JP7227818B2 - Banknote identification device, banknote handling device, and banknote identification method - Google Patents

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a banknote validating device, a banknote handling device, and a banknote validating method. More specifically, the present invention relates to a banknote identification device and a banknote identification method suitable for determining the authenticity of conveyed banknotes, and a banknote processing apparatus including such a banknote identification device.

Currently, in a banknote processing apparatus equipped with a banknote identification device, recognition of the denomination of banknotes, authenticity determination, fitness determination, serial number recognition, and the like are performed in the process of conveying banknotes. For example, by analyzing the image of a banknote read by an optical line sensor, identification of the denomination of the banknote, determination of authenticity of the banknote, determination of fitness of the banknote, character recognition of the serial number written on the banknote, and the like are performed. ing.

For example, in Patent Document 1, a light receiving sensor receives reflected light or transmitted light of light irradiated to paper sheets such as bills, and the presence or absence of stains on the paper sheets is determined based on the output signal of the light receiving sensor. A leaf fouling discriminator is disclosed. This apparatus arbitrarily sets a detection area on a scanning line for detecting stains on paper sheets, binarizes the output signal of the light receiving sensor in the detection area, and adds the binarized signal at each reference timing. The output signal of the light-receiving sensor in the detection area is added at each reference timing, and based on the result of these two addition calculations, the case of no stain, the case of partial stain, and the case of overall stain are determined. is discriminating.

Further, in Patent Document 2, an output pattern of an electric signal output from a light receiving unit that receives reflected light reflected by a banknote or transmitted light transmitted through the banknote is compared with a pre-stored standard output pattern to identify a banknote. Several banknote identification methods have been disclosed. For example, there is disclosed a method of excluding areas where the electrical signal output from the light receiving unit is greater than a predetermined value from comparison objects for identifying banknotes. Also disclosed is a method of correcting the standard output pattern according to the output of the electrical signal from the light receiving section.

Japanese Patent Publication No. 6-90750 Japanese Patent Application Laid-Open No. 2006-202075

In order to prevent counterfeiting, non-infrared absorbing inks are sometimes used in the printing of banknotes. Since the areas printed with non-infrared absorbing ink absorb visible light and do not absorb infrared light, the pattern printed with this ink is visible under a visible light source, but under an infrared light source The bill cannot be imaged even by the optical line sensor, and the bill is imaged in a state where the design has disappeared. In addition, at locations printed with non-infrared absorbing ink, the output of the optical line sensor based on the light reflected by the banknote irradiated with infrared light (hereinafter also referred to as reflected infrared output) is relatively large, When the bill is irradiated with infrared light, the output of the optical line sensor based on the light transmitted through the bill (hereinafter also referred to as transmitted infrared output) becomes relatively small. On the other hand, in a counterfeit portion printed with infrared absorbing ink instead of non-infrared absorbing ink, the infrared light is absorbed, so that the reflected infrared output and the transmitted infrared output are small.

Therefore, it can be determined that a portion having a low reflected infrared output with respect to a reference template prepared in advance by learning from a genuine note is suspected of being forged. Specific examples of such determination methods include the following methods. That is, first, a reflected infrared output (infrared reflected image) is collected in the entire printing area of the banknote to be judged. Subsequently, the sampled reflected infrared output is compared with the reference template, and the pixels outside the threshold tolerance are defined as counterfeit pixels, and their number is counted. Authenticity determination is then performed by comparing the total number of forged pixels with a separately set threshold value.

However, in the above determination method, only the reflected infrared output is used, and the authenticity determination is performed based only on the number of pixels that are outside the permissible threshold value. Media with oil stains that affect

Also, if the banknote is dirty, the infrared light will be absorbed at that location, resulting in a small reflected infrared output. However, in the above determination method, only the reflected infrared output is used, and the true/false determination is performed based only on the number of pixels that are out of the allowable threshold value. When the sum of is large, it may be erroneously determined as a counterfeit ticket.

On the other hand, the paper sheet damage determination apparatus described in the above-mentioned Patent Document 1 is for determining the presence or absence of stains on paper sheets, and the problem of erroneously determining a dirty medium as a counterfeit ticket and its solution. No means were disclosed.

In addition, in the banknote identification method described in Patent Document 2, since comparison targets for identifying banknotes are restricted based on the output value of an electric signal by reflected light or transmitted light, counterfeit locations are excluded from comparison targets. likely to. Also, if a banknote has multiple partial stains, it may be erroneously determined to be a counterfeit note.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a banknote validating device, a banknote handling device, and a banknote validating method capable of reducing erroneous determination of a damaged banknote as a counterfeit banknote. be.

