JP2016206839A - Medium recognition device and transaction device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To reduce a data amount when the image data of the identification information part of a medium is stored.SOLUTION: The present invention relates to a medium recognition device for recognizing the medium. The medium recognition device includes image acquisition means for imaging the medium and acquiring an image picture, medium identification information recognition means for recognizing the medium identification information of the medium from the image picture acquired by the image acquisition means, reliability calculation means for calculating the reliability of a recognition result, in the medium identification information recognized by the medium identification information recognition means, character area image acquisition means for acquiring the character area image of a character constituting the medium identification information from the image picture, and image processing means for performing conversion processing for conversion into an image having resolution based on the reliability calculated by the reliability calculation means, in the character area image.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a medium recognition device and a transaction device, and can be applied to a device that stores image data of a banknote, for example, when a serial number of a banknote to be handled is recognized.

  2. Description of the Related Art Conventional transaction apparatuses such as ATM (Automated Teller Machine) are provided with a medium recognition apparatus that recognizes the type and serial number of banknotes to be handled. And in conventional ATM, in order to manage the origin etc. of a banknote, the image data of a serial number part may be cut out and preserve | saved (for example, refer patent document 1).

JP 11-328493 A

  However, in the conventional ATM, when the image data of the serial number part is stored for a large amount of banknotes, the capacity of the image data of the serial number part stored in the apparatus becomes a problem.

  Therefore, there is a demand for a medium recognition device and a transaction device that can reduce the data amount when storing image data of identification information (for example, serial number) portions of a medium (for example, banknote).

  The first aspect of the present invention includes (1) image acquisition means for capturing an image of a medium and acquiring an image, and (2) medium identification information for recognizing medium identification information of the medium from the image image acquired by the image acquisition means. Recognizing means, (3) reliability calculating means for calculating the reliability of the recognition result for the medium identification information recognized by the medium identification information recognizing means, and (4) characters constituting the medium identification information from the image image. Character area image acquisition means for acquiring a character area image; and (5) Image processing means for performing conversion processing for converting the character area image into an image having a resolution based on the reliability calculated by the reliability calculation means. It is characterized by that.

  According to a second aspect of the present invention, in a transaction apparatus for performing a transaction using a medium, the medium recognition apparatus for recognizing a medium to be handled is provided, and the medium recognition apparatus of the first aspect of the present invention is applied as the medium recognition apparatus. Transaction equipment.

  ADVANTAGE OF THE INVENTION According to this invention, the medium recognition apparatus and transaction apparatus which reduce the data amount at the time of preserve | saving the image data of the identification information part of a medium can be provided.

It is the block diagram shown about the functional structure of ATM which concerns on 1st Embodiment. It is a perspective view of the appearance of ATM concerning a 1st embodiment. It is explanatory drawing shown about the structure of the image sensor which concerns on 1st Embodiment. It is explanatory drawing shown about the structural example of the banknote handled by ATM which concerns on 1st Embodiment. It is explanatory drawing shown about the example of the process which the recognition process part and image process part which concern on 1st Embodiment perform. It is explanatory drawing shown about the example of a setting of the image process part which concerns on 1st Embodiment. It is the flowchart shown about operation | movement of ATM (medium recognition part) which concerns on 1st Embodiment. It is the block diagram shown about the functional structure of ATM which concerns on 2nd Embodiment. It is explanatory drawing shown about the structural example of the resolution setting information hold | maintained at the medium recognition part which concerns on 2nd Embodiment. It is the flowchart shown about operation | movement of ATM (medium recognition part) which concerns on 2nd Embodiment. It is the block diagram shown about the functional structure of ATM which concerns on 3rd Embodiment. It is the flowchart shown about operation | movement of ATM (medium recognition part) which concerns on 3rd Embodiment.

(A) First Embodiment Hereinafter, a first embodiment of a medium recognition device and a transaction device according to the present invention will be described in detail with reference to the drawings. In the first embodiment, an example in which a transaction apparatus equipped with the medium recognition apparatus of the present invention is applied to ATM will be described. In the first embodiment, an example in which the medium recognition device of the present invention is applied to a medium recognition unit will be described.

(A-1) Configuration of the First Embodiment FIG. 1 is a block diagram showing the configuration of the ATM 1 of this embodiment. FIG. 2 is a diagram showing an outline of the appearance of the ATM 1 of this embodiment.

  ATM1 has the control part 10, the memory | storage part 20, host I / F30, the operation display part 40, the card | curd process part 50, the banknote process part 60, and the coin process part 70. FIG.

  The control unit 10 has a function of controlling the operation of each unit in the ATM 1. For example, the control unit 10 may be realized by installing a program in a program implementation configuration (computer) including a processor, a memory, and the like.

