT to be identified. Furthermore, the reference image RIMG is an image of the front of the gift certificate GT corresponding to the same denomination as the gift certificate GT to be identified among the multiple denominations registered in the denomination table TBL. For example, the reference image RIMG is read from a storage location for image information of the same denomination as the gift certificate GT to be identified among the multiple storage locations for image information registered in the denomination table TBL.

[0067] The read image is an image of the gift certificate GT to be identified (an image of the gift certificate GT read by the image input device 130). In the example shown in FIG. 5, an image IIMGf of the front side of the gift certificate GT to be identified and an image IIMGb of the back side of the gift certificate GT to be identified are displayed on the confirmation screen SC as images of the gift certificate GT to be identified. Note that the number area NAR in the image IIMGb of the back side of the gift certificate GT is an area in which a gift certificate number is written so that the card company that issued the gift certificate GT can manage the gift certificate GT. The number area NAR in which the gift certificate number is written varies depending on the card company or the type of certificate. There are also gift certificates GT that do not have a gift certificate number written on them. In this embodiment, the operation of the securities processing device 10 will be described, focusing on the identification of gift certificates GT, and therefore a case will be assumed in which the gift certificate number is not read; however, the gift certificate number may be read by the securities processing device 10, as shown in a first modified example described below.

[0068] The gift certificate GT with an unknown denomination shown in Figure 5 (gift certificate GT with reading order "4") is a gift certificate GT that has been determined not to correspond to any of the multiple denominations registered in the denomination table TBL.

[0069] A store employee who identifies a gift certificate GT can easily confirm whether the gift certificate GT to be identified has been correctly identified by checking the confirmation screen SC. For example, the employee may select a correctly identified gift certificate GT on the confirmation screen SC and confirm the identification of the selected gift certificate GT by pressing the "Confirm" button BT. Note that the identification of the gift certificate GT may also be confirmed without pressing the "Confirm" button BT. The employee may also select an incorrectly identified gift certificate GT on the confirmation screen SC and cancel the identification of the selected gift certificate GT by pressing the "Delete" button BT.

[0070] The confirmation screen SC is not limited to the example shown in Fig. 5. For example, buttons BT such as "Delete" and "Confirm" do not have to be displayed on the confirmation screen SC. Also, an operation screen for editing the note type table TBL, such as deleting a note type from the note type table TBL, may be displayed on the display device 210 separately from the confirmation screen SC.

[0071] Next, an outline of the operation of the securities processing device 10 will be described with reference to FIG.

[0072] FIG. 6 is a flowchart showing an example of the operation of the securities processing device 10 when a user uses a gift certificate TG to settle the payment for a purchased product.

[0073] The purchase amount is calculated when the user registers the purchased items in the POS register 20. The user then begins settling the purchase amount, and the following describes a case where part or all of the purchase amount is settled with a gift certificate TG.

[0074] First, the user inserts the gift certificate TG that the customer wishes to use into the insertion slot INP of the securities processing device 10. Then, in step S100, the processing device 120 of the securities processing device 10 functions as the image information acquisition unit 122 and acquires, from the image input device 130, first-side image information and second-side image information that respectively show images of the first and second sides of the gift certificate GT to be identified that the customer wishes to use.

[0075] Next, in step S200, the processing device 120 functions as the face identification unit 123 and executes a face identification process to identify which of the first and second faces is the face of the gift certificate GT. Details will be explained in Fig. 7, but for example, the face identification unit 123 identifies the image of the face of the gift certificate GT based on the number of contours in the image of the first face and the number of contours in the image of the second face.

[0076] Next, in step S300, the processing device 120 functions as the feature extraction unit 124 and calculates a feature vector indicating the feature amount of the image (first image) of the front of the gift certificate GT identified in step S200. That is, the feature vector of the first image is calculated by the processing of step S300.

[0077] Then, in step S400, the processing device 120 functions as the distance calculation unit 125 and calculates the inter-vector distance, which is the distance between the feature vector calculated in step S300 (the feature vector of the first image) and the reference feature vector of a reference gift certificate GT that has been registered in advance in the certificate type table TBL. The reference feature vector is, for example, the feature vector of the second image, which is an image of the reference gift certificate GT (the feature vector of the certificate type registered in the certificate type table TBL). For example, if multiple certificate types are registered in the certificate type table TBL, the distance calculation unit 125 calculates the inter-vector distance between the feature vector of each of the multiple certificate types (i.e., the feature vector of each of the multiple second images) and the feature vector of the first image. Therefore, if multiple certificate types are registered in the certificate type table TBL, multiple inter-vector distances corresponding to the multiple certificate types are calculated.