In order to solve the above-described problems and achieve the object, the present invention provides a banknote validator for discriminating banknotes, comprising an image acquiring unit for acquiring an infrared reflection image and an infrared transmission image of a banknote, and an authentic a storage unit for storing infrared reflection image reference data and infrared transmission image reference data based on banknotes; comparing the infrared image with first reference data, which is one of the reference data for the infrared reflection image and the reference data for the infrared transmission image, corresponding to the first infrared image; a primary determination unit that determines whether or not an abnormal area outside the allowable range for the first reference data exists in the image; and if the abnormal area exists in the first infrared image, the A determination target area corresponding to the abnormal area of a second infrared image that is the other of the infrared reflection image and the infrared transmission image obtained by the image obtaining unit, and a determination target area corresponding to the second infrared image. is compared with second reference data which is the other of the infrared reflection image reference data and the infrared transmission image reference data, and the determination target region is within an allowable range with respect to the second reference data and a secondary determination unit that determines whether or not the first infrared image is A main determination unit that performs authenticity determination processing on an area excluding at least the abnormal area;
characterized by comprising

Further, according to the present invention, in the above invention, the storage unit further stores a reference value for the size of the abnormal region, and the main determination unit determines whether the abnormal region exists in the first infrared image, and when the secondary determination unit determines that the determination target region is not within the allowable range with respect to the second reference data, the size of the abnormal region and the reference value stored in the storage unit If the size of the abnormal area is smaller than the reference value, the area of the first infrared image excluding at least the abnormal area is subjected to authenticity determination processing.

Further, according to the present invention, in the above invention, the first infrared image is the reflected infrared image, and the primary determination unit compares the reflected infrared image with the infrared reflected image reference data. , wherein the second infrared image is the infrared transmission image, and the secondary determination unit compares a determination target area of the infrared transmission image with the infrared transmission image reference data. do.

Further, according to the present invention, in the above invention, the infrared reflection image reference data includes a reference value of a pixel value of each pixel of the infrared reflection image, and the infrared transmission image reference data includes the infrared reflection image. Including a reference value of a pixel value of each pixel of the transmission image, the primary determination unit is composed of pixels having a pixel value smaller than a corresponding reference value included in the infrared reflection image reference data in the infrared reflection image. is determined to be the abnormal area, and the secondary determination unit determines when the pixel value of each pixel in the determination target area is larger than the corresponding reference value included in the infrared transmission image reference data It is characterized in that the target area is determined to be within the allowable range with respect to the reference data for the infrared transmission image.

Further, according to the present invention, in the above invention, the first infrared image is the infrared transmission image, and the primary determination unit compares the infrared transmission image with the infrared transmission image reference data. , wherein the second infrared image is the infrared reflected image, and the secondary determination unit compares a determination target area of the infrared reflected image with the infrared reflected image reference data. do.

According to another aspect of the present invention, there is provided a banknote processing apparatus including the banknote identification device.

The present invention also provides a banknote identification method for identifying banknotes, comprising: an image acquisition step of acquiring an infrared reflection image and an infrared transmission image of a banknote; The first infrared image, which is one of the infrared transmission images, is the one of the infrared reflection image reference data and the infrared transmission image reference data based on a genuine bill corresponding to the first infrared image. a primary determination step of determining whether or not there is an abnormal region outside the allowable range for the first reference data in the first infrared image by comparing with the first reference data; When the abnormal region exists in the infrared image, a region corresponding to the abnormal region in a second infrared image that is the other of the infrared reflection image and the infrared transmission image acquired in the image acquisition step. The determination target region is compared with the second reference data corresponding to the second infrared image, out of the reference data for the infrared reflection image and the reference data for the infrared transmission image, and the determination a secondary determination step of determining whether or not the target region is within the allowable range with respect to the second reference data; and the secondary determination step determines whether the determination target region is within the allowable range with respect to the second reference data. and a main determination step of performing authenticity determination processing on a region excluding at least the abnormal region of the first infrared image when it is determined that the first infrared image is the abnormal region.

According to the banknote validating device, banknote handling device, and banknote validating method of the present invention, it is possible to reduce erroneous determinations of damaged banknotes as counterfeit banknotes.

BRIEF DESCRIPTION OF THE DRAWINGS It is a figure for demonstrating the outline|summary of the banknote recognition apparatus and banknote recognition method which concern on Embodiment 1. FIG. 1 is a schematic perspective view showing an appearance of a banknote processing apparatus according to Embodiment 1; FIG. 1 is a block diagram illustrating the configuration of a banknote identification device according to Embodiment 1; FIG. FIG. 2 is a schematic cross-sectional view for explaining the configuration of an image acquisition unit included in the banknote identification device according to Embodiment 1; FIG. 4 is a schematic diagram showing an example of an infrared reflection image acquired by an image acquisition unit included in the banknote validator according to the first embodiment; 4 is a schematic diagram showing an example of an infrared transmission image acquired by an image acquisition unit included in the banknote identification device according to the first embodiment; FIG. FIG. 7 is a diagram for explaining an example of a method of calculating the size of an abnormal region in an infrared reflection image by a secondary determination unit included in the banknote identification device according to Embodiment 1; 5 is a flow chart showing a processing procedure of banknote recognition processing in the banknote recognition device and the banknote recognition method according to the first embodiment;

BEST MODE FOR CARRYING OUT THE INVENTION Preferred embodiments of a banknote recognition device, a banknote processing device, and a banknote recognition method according to the present invention will be described below with reference to the drawings.