  The storage unit 20 is a storage unit that holds data such as programs and parameters necessary for the operation of the control unit 10. As the storage unit 20, for example, a nonvolatile memory such as a hard disk drive or a flash memory can be applied.

  The host I / F 30 is a network interface for the ATM 1 to communicate with an external host 2 device.

  The operation display unit 40 has a user interface function. The type of device applied to the operation display unit 40 is not limited. In ATM1 of this embodiment, it demonstrates as what applies a touch panel display as the operation display part 40. FIG. In ATM1, it is possible to display various operation screens (GUI) on the operation display unit 40 and accept information output to the user and operation input from the user.

  Under the control of the control unit 10, the card processing unit 50 takes in a card (cash card) inserted from the customer into the card insertion / ejection slot 51 and records the recorded data (magnetic recording data, IC chip, etc.) of the card. Data) is read.

  The banknote processing unit 60 performs processing for receiving and storing banknotes according to control from the control unit 10 and withdrawal (discharge) of stored banknotes. The banknote processing unit 60 deposits and withdraws banknotes at a banknote deposit / withdrawal port 61.

  The coin processing unit 70 receives and stores coins according to control from the control unit 10 and performs withdrawal (discharge) of stored coins. The coin processing unit 70 deposits and withdraws coins at a coin deposit / withdrawal port 71.

  Next, the details of the internal configuration of the banknote processing unit 60 will be described. The banknote processing unit 60 includes a banknote deposit / withdrawal port 61, a conveyance path 62, a temporary storage unit 63, a banknote storage unit 64, and a medium recognition unit 200.

  The transport path 62 has a function of transporting banknotes in the banknote processing unit 60. The conveyance path 62 can be realized using, for example, a belt for nipping and conveying banknotes, a roller for driving the belt, a blade for switching the direction of the banknotes to be conveyed, and the like.

  The banknote deposit / withdrawal port 61 has a function of accepting insertion of banknotes from a customer and a function of dispensing (ejecting and dispensing) banknotes to a customer.

  The banknote storage unit 64 has a function of storing banknotes. The banknote storage unit 64 stores banknotes (storage of banknotes supplied from the transport path 62) and feeds out banknotes stored therein (feeds banknotes to the transport path 62).

  The temporary storage unit 63 has a function of temporarily storing banknotes taken from the banknote deposit / withdrawal port 61, banknotes fed out from the banknote storage unit 64, and the like.

  The medium recognizing unit 200 has a function of recognizing banknotes passing through the conveyance path 62 (such as banknotes deposited from the banknote deposit / withdrawal port 61 and banknotes fed out from the banknote storage unit 64). The medium recognizing unit 200 recognizes, for example, the denomination of the banknote, the authenticity of the banknote, the degree of corruption of the banknote, and the serial number of the banknote.

  Next, a detailed configuration of the medium recognition unit 200 will be described.

  The medium recognition unit 200 includes a medium detection unit 201, an image sensor 202, an AD conversion unit 203, a recognition processing unit 204, and an image processing unit 205.

  The medium detection unit 201 is a sensor that detects the position of a banknote passing on the transport path 62. For example, the medium detection unit 201 may be configured to optically detect the position of a bill passing over the transport path 62.

  The image sensor 202 is a sensor that acquires an image image obtained by capturing the banknote detected by the medium detection unit 201.

  FIG. 3 is an explanatory diagram showing a configuration example of the image sensor 202.

  As shown in FIG. 3, the image sensor 202 includes a light source 202a and a light receiving sensor 202b. The light source 202a irradiates the banknote M passing on the transport path 62 with light. And the light reception sensor 202b images the banknote M irradiated with light by the light source 202a (receives the reflected light of the banknote M). In the medium recognition unit 200, when a bill is detected by the medium detection unit 201, a light emission instruction is given to the light source 202a. In the light receiving sensor 202b, the shading pattern of the banknote M can be obtained according to the strength (reflectance) of the reflected light of the banknote M. Moreover, in the medium recognition part 200, it is desirable to adjust the sensitivity of the light receiving sensor 202b in advance so that the background portion where the banknote M does not exist is black.

  The AD conversion unit 203 digitizes (quantizes) the signal (analog signal) of the image image received by the light receiving sensor 202b and converts it into image data.