[0078] Next, in step S500, the processing device 120 functions as the identification unit 126 and searches for reference feature vectors whose inter-vector distance is equal to or less than a first distance. For example, the processing device 120 determines whether the inter-vector distance calculated in step S400 is equal to or less than the first distance. Note that, for example, if a plurality of inter-vector distances are calculated in step S400, the processing device 120 determines whether each of the plurality of inter-vector distances calculated in step S400 is equal to or less than the first distance.

[0079] Then, in step S520, the processing device 120 functions as the identification unit 126 and determines whether or not there is a reference feature vector whose inter-vector distance is equal to or less than the first distance.

[0080] If the result of the determination in step S520 is positive, since the corresponding gift certificate GT is present among the pre-registered gift certificates GT, the processing device 120 identifies the type of gift certificate GT to be processed in step S600.

[0081] In step S600, the processing device 120 functions as the recognition unit 126 and identifies the type of gift certificate GT to be recognized. For example, the recognition unit 126 identifies the type of gift certificate GT to be recognized as the type of gift certificate GT corresponding to a reference feature vector whose inter-vector distance is equal to or less than a first distance. Note that if there are multiple reference feature vectors whose inter-vector distance is equal to or less than the first distance, the recognition unit 126 may identify the type of gift certificate GT to be recognized as the type of gift certificate GT corresponding to the reference feature vector whose inter-vector distance is the smallest.

[0082] Furthermore, if the POS register is not a self-checkout register, an employee may identify the gift certificate GT by displaying on the confirmation screen SC, as shown in Figure 5, images of multiple gift certificates GT corresponding to multiple reference feature vectors whose inter-vector distance is less than or equal to a first distance, and an image of the gift certificate GT to be identified.

[0083] When the type of gift certificate TG is identified in step S600, the securities processing device 10 determines that the gift certificate GT can be used at the store. Then, in step S620, the control unit 220 of the POS register 20 executes a settlement process according to the face value of the gift certificate GT. For example, the securities processing device 10 transmits settlement process information (information indicating the recognition result of the recognition unit 126) according to the type of gift certificate GT identified by the recognition unit 126 to at least one of the POS register 20 and the change dispenser 30. The process of transmitting the settlement process information may be executed by the recognition unit 126 or may be executed by a functional block other than the recognition unit 126. For example, the processing device 120 may function as a settlement information processing unit that transmits settlement process information according to the type of gift certificate GT identified by the recognition unit 126 to at least one of the POS register 20 and the change dispenser 30. The POS register 20 and the change dispenser 30 execute a settlement process according to the face value of the gift certificate GT based on the settlement process information.

[0084] The settlement process, for example, is similar to that of a normal POS register, in that the face value of the gift certificate TG is subtracted from the customer's purchase amount and the subtracted amount is displayed to the customer, thereby prompting the customer to settle. When prompted to settle, the customer pays using a settlement method such as cash, credit card, prepaid card, or electronic currency.

[0085] If the result of the determination in step S520 is negative, the corresponding gift certificate GT was not found among the pre-registered gift certificates GT, and the processing device 120 returns the gift certificate GT to be processed in step S700. For example, the gift certificate GT to be returned is returned to the return port REP. The return of the gift certificate GT may be executed by the recognition unit 126, or may be executed by a functional block other than the recognition unit 126.

[0086] Furthermore, when returning the gift certificate GT, the settlement processing system 1 may clearly display on the display device 210 that "this gift certificate cannot be used at our store." Furthermore, in the case of a self-checkout, a store employee may be notified at the same time as the gift certificate GT is returned. Furthermore, the customer may stop using the gift certificate GT and continue the settlement process by means other than the gift certificate GT. Furthermore, although not shown in FIG. 6, it is also possible to interrupt the settlement process. Furthermore, by returning the gift certificate GT to the gift certificate GT return slot REP, it is possible to prevent the user from forgetting to pick it up.

[0087] In this way, the operation shown in FIG. 6 is completed.