  The recognition process part 204 performs the recognition process (For example, the process which recognizes the denomination of a banknote, the authenticity of a banknote, the corruption degree of a banknote, the serial number of a banknote, etc.) about the banknote which passes the conveyance path 62. The recognition processing unit 204 performs banknote recognition processing using, for example, image data (image data obtained by capturing a banknote) acquired by the AD conversion unit 203. Note that the recognition processing unit 204 may recognize the banknote using other sensors (for example, a sensor that detects the thickness of the banknote) in addition to the image data obtained by imaging the banknote. The recognition processing unit 204 of this embodiment will be described as recognizing at least the serial number of each bill. The recognition processing unit 204 is not limited to recognition items other than banknote serial numbers.

  The recognition processing unit 204 recognizes a serial number (each character constituting the serial number) attached to the banknote based on the image data acquired by the AD conversion unit 203. In addition, when the recognition processing unit 204 performs character recognition for each character of the serial number (characters including numerals and alphabets), the recognition processing unit 204 also calculates the reliability (a numerical value representing the accuracy of the recognition result) related to each recognized character. . The recognition processing unit 204 notifies the control unit 10 of a recognition result (a recognition result of each item including a serial number).

  The image processing unit 205 performs image data compression processing according to the recognition result of the recognition processing unit 204. The image processing unit 205 performs compression processing (data amount compression processing) according to the reliability recognized by the recognition processing unit 204 for each character constituting the serial number. Then, the image processing unit 205 supplies the processed image data to the control unit 10. And the control part 10 records the acquired image data in the memory | storage part 20 in the format which can be managed for every banknote.

  Next, an outline of processing performed by the medium recognition unit 200 will be described.

  FIG. 4 is an explanatory diagram showing a configuration example of the banknote M. 4A is a schematic plan view of the banknote M. FIG. As shown in FIG. 4A, a serial number composed of nine characters (numbers or alphabets) is printed on the lower right end of the banknote M. FIG. 4B is an enlarged view showing the area of the banknote M on which the serial number is printed.

  The recognition processing unit 204 performs serial number recognition processing by paying attention to the area of the banknote M on which the serial number is printed (hereinafter referred to as “serial number area”). In the following, an image in the serial number region (an image captured by the image sensor 202) is referred to as a “serial number region image”.

  FIG. 5 is an explanatory diagram showing an example of processing performed by the recognition processing unit 204 and the image processing unit 205.

  FIG. 5A is a diagram showing an example of a serial number region image.

  As shown in FIG. 5B, the recognition processing unit 204 divides the serial number area image into areas for one character (hereinafter referred to as “character areas”), and images of the respective character areas (hereinafter referred to as “character areas”). Character recognition processing is performed for “character area image”. In addition, the recognition processing unit 204 obtains the character recognition reliability (character recognition reliability) when the character recognition process is performed for each character region. Note that the recognition processing unit 204 may perform character recognition for the serial number region image in a lump and then recognize and divide each character region.

  In this embodiment, the recognition processing unit 204 obtains the character recognition reliability by quantifying each character area (each character constituting the serial number) in 11 steps from the lowest 0 to the highest 10. And

  The method for obtaining the reliability of character recognition by the recognition processing unit 204 is not limited. For example, for each character region image, the acquired character region image and the character recognition dictionary (recognized character reference and The reliability of character recognition may be calculated based on the cumulative value (sum) of the difference from the image. For example, when the recognition processing unit 204 recognizes that an image of an arbitrary character area is a character “A”, the recognition processing unit 204 acquires an image (character recognition dictionary) serving as a reference for “A”, The difference may be accumulated, and the greater the accumulated value of the difference, the lower the reliability. The recognition processing unit 204 compares the degree of similarity between the acquired image of the character region and the character recognition dictionary (an image serving as a reference for the recognized character) using various character comparison techniques, and the degree of similarity is high. You may make it estimate that reliability is so high.

  For example, when the serial number area image has the contents as shown in FIG. 5B, the recognition processing unit 204 divides the serial number area image into nine character area images as shown in FIG. 5B. Character recognition is performed for each character area image. As a result, as shown in FIG. 5C, the recognition processing unit 204 reads nine characters “FZ2B9423N” sequentially from the left as a serial number. Then, the recognition processing unit 204 determines the reliability of each character “FZ2B9423N”. For example, in the example of FIG. 5C, the reliability “9” is assigned to the first character “F” of “FZ2B9423N”.

  Then, the image processing unit 205 performs processing for compressing each character region image (data of each character region image) according to the reliability determined by the recognition processing unit 204. For each character area image, the image processing unit 205 performs compression processing (processing that further reduces the data amount) at a higher compression rate as the reliability is higher.

  Specifically, it is assumed that the image processing unit 205 performs compression processing on the character area image by reducing the resolution. In other words, the image processing unit 205 performs a process of reducing the resolution of the character area image with higher reliability to a lower resolution. In other words, the image processing unit 205 performs processing for maintaining a higher resolution for a character region image with low reliability. For example, the image processing unit 205 may determine that a character area image having a reliability lower than a predetermined reliability (for example, a reliability of 0 to 2) is not compressed (the resolution is not lowered). Good.

  FIG. 5D shows an example in which the image processing unit 205 compresses each character area image (each character area image in FIG. 5B). FIG. 5D shows an image (based on the image data after compression) when the character area image shown in FIG. 5B is compressed based on the determination result of the reliability shown in FIG. Image). In FIG. 5D, a character area image with higher reliability is converted into an image with lower resolution.

  FIG. 6 is an explanatory diagram showing a specific setting example of compression processing performed by the image processing unit 205.

  In the example of this embodiment, the image processing unit 205 compresses each character area image at a compression rate corresponding to the reliability of 0 to 10 based on the setting content shown in FIG.

  In the example of setting contents shown in FIG. 6, the compression rate for reliability 0 to 2 is 100% (not compressed), the compression rate corresponding to reliability 3 to 5 is 25% (1 / (2 × 2)), and reliability. The compression rate corresponding to degrees 6 to 8 is set to 6.25% (1 / (4 × 4)), and the compression rate corresponding to reliability 9 and 10 is set to 4% (1/5 × 5). Yes. In the example of the setting contents shown in FIG. 6, the original resolution of the character area image is set to 200 DPI. Therefore, in the example of the setting content shown in FIG. 6, the resolution for the reliability 0 to 2 is 200 DPI (200 × (1/1) = 200 DPI), and the resolution corresponding to the reliability 3 to 5 is 100 DPI (200 × (1 / 2) = 100 DPI), the resolution corresponding to the reliability 6 to 8 is 50 DPI (200 × (1/4) = 50 DPI), and the resolution corresponding to the reliability 9 and 10 is 40 DPI (200 × (1/5) = 40 DPI). ) Will be set respectively. For example, the image processing unit 205 does not perform the process of reducing the resolution for the character area images having the reliability of 0 to 3. For example, the image processing unit 205 performs compression processing on a character region image having a reliability of 3 to 6 by converting the resolution to an image whose resolution is reduced from 200 DPI to 100 DPI. Note that various methods can be applied to image processing when the image processing unit 205 lowers the resolution of each character area image, and thus detailed description thereof is omitted.

  As described above, in the first embodiment, the image sensor 202 and the AD conversion unit 203 constitute an image acquisition unit that captures a banknote and acquires an image. In the first embodiment, the medium recognition unit 200 constitutes medium identification information recognition means for recognizing a serial number (medium identification information) of a bill (medium). Furthermore, in the first embodiment, the recognition processing unit 204 constitutes character area image acquisition means for acquiring the character area image of each character constituting the serial number from the serial number area image. In the first embodiment, the recognition processing unit 204 constitutes a reliability calculation unit that calculates the reliability of the recognition result for each character of the serial number. Furthermore, in the first embodiment, the image processing unit 205 constitutes an image processing unit that performs compression processing (conversion processing for converting to a corresponding resolution) according to the reliability of each character region image. Furthermore, in the first embodiment, the control unit 10 and the storage unit 20 constitute recording means for recording serial number region image data for each banknote.

(A-2) Operation of the First Embodiment Next, the operation of the ATM 1 of the first embodiment having the above configuration will be described.

  FIG. 7 is a flowchart focusing on the process in which the medium recognition unit 200 recognizes the serial number in ATM1. In FIG. 7, the medium recognizing unit 200 is illustrated as performing at least serial number recognition processing on banknotes, but it is naturally possible to perform recognition processing on items other than serial numbers. It is.

  First, in the banknote processing unit 60, it is detected that a banknote has been inserted (inserted) into the banknote deposit / withdrawal port 61 (S101). The bill inserted (inserted) into the bill deposit / withdrawal port 61 is taken into the bill processing unit 60 and fed out onto the transport path 62. And the banknote conveyed on the conveyance path 62 is detected by the medium detection part 201 of the medium recognition part 200. FIG. When the medium detection unit 201 detects the banknote, the medium recognition unit 200 causes the image sensor 202 to image the banknote. Then, the image data of the image captured by the image sensor 202 is acquired by the AD conversion unit 203 (S102).

  Next, the recognition process part 204 cuts out a serial number area | region from the image data of a banknote, and acquires a serial number area | region image (S103).

  Next, the recognition processing unit 204 divides the serial number region image for each character region and obtains a character region image (S104).