[0088] Thus, in this embodiment, when a second image in which the inter-vector distance is equal to or less than the first distance is identified, the recognition unit 126 determines that the type of gift certificate GT to be recognized is the same as the type of reference gift certificate GT indicated by the second image in which the inter-vector distance is equal to or less than the first distance. Then, the control unit 220 may cause the display device 210 to display the second image in which the inter-vector distance is equal to or less than the first distance and the first image.

[0089] Next, the surface specification process of step S52 shown in FIG. 4 and step S200 shown in FIG. 6 will be described with reference to FIG.

[0090] Fig. 7 is a flowchart showing an example of the surface identification process shown in Fig. 4 and Fig. 6. For example, the processing device 120 functioning as the surface identification process of step 52 shown in Fig. 4 and step S200 shown in Fig. 6 executes a series of processes from step S220 to step S280 shown in Fig. 7. Therefore, the process of step S220 is executed after the process of step 51 shown in Fig. 4 or step S100 shown in Fig. 6 has been executed. Furthermore, after the process of step S280 has been executed, the process of step 53 shown in Fig. 4 or step S300 shown in Fig. 6 is executed.

[0091] First, in step S220, the surface specifying unit 123 calculates the number of contours (hereinafter also referred to as the contour number N1) included in the image of the first surface (the image indicated by the first surface image information).

[0092] Next, in step S222, the surface specifying unit 123 calculates the number of contours (hereinafter also referred to as the number of contours N2) included in the image of the second surface (the image indicated by the second surface image information).

[0093] Then, in step S240, the surface specifying unit 123 determines whether the number of contours N1 is equal to or less than the number of contours N2.

[0094] If the result of the determination in step S240 is positive, in step S260 the face identification unit 123 identifies the first face, which has the fewer contours, as the face of the gift certificate GT, and proceeds to step S280.

[0095] On the other hand, if the result of the determination in step S240 is negative, the face identification unit 123 in step S262 identifies the second face, which has the fewer contours, as the face of the gift certificate GT, and proceeds to step S280.

[0096] In step S280, the front surface identification unit 123 identifies the image of the front surface of the gift certificate GT as the image (first image) for which a feature vector is calculated.

[0097] In a typical gift certificate GT, the number of outlines on the front side is smaller than that on the back side, since the stores that accept the gift certificate GT and important notes are printed on the back side. For this reason, in this embodiment, as described above, of the first and second sides, the side with the fewer outlines is identified as the front side of the gift certificate GT.

[0098] Alternatively, for example, a method may be employed in which the number of characters on the first side and the number of characters on the second side are calculated by character recognition processing that recognizes characters contained in an image using optical character recognition (OCR) technology. In this case, the side with the fewest characters is identified as the front side of the gift certificate GT. However, the process of calculating the number of characters contained in an image by character recognition processing tends to take longer than the process of calculating the number of contours contained in an image. In other words, the time required for the process of calculating the number of contours contained in an image is shorter than the time required for the process of calculating the number of characters contained in an image by character recognition processing. Therefore, in this embodiment, the time required for the front side identification process to identify the front side of the gift certificate GT can be shortened compared to an embodiment in which the number of characters contained in the images of each of the first and second sides is calculated by character recognition processing.

[0099] Furthermore, the operation of the securities processing device 10 is not limited to the examples shown in FIGS. 4, 6, and 7. For example, if the front and back sides of a gift certificate GT are specified when the image input device 130 reads the gift certificate GT, the front side identification process of step S52 may be omitted from the operation shown in FIG. 4, and the front side identification process of step S200 may be omitted from the operation shown in FIG. 6. Furthermore, for example, in a mode in which information (e.g., a gift certificate number, etc.) printed on the back side of the gift certificate GT is not referenced, the image information acquisition unit 122 does not need to acquire image information indicating an image of the back side of the gift certificate GT to be identified. For example, the image information acquisition unit 122 acquires image information indicating an image of the front side of the gift certificate GT to be identified as first image information from the image input device 130. In this case, too, the front side identification process of step S52 may be omitted from the operation shown in FIG. 4, and the front side identification process of step S200 may be omitted from the operation shown in FIG. 6. Furthermore, for example, the process of step S222 in FIG. 7 may be executed before the process of step S220, or may be executed in parallel with the process of step S220.