  Next, the recognition processing unit 204 performs character recognition for each character area image (S105). Then, the recognition processing unit 204 reports the result of character recognition to the control unit 10. In addition, when the recognition process part 204 is performing recognition processes other than character recognition with respect to a banknote, the recognition process part 204 will report to the control part 10 also about another recognition result.

  Next, the recognition processing unit 204 calculates the reliability of the character recognition result for each character area image (S106).

  Next, the image processing unit 205 performs a compression process (a process of converting the resolution according to the reliability) according to the reliability for each character area image (S107).

  Next, the recognition processing unit 204 supplies character area image data to the control unit 10 (S108).

  Next, when acquiring the character area image data, the control unit 10 records the character area image data in the storage unit 20 (S109).

  At this time, the control unit 10 records the character area image data of each banknote as a set in the storage unit 20. The format in which the control unit 10 records the character area image data for each banknote is not limited.

  For example, the control unit 10 may store a plurality of character area image data constituting the serial number of one banknote as a single file by connecting them in the order of the serial number.

  In addition, for example, the control unit 10 may store folders separately for each banknote in the character area image data of each banknote. At that time, the control unit 10 records each character area image data in each folder in a format in which it is possible to recognize what number (character number) of the serial number. For example, the control unit 10 records the number of digits of the serial number in a part of the file name of each file (character area image data file) in each folder. It is also possible to make it possible to recognize the number of digits (character number).

  Further, the control unit 10 may record character area image data as different files. At this time, the control unit 10 records the character area image data corresponding to each banknote in a format that can be associated (for example, a format that can be managed by a database, a file name, or the like). For example, the control unit 10 may assign a management number to each banknote, and set a file name including a common management number for files (character area image data files) constituting the same banknote serial number. . At this time, the control unit 10 records the number of digits of the serial number in a part of the file name of each file (character area image data file), and each character area image data file has the digit number of the serial number. You may make it possible to recognize what number (characters).

(A-3) Effects of First Embodiment According to the first embodiment, the following effects can be achieved.

  ATM1 (medium recognition unit 200) performs processing (compression processing) for converting each character region image constituting the serial number region image into a resolution corresponding to the reliability of the character recognition result. Thereby, in ATM1 (medium recognition unit 200), a character having a high character recognition reliability is set to a low resolution (data compression degree is increased), and a character having a low character recognition reliability is set to a high resolution (data compression degree is reduced). ) Is set. Thereby, in ATM1 (medium recognition unit 200), it is possible to reduce the data capacity (storage capacity that needs to be secured in the storage unit 20 in this embodiment) when recording the serial number region image (character region image). it can.

  Further, in ATM1 (medium recognition unit 200), the amount of data can be reduced by reducing the resolution of characters having high character recognition reliability. Further, in ATM1 (medium recognition unit 200), the resolution of characters with low character recognition reliability is set to be large (the data compression rate is small), so that the data that maintains the clearest image quality as much as possible for unclear character region images. Can be recorded. Therefore, ATM1 (medium recognition unit 200) can suppress deterioration in the image quality of the recorded image while reducing the data capacity when recording the serial number region image (character region image).

  For example, when there is a serial number that cannot be accurately read by the serial number recognition by the medium recognition unit 200 (low reliability), an operator records the recorded image (serial number area image after compression processing) later (for example, In addition, there may be an operation in which the serial number is input / corrected manually by confirming with an image displayed using image display software or the like. Even if all the serial number area images are recorded regardless of the reliability, if the data compression degree is uniformly increased and recorded, the serial number image that could not be accurately recognized by the apparatus (mainly, the serial number part is stained or blurred) However, the data compression degree is increased and stored. In this case, it becomes difficult for the operator to visually check and determine the character, and this affects the operation of inputting and correcting the number of the serial number area image with low reliability (for example, correction to an accurate number cannot be performed). ). However, in the ATM 1 of this embodiment, with respect to the serial number area image that can be recognized with high reliability, the compression rate is increased by placing importance on the reduction of the data capacity, and conversely, the serial number that can be recognized only with low reliability. The region image is designed to have a low compression rate in consideration of the operator's workability rather than the data capacity reduction. Thereby, in ATM1 of this embodiment, the required data capacity can be reduced without impairing convenience.

(B) Second Embodiment Hereinafter, a second embodiment of the medium recognition device and the transaction device according to the present invention will be described in detail with reference to the drawings. In the second embodiment, an example in which a transaction apparatus equipped with the medium recognition apparatus of the present invention is applied to ATM will be described. In the second embodiment, an example in which the medium recognition apparatus of the present invention is applied to a medium recognition unit will be described.