[0100] 6 shows the operation of the securities processing device 10 when identifying one gift certificate GT to be identified (when one gift certificate GT is used for settlement) in order to make the operation of the securities processing device 10 easier to understand. Therefore, when identifying multiple gift certificates GT, the operation shown in FIG. 6 is repeatedly executed except for the processing of step S620. Note that when identifying multiple gift certificates GT, after acquiring all image information of the multiple gift certificates GT to be identified, the series of processing from steps S200 to S520, the processing of step S600 and the processing of step S700 may be repeatedly executed.

[0101] Here, in this embodiment, as described above, a model that has undergone distance learning specifically for gift certificates is used to identify gift certificates GT. Note that in a general method for identifying gift certificates GT (hereinafter also referred to as the comparative example), for example, an image recognition model that has been trained to identify gift certificates GT by type is used. In the comparative example that uses an image recognition model, in order to create an image recognition model, it is necessary to perform learning for identifying the type of gift certificate GT for each type of certificate using a large amount of training data. For this reason, in the comparative example, the time and effort required for learning increases.

[0102] In contrast, in this embodiment, a model generated by metric learning (distance learning) dedicated to gift certificates is used, so there is no need to use a large amount of training data for each type of gift certificate for learning. Therefore, as shown in the flowchart in Figure 4, when registering a new gift certificate GT, registration is completed by simply reading in one reference gift certificate GT, thereby reducing the time and effort required for learning. In other words, in this embodiment, it is possible to reduce the effort required to generate the information necessary to identify gift certificates GT.

[0103] Furthermore, since this embodiment uses a lightweight model compared to the image recognition model, it is possible to process the gift certificate GT to be recognized as shown in the flowchart of Figure 6 at a higher speed than conventional methods while maintaining at least the same accuracy as conventional methods. Furthermore, since a general personal computer can be used as the securities processing device 10, it can be realized at low cost.

[0104] In contrast, when training an image recognition model on a new denomination that has not been used to create the image recognition model, a large amount of training data for the new denomination is required. In contrast, in distance learning specifically for gift certificates, when a new denomination is added to the denomination table TBL, learning is completed with a single image. Therefore, in this embodiment, employees can easily add new denominations (add reference denominations).

[0105] Furthermore, in this embodiment, a feature vector is extracted from the image of the entire gift certificate GT. Then, based on the distance between the two feature vectors (vector distance), it is determined whether the two gift certificates GT corresponding to the two feature vectors are of the same type. Therefore, in this embodiment, it is possible to prevent a decrease in the accuracy of identifying the type of gift certificate GT due to noise such as stains, notes, and seal impressions on the gift certificate GT.

[0106] As described above, in this embodiment, the securities processing device 10 includes an image information acquisition unit 122 that acquires first image information indicating a first image, which is an image of the gift certificate GT to be recognized, a feature extraction unit 124 that generates a feature vector of the first image by executing a process on the first image to generate a feature vector indicating the feature quantities of the image, a distance calculation unit 125 that calculates the inter-vector distance, which is the distance between the feature vector of the first image and the feature vector of a second image, which is an image of each of a plurality of reference gift certificates GT that have been registered in advance, and a recognition unit 126 that recognizes the gift certificate GT to be recognized based on the inter-vector distance. The POS register 20 and the change dispenser 30 perform a settlement process for the product that the customer wishes to purchase based on the recognition result of the recognition unit 126.

[0107] In this manner, in this embodiment, the gift certificate GT to be identified is identified based on the inter-vector distance, which is the distance between the feature vector of the first image, which is an image of the gift certificate GT to be identified, and the feature vector of the second image, which is an image of the reference gift certificate GT. For this reason, in this embodiment, there is no need to perform learning for identifying the type of gift certificate GT for each type of gift certificate using a large amount of training data. As a result, in this embodiment, it is possible to reduce the time and effort required for learning. In other words, in this embodiment, it is possible to reduce the effort required to generate information (e.g., a trained model) required to identify the gift certificate GT.

[0108] Furthermore, in this embodiment, the feature vector of each of the second images of multiple reference gift certificates GT is calculated from the second image of one gift certificate GT for each reference by using a model trained by distance learning in the feature extraction unit 124. This allows the user to easily add reference gift certificates GT in this embodiment.

[0109] Furthermore, in this embodiment, when a second image in which the inter-vector distance is equal to or less than the first distance is identified, the recognition unit 126 determines that the type of the gift certificate GT to be recognized is the same as the type of the reference gift certificate GT indicated by the second image in which the inter-vector distance is equal to or less than the first distance. In this way, in this embodiment, the type of the reference gift certificate GT indicated by the second image in which the inter-vector distance is equal to or less than the first distance is identified as the type of the gift certificate GT to be recognized. This makes it possible to easily recognize the gift certificate GT to be recognized by type in this embodiment.

[0110] Furthermore, in this embodiment, in response to control from the securities processing device 10, when a second image in which the inter-vector distance is equal to or less than the first distance is identified, the control unit 220 of the POS register 20 can display the second image in which the inter-vector distance is equal to or less than the first distance and the first image on the display device 210. That is, in this embodiment, an image of the gift certificate GT to be identified (first image) and an image of a reference gift certificate GT of the same type as the gift certificate GT to be identified (second image) can be displayed on the display device 210. This allows an employee to easily check whether the gift certificate GT to be identified has been correctly identified.

[0111] Furthermore, in this embodiment, if the recognition unit 126 does not identify a second image in which the inter-vector distance is equal to or less than the first distance, the inserted gift certificate GT to be recognized is returned to the outside of the securities processing device 10. This makes it possible to prevent gift certificates GT that cannot be handled at the store from being used for settlement.

[0112] Furthermore, in this embodiment, if a second image in which the inter-vector distance is equal to or less than the first distance is not identified, the control unit 220 of the POS register 20 may cause the display device 210 to display that the gift certificate GT to be identified cannot be used for settlement processing. In this case, for example, a store employee can easily understand that the gift certificate GT inserted into the securities processing device 10 cannot be used at the store.

[0113] In this embodiment, the securities processing device 10 further includes a front side identification unit 123. The image information acquisition unit 122 acquires first side image information showing an image of the first side of the gift certificate GT to be identified, and second side image information showing an image of the second side opposite the first side of the gift certificate GT to be identified. The front side identification unit 123 identifies the front and back sides of the gift certificate GT to be identified based on the number of contours included in the image of the first side shown by the first side image information and the number of contours included in the image of the second side shown by the second side image information, and identifies the image information showing the image of the front side from the first side image information and the second side image information as first image information.

[0114] As described above, in this embodiment, the front and back sides of the gift certificate GT to be identified are identified based on the number of contours included in each image of the first and second sides of the gift certificate GT to be identified. This prevents the feature vector of the first image used to calculate the inter-vector distance from being extracted from the image of the back side of the gift certificate GT. As a result, this embodiment can efficiently identify the type of gift certificate GT to be identified. Furthermore, for example, a user can have the image input device 130 read the gift certificate GT without being aware of the front and back sides of the gift certificate GT. Therefore, this embodiment can improve usability when having the securities processing device 10 identify the gift certificate GT to be identified. Furthermore, in this embodiment, the front side of the gift certificate GT is identified based on the number of contours included in the image, which shortens the time required for the front side identification process to identify the front side of the gift certificate GT compared to when the front side of the gift certificate GT is identified based on the number of characters included in the image.

[0115] Furthermore, in this embodiment, the securities processing device 10 transmits settlement processing information according to the type of gift certificate GT identified by the recognition unit 126 to at least one of the POS register 20 and the change dispenser 30. As a result, in this embodiment, the POS register 20 and the change dispenser 30 can execute settlement processing according to the face value of the gift certificate GT based on the settlement processing information.

[0116] [2. Modifications] The present invention is not limited to the above-described exemplary embodiments. Specific modified embodiments are exemplified below. Two or more embodiments selected arbitrarily from the following examples may be combined.

[0117] [First Modification] In the above-described embodiment, the securities processing device 10 may read, from the gift certificate GT to be identified, a gift certificate number that is used by the card company to manage the gift certificate GT.

[0118] Figure 8 is an explanatory diagram for explaining an overview of the settlement processing system 1 according to the first modified example. Elements similar to those explained in Figures 1 to 7 are given the same reference numerals, and detailed explanations will be omitted.