(B-1) Configuration of the Second Embodiment FIG. 8 is a block diagram showing the overall configuration of the ATM 1A of this embodiment. The same parts and corresponding parts as those in the first embodiment (the above-mentioned FIG. 1) are shown in FIG. , The same code or corresponding code is attached.

  Hereinafter, differences of the second embodiment from the first embodiment will be described.

  The ATM 1A of the second embodiment is different from the first embodiment in that the medium recognition unit 200 is replaced with a medium recognition unit 200A. The medium recognition unit 200A is different from the first embodiment in that the image processing unit 205 is replaced with the image processing unit 205A.

  In the image processing unit 205 of the first embodiment, character area image data is compressed at a resolution set in advance for each reliability. In contrast, the image processing unit 205A according to the second embodiment stores and manages information (resolution setting information 300 in FIG. 8) of resolution corresponding to each reliability (resolution corresponding to compression). Yes.

  FIG. 9 is an explanatory diagram showing a configuration example of the resolution setting information 300.

  In the resolution setting information 300, as shown in FIG. 9, resolutions corresponding to the respective reliability levels 0 to 10 are set.

  It is assumed that the image processing unit 205A can accept a change in the content of the resolution setting information 300 in accordance with an operation of a user (for example, a maintenance person or a staff member of a financial institution store), an external control, or the like. In the ATM 1A (medium recognition unit 200A), the method of accepting the content change of the resolution setting information 300 is not limited. For example, the menu operation using the operation display unit 40 (for example, dedicated for maintenance personnel, staff, etc.) (Menu) or a change in the content of the resolution setting information 300 may be accepted according to control from an external device such as the host 2.

  As described above, in the second embodiment, a resolution information holding unit that holds the resolution setting information 300 is configured by the image processing unit 205A. In the second embodiment, the image processing unit 205A, the control unit 10, the operation display unit 40, and the like constitute a resolution information input unit that receives input of the resolution setting information 300.

(B-2) Operation of the Second Embodiment Next, the operation of the ATM 1A of the second embodiment having the above configuration will be described.

  FIG. 10 is a flowchart focusing on the process in which the medium recognition unit 200A recognizes the serial number in ATM 1A.

  Below, operation | movement of ATM1A of 2nd Embodiment is demonstrated centering on the difference with 1st Embodiment.

  In the ATM 1A (medium recognition unit 200A) of the second embodiment, it is possible to accept input (content change) of the resolution setting information 300 at an arbitrary timing. The flowchart of FIG. 10 describes an example in which the input of resolution setting information 300 is accepted in the first step S200. Therefore, here, the image processing unit 205A of the medium recognition unit 200A performs the compression process according to the resolution setting information 300 input in step S200 described above.

  Thereafter, the ATM 1A (medium recognizing unit 200A) of the second embodiment recognizes the serial number of the inserted banknote by the processing of steps S201 to S209, and the image data (data of the serial number area image after compression). Generate. Since the processing of steps S201 to S209 is substantially the same as the processing of the first embodiment (processing of steps S101 to S109), detailed description thereof is omitted. In the second embodiment, the first point is that in step S207, the image processing unit 205A performs a process of compressing the character area image data with the content according to the resolution setting information 300 (information input in step S200 described above). This is different from the embodiment.

(B-3) Effects of Second Embodiment According to the second embodiment, the following effects can be obtained in addition to the effects of the first embodiment.

  In the ATM 1A (medium recognition unit 200A) of the second embodiment, the resolution setting information 300 can be changed to any content according to the user's operation. As a result, in the ATM 1A (medium recognition unit 200A) of the second embodiment, a character having a high character recognition reliability may have a reduced resolution or a character having a low reliability may have a higher resolution as necessary. it can. That is, in the ATM 1A (medium recognition unit 200A) of the second embodiment, the compression processing of the image processing unit 205A is flexibly adjusted according to the usage status of the ATM 1A (for example, the image quality of stored image data is improved or stored. The amount of image data can be reduced).

(C) Third Embodiment Hereinafter, a third embodiment of the medium recognition device and the transaction device according to the present invention will be described in detail with reference to the drawings. In the third embodiment, an example in which a transaction apparatus equipped with the medium recognition apparatus of the present invention is applied to ATM will be described. In the third embodiment, an example in which the medium recognition device of the present invention is applied to a medium recognition unit will be described.

(C-1) Configuration of the Third Embodiment FIG. 11 is a block diagram showing the overall configuration of the ATM 1B of this embodiment. The same parts and corresponding parts as those of the first embodiment (FIG. 1 described above) , The same code or corresponding code is attached.

  Hereinafter, differences of the third embodiment from the first embodiment will be described.