[0119] The settlement processing system 1 shown in FIG. 8 has the same configuration as the settlement processing system 1 shown in FIG. 1. For example, the settlement processing system 1 includes a securities processing device 10 including a processing device 120, an image input device 130, a storage device 140, and a communication device 160, a POS register 20, and a change dispenser 30. However, the control program PG2 stored in the storage device 140 of the securities processing device 10 differs from the control program PG1 shown in FIG. 2. In this variation, the control program PG2 includes application programs for causing the processing device 120 to function as an image information acquisition unit 122, a surface identification unit 123, a feature extraction unit 124, a distance calculation unit 125, an identification unit 126, and a character recognition unit 127. Note that the control program PG2 may include, for example, an operating system program for the processing device 120 to control each unit of the securities processing device 10. Furthermore, the control program PG2 may be transmitted from another device via a network.

[0120] The processing device 120 shown in Fig. 8 is similar to the processing device 120 shown in Fig. 2, except that it executes a control program PG2 instead of the control program PG1 shown in Fig. 2. For example, by executing the control program PG2 stored in the storage device 140, the processing device 120 functions as an image information acquisition unit 122, a surface identification unit 123, a feature extraction unit 124, a distance calculation unit 125, an identification unit 126, and a character recognition unit 127. That is, this modification differs from the above-described embodiment in that the processing device 120 functions as the character recognition unit 127.

[0121] The image information acquisition unit 122, the surface identification unit 123, the feature extraction unit 124, the distance calculation unit 125, and the identification unit 126 are the same as those in the above-described embodiment. The following description will focus on the character recognition unit 127, which is different from the above-described embodiment.

[0122] The character recognition unit 127 recognizes the gift certificate number written in the number area NAR in image IIMGb by performing character recognition processing on the number area NAR in image IIMGb on the back of the gift certificate GT identified by the recognition unit 126. Note that the number area NAR in which the gift certificate number is written varies depending on the card company or type of gift certificate, as described in FIG. 5. Therefore, the character recognition unit 127 identifies the position of the number area NAR based on the type of gift certificate GT from which the gift certificate number is to be read. The character recognition unit 127 then performs character recognition processing on the number area NAR in image IIMGb on the back of the gift certificate GT.

[0123] Character recognition processing is performed on the number area NAR to recognize the gift certificate number of the gift certificate GT to be identified. For example, the character recognition unit 127 generates character information indicating the gift certificate number recognized by character recognition processing on the number area NAR in the image IIMGb on the back of the gift certificate GT. Note that the character recognition unit 127 may generate the character information by, for example, converting a character image indicating the gift certificate number written in the number area NAR into a character code by character recognition processing. Furthermore, when the image input device 130 stores first image information in a shared memory (not shown), the character recognition unit 127 may store the character information indicating the gift certificate number recognized by character recognition processing in the shared memory in association with the first image information.

[0124] The character recognition process by the character recognition unit 127 to recognize the gift certificate number of the gift certificate GT to be identified is executed, for example, after the process of step S600 shown in Fig. 6 is executed. Therefore, in this modified example, if the type of gift certificate GT to be identified is unknown, the character recognition process to recognize the gift certificate number of the gift certificate GT is not executed. As a result, in this modified example, the character recognition process to recognize the gift certificate number of the gift certificate GT can be executed efficiently.

[0125] Furthermore, in step S620 shown in FIG. 6, the control unit 220 may cause the display device 210 to display the gift certificate number recognized by the character recognition unit 127 in addition to the image of the gift certificate GT to be identified.

[0126] As described above, this modified example can also achieve the same effects as the above-described embodiment. Furthermore, in this modified example, since the gift certificate number is read from the gift certificate GT whose type has been identified, the read gift certificate GT can be identified as a used gift certificate GT and processed (deleted), and tasks such as managing the gift certificate GT can be performed efficiently.

[0127] [Second Modification] In the above-described embodiment and modified examples, multiple images of gift certificates GT may be associated with one piece of certificate type information. In this case, for example, multiple feature vectors extracted from multiple images of gift certificates GT are associated with one piece of certificate type information. In this modified example, even if multiple designs of gift certificates GT exist for the same certificate type due to design changes, for example, it is possible to identify the gift certificates GT by type while preventing the management of reference gift certificates GT from becoming complicated.

[0128] As described above, in this modified example, the same effects as those of the second embodiment can be obtained.

[0129] [Third Modification] In the above-described embodiment and modified example, the settlement processing system 1 is a securities processing system that identifies securities such as gift certificates GT by type, but the present invention is not limited to this embodiment. For example, the settlement processing system 1 may be a system that identifies non-securities other than securities (e.g., service vouchers, coupons, discount vouchers, etc.). As described above, this modified example can also achieve the same effects as the above-described embodiment and modified example.

[0130] [Fourth Modification] In the above-described embodiment and modified example, the securities processing device 10 may identify the gift certificates GT and tally them by type. For example, the securities processing device 10 may tally the gift certificates GT by type according to the identification result in the identification unit 126. Specifically, the processing device 120 may function as an identification processing unit that tally the gift certificates GT by type of gift certificate GT identified by the identification unit 126. As described above, in this modified example, the same effects as those of the above-described embodiment and modified example can be obtained. [Explanation of symbols]

[0131] 1... settlement processing system, 10... securities processing device, 20... POS register, 30... change dispenser 120...processing device, 122...image information acquisition unit, 123...surface identification unit, 124...feature extraction unit, 125...distance calculation unit, 126...identification unit, 127...character recognition unit, 130...image input device, 140...storage device, 160...communication device, 210...display device, 220...control unit, GT...gift certificate.

Claims

1. A settlement processing system having at least a POS register, a settlement processing device, and a securities processing device, The securities processing device comprises: an acquisition unit that acquires first image information indicating a first image that is an image of the inserted security to be identified; a generation unit that generates a feature vector of the first image by executing a process for generating the feature vector indicating a feature amount of the image on the first image; a calculation unit that calculates an inter-vector distance between the feature vector of a second image, which is an image of each of a plurality of reference securities registered in advance, and the feature vector of the first image; an identification unit that identifies the securities to be identified based on the inter-vector distance; Equipped with The POS register and the settlement processing device are and executing a payment process for the product that the customer wishes to purchase according to the recognition result of the recognition unit. A settlement processing system characterized by:

2. The settlement processing system described in claim 1, characterized in that the feature vector of each of the second images of the securities of the multiple references is calculated from the second image of one security in each reference by using a model trained by metric learning in the generation unit.

3. The identification unit when the second image in which the inter-vector distance is equal to or less than the first distance is identified, it is determined that the type of the security to be identified is the same as the type of the reference security indicated by the second image in which the inter-vector distance is equal to or less than the first distance; 3. The settlement processing system according to claim 1 or 2.

4. The POS register has at least a display device and a control unit, The control unit When the second image in which the inter-vector distance is equal to or less than the first distance is identified, the second image in which the inter-vector distance is equal to or less than the first distance and the first image are displayed on the display device.

4. The settlement processing system according to claim 3.

5. The settlement processing system described in claim 1 or 2, characterized in that if the identification unit does not identify the second image in which the vector distance is less than the first distance, the inserted securities to be identified are returned outside the securities processing device.

6. The POS register has at least a display device and a control unit, The control unit If the second image in which the inter-vector distance is equal to or less than the first distance is not identified, a message indicating that the securities to be identified cannot be used for the settlement process is displayed on the display device.

6. The settlement processing system according to claim 5.

7. The security processing device further includes a surface identification unit, The acquisition unit acquiring first-side image information indicating an image of a first side of the security to be identified and second-side image information indicating an image of a second side of the security to be identified that is opposite to the first side; The surface specifying unit is Identifying the front and back of the security to be identified based on the number of contours included in the image of the first side indicated by the first side image information and the number of contours included in the image of the second side indicated by the second side image information; Identifying, as the first image information, image information showing an image of the front side out of the first side image information and the second side image information.

3. The settlement processing system according to claim 1 or 2.

8. the securities processing device counts the securities by type in accordance with the recognition result of the recognition unit; 3. The settlement processing system according to claim 1 or 2.

9. The securities processing device comprises: a communication link between the POS register and the settlement processing device, and transmitting settlement processing information corresponding to the type of securities identified by the identification unit to at least one of the POS register and the settlement processing device; 3. The settlement processing system according to claim 1 or 2.

10. acquiring first image information indicating a first image which is an image of the inserted security to be identified; generating a feature vector of the first image by executing a process for generating a feature vector indicating a feature amount of the image on the first image; calculating an inter-vector distance between the feature vector of a second image, which is an image of each of a plurality of reference securities registered in advance, and the feature vector of the first image; Identifying the securities to be identified based on the inter-vector distance; and executing a settlement process for the product that the customer wishes to purchase using a POS register and a settlement processing device according to the identification result of the securities to be identified. A settlement processing method characterized by:

Images