  The ATM 1B of the third embodiment is different from the first embodiment in that the medium recognition unit 200 is replaced with the medium recognition unit 200B. The medium recognition unit 200B is different from the first embodiment in that the image processing unit 205 is replaced with the image processing unit 205B.

  In the image processing unit 205 of the first embodiment, the character area image data is always compressed. On the other hand, the image processing unit 205B of the third embodiment determines whether or not to compress the character area image data according to the usage status (for example, remaining capacity) of the storage unit 20. This is different from the first embodiment.

  In the example of this embodiment, the image processing unit 205B only stores the character area image data when the remaining storage capacity of the storage unit 20 is less than the threshold (for example, when the remaining storage capacity is less than 30% of the total). It is assumed that compression processing is performed. That is, the image processing unit 205B does not perform the compression process of the character area image data while the remaining storage capacity of the storage unit 20 is equal to or greater than the threshold value.

  Assume that the image processing unit 205B stores an image compression threshold value 400 as a threshold value for determining whether or not to perform compression processing on character area image data. It should be noted that the image processing unit 205B can accept changes in the content of the image compression threshold 400 in accordance with user operations (for example, maintenance personnel, financial institution store staff, etc.) or external control. To do. In ATM1B (medium recognition unit 200B), the method of accepting the content change of the image compression threshold 400 is not limited. For example, menu operations using the operation display unit 40 (for example, dedicated to maintenance personnel, staffs, etc.) Menu), a change in the content of the image compression threshold 400 may be accepted in accordance with a control instruction from the host 2 or the like.

  As described above, in the third embodiment, the image processing unit 205B, the control unit 10, the operation display unit 40, and the like constitute a threshold value input unit that receives an input of the image compression threshold value 400.

(C-2) Operation of the Third Embodiment Next, the operation of the ATM 1B of the third embodiment having the above configuration will be described.

  FIG. 12 is a flowchart focusing on the process in which the medium recognition unit 200B recognizes the serial number in ATM 1B.

  Below, operation | movement of ATM1B of 3rd Embodiment is demonstrated centering on the difference with 1st Embodiment.

  In the ATM 1B (medium recognition unit 200B) of the third embodiment, an input (content change) of the image compression threshold 400 can be accepted. The flowchart of FIG. 12 describes an example in which the input of the image compression threshold 400 is accepted in the first step S300. Accordingly, here, the image processing unit 205B of the medium recognition unit 200B determines whether or not to perform compression processing according to the image compression threshold 400 input in step S300 described above.

  Thereafter, the ATM 1B (medium recognition unit 200B) of the third embodiment obtains the serial number area image of the inserted banknote by the processing of steps S301 to S306, and divides it into character areas for character recognition. A process of calculating the reliability for each character area image is performed. In the third embodiment, the processing in steps S301 to S306 is the same as the processing in the first embodiment (the above-described steps S101 to S106), and thus detailed description thereof is omitted.

  Next, the image compression threshold 400 of the medium recognition unit 200B measures and confirms the remaining storage capacity of the storage unit 20 (S307).

  Next, the image compression threshold 400 compares the remaining storage capacity of the storage unit 20 with the image compression threshold 400 (the information input in step S300 described above) (S308).

  Then, the image compression threshold 400 performs the compression processing of the character area image data only when the remaining storage capacity of the storage unit 20 is smaller than the image compression threshold 400 (S309). That is, the image compression threshold value 400 is not subjected to compression processing of character area image data while the remaining storage capacity of the storage unit 20 is equal to or larger than the image compression threshold value 400.

  Next, the recognition processing unit 204B supplies character area image data to the control unit 10 (S310).

  Next, when acquiring the character area image data, the control unit 10 records the character area image data in the storage unit 20 (S311).

(C-3) Effects of the Third Embodiment According to the third embodiment, the following effects can be obtained in addition to the effects of the first embodiment.

  In the ATM 1B (medium recognition unit 200B) of the third embodiment, it is determined whether or not to perform the compression process according to the storage capacity of the storage unit 20 (remaining storage capacity). Thereby, in ATM1B (medium recognition part 200B) of 3rd Embodiment, according to the memory capacity of the memory | storage part 20, it is possible to perform a compression process (process to reduce the resolution). That is, the ATM 1B (medium recognition unit 200B) of the third embodiment stores high resolution (high image quality) image data (data of the serial number area image) when the storage unit 20 has a sufficient storage capacity. If the storage capacity of the storage unit 20 is not sufficient, image data whose image quality has been reduced by compression processing is stored. Thereby, in ATM1B (medium recognition part 200B) of 3rd Embodiment, when the storage capacity of the memory | storage part 20 has room, a high quality character area image is acquired, and the memory capacity of the memory | storage part 20 has room. If not, the storage capacity of the necessary character area image of the serial number area image can be reduced.

(D) Other Embodiments The present invention is not limited to the above-described embodiments, and may include modified embodiments as exemplified below.

  (D-1) In each of the above embodiments, the medium recognition device and the transaction device according to the present invention are shown as examples applied to ATM. However, transaction devices that handle other media such as banknotes (for example, currency exchange machines, vending machines) For example). Moreover, although each said embodiment demonstrated the example which mounts the medium recognition apparatus (medium recognition part) of this invention in ATM, the medium recognition apparatus (medium recognition part) of this invention processes another banknote. You may make it mount in banknote processing apparatuses (for example, cash sorter, banknote discriminator, etc.).

  In addition, the medium recognition device and the transaction device of the present invention are not limited to banknotes, but processing of other media (for example, gift certificates, tickets, checks, etc.) printed with identification information (recognition and image of medium identification information of the medium) This can be applied to processing including data recording.

  (D-2) In each of the above embodiments, the medium recognizing unit has been described as being mounted on an ATM. However, the medium recognizing unit is a single device (for example, for each banknote by recognizing a serial number of a banknote). It may be configured as a device for storing character area image data.

  Further, in each of the above embodiments, the control unit 10 and the storage unit 20 realize the function of recording image data (character area image data) for each bill. However, the medium recognition unit 200 has a nonvolatile memory (for example, A hard disk display, flash memory, etc.) may be mounted and recorded. In each of the above-described embodiments, functions such as the recognition processing unit 204 and the image processing unit 205 (for example, functions that can be realized by software such as image processing and data processing) are executed on the control unit 10 side. Good. As described above, the constituent elements to be executed for image processing and the like in which the serial number of the banknote is captured in the ATM 1 are not limited.

  (D-3) In the ATM 1B (medium recognition unit 200B) of the third embodiment, the input of the resolution setting information 300 is accepted in the same manner as in the second embodiment, and the compression process according to the input resolution setting information 300 May be performed.

  DESCRIPTION OF SYMBOLS 1 ... ATM, 10 ... Control part, 20 ... Memory | storage part, 30 ... Host I / F, 40 ... Operation display part, 50 ... Card processing part, 51 ... Card insertion discharge port, 60 ... Banknote processing part, 61 ... Banknote insertion / extraction Cash inlet, 62 ... transport path, 63 ... temporary storage part, 64 ... banknote storage part, 70 ... coin processing part, 71 ... coin deposit / withdrawal port, 200 ... medium recognition part, 201 ... medium detection part, 202 ... image sensor, 202a ... light source, 202b ... light receiving sensor, 203 ... AD conversion unit, 204 ... recognition processing unit, 205 ... image processing unit, 2 ... host.

Claims (8)

Image acquisition means for acquiring an image by imaging a medium;
Medium identification information recognition means for recognizing medium identification information of the medium from the image acquired by the image acquisition means;
About the medium identification information recognized by the medium identification information recognition means, reliability calculation means for calculating the reliability of the recognition result;
Character area image acquisition means for acquiring a character area image of characters constituting the medium identification information from the image image;
An image processing unit that performs a conversion process for converting a character region image into an image having a resolution based on the reliability calculated by the reliability calculation unit;
A medium recognition device comprising: The reliability calculation means calculates the reliability of the recognition result for each character of the medium identification information recognized by the medium identification information recognition means,
The character area image acquisition means acquires a character area image of each character constituting the medium identification information from the image image,
The medium recognition device according to claim 1, wherein the image processing unit converts the character region image of each character into an image having a resolution based on the reliability calculated by the reliability calculation unit.   2. The medium recognition apparatus according to claim 1, further comprising recording means for recording a character area image processed by the image processing means. It further comprises resolution information holding means for holding resolution information corresponding to each reliability,
The medium recognition apparatus according to claim 2, wherein the image processing unit performs conversion processing of each character area image according to information held by the resolution information holding unit.   5. The medium recognition apparatus according to claim 4, further comprising resolution information input means for receiving input of information held by the resolution information holding means.   4. The medium recognition apparatus according to claim 3, wherein the image processing unit performs the conversion process only when the remaining storage capacity of the recording unit is smaller than a threshold value.   The medium recognition apparatus according to claim 6, further comprising a threshold value input unit that receives an input of the threshold value used in the image processing unit.   A transaction apparatus for performing a transaction using a medium, comprising a medium recognition apparatus for recognizing a medium to be handled, wherein the medium recognition apparatus according to any one of claims 1 to 7 is applied as the medium recognition apparatus. apparatus.

Images