In this specification, the reflected image means an image based on the intensity distribution of the light reflected by the banknote irradiated with light. Also called an infrared reflection image. In addition, the transmission image means an image based on the intensity distribution of the light transmitted through the banknote by irradiating light on the banknote. To tell.

<Overview of Banknote Validation Device and Banknote Validation Method>
First, with reference to FIG. 1, an outline of a banknote recognition device and a banknote recognition method according to the present embodiment will be described. The main features of this embodiment are as shown in I and II below.

I. By confirming both the reflected infrared output and the transmitted infrared output (reflected infrared image and transmitted infrared image), we can separate oil stains and counterfeit areas (see the center and right side of each image in FIG. 1).

II. Depending on the situation around pixels outside the threshold tolerance, we separate the local smudges from the counterfeit locations (see the middle and left sides of each image in FIG. 1).

According to these features, it is possible to reduce erroneous determination of a damaged bill as a counterfeit bill. Each feature will be described in more detail below.

(I) When the banknote is soaked with oil, the unevenness of the fiber of the banknote decreases, and the amount of transmitted light increases, that is, the amount of reflected light decreases. Therefore, at a dirty location due to oil stain, the reflected infrared output is relatively small and the transmitted infrared output is relatively large. As described above, a location with a low reflected infrared output relative to the reference template is suspected of being forged, so there is a possibility that a soiled location due to oil stains may be erroneously determined to be a forged location only from the reflected infrared output. However, in the present embodiment, the transmission infrared output of that location is also checked, and if the transmission infrared output of that location is large, it is determined that the location is not a counterfeit location but a dirty location due to oil stains. As a result, it is possible to exclude, from the counterfeit pixels, the locations determined to be soiled by oil stains, thereby reducing erroneous determination of a soiled ticket as a counterfeit ticket.

(II) Empirically, the characteristics of forgery often appear in a group of places. For this reason, if there are suspected counterfeiting points around the suspected counterfeiting point (=reflected infrared output and/or transmitted infrared output are not acceptable), judged to be dirty. As a result, it is possible to reduce erroneous determination that local stains are forgery locations.

<Configuration of banknote processing device>
The configuration of the banknote processing apparatus according to this embodiment will be described with reference to FIG. The banknote processing apparatus according to the present embodiment may have the configuration shown in FIG. 2, for example. The banknote processing apparatus 300 shown in FIG. 2 is a small-sized banknote processing apparatus that is installed on a table and used. A hopper 301 in which banknotes are placed in a stack, and a reject banknote, such as a counterfeit banknote or a banknote whose authenticity is uncertain, discharged from the hopper 301 into a housing 310. an operation unit 303 for inputting instructions from the operator; Stacking units 306a to 306d and a display unit 305 for displaying information such as bill identification counting results and the stacking status of each stacking unit 306a to 306d. Based on the result of fitness determination by the bill identification device, among the four stacking units 306a to 306d, the stacking units 306a to 306c store fit bills, and the stacking unit 306d stores damaged bills. Note that the method of distributing banknotes to the stacking units 306a to 306d can be set arbitrarily.

<Configuration of banknote identification device>
The configuration of the bill identification device according to this embodiment will be described with reference to FIG. As shown in FIG. 3 , the banknote identification device 1 according to this embodiment includes a control section 10 , a detection section 20 and a storage section 30 .

The control unit 10 includes a program for realizing various processes stored in the storage unit 30, a CPU (Central Processing Unit) that executes the program, various hardware controlled by the CPU, and an FPGA (Field Logic devices such as Programmable Gate Array). The controller 10 controls each part of the banknote validator 1 based on signals output from each part of the banknote validator 1 and control signals from the controller 10 according to a program stored in the storage unit 30 . The control unit 10 also has functions of an identification unit 11 , an authenticity determination unit 12 , and a fitness determination unit 13 by a program stored in the storage unit 30 .

The detection unit 20 includes an image acquisition unit 21 , a magnetic detection unit 22 and a UV detection unit 23 . The image acquisition unit 21 acquires an image of a banknote. The magnetic detection unit 22 includes a magnetic sensor (not shown) that measures magnetism, and the magnetic sensor detects the magnetism of magnetic ink printed on banknotes, security threads, and the like. A magnetic sensor is a magnetic line sensor in which a plurality of magnetic detection elements are arranged in a line. The UV detection unit 23 includes an ultraviolet irradiation unit (not shown) and a light receiving unit (not shown). Detected by

The storage unit 30 is composed of a non-volatile storage device such as a semiconductor memory or a hard disk, and stores various programs and data for controlling the banknote identification device 1 . The storage unit 30 also stores reference data for an infrared reflection image, reference data for an infrared transmission image, and a reference value for the size of an abnormal region (hereinafter also referred to as a size reference value).

The infrared reflection image reference data and the infrared transmission image reference data are reference templates used as judgment criteria in the authenticity judging process by the authenticity judging unit 12. It is a parameter group prepared in advance for each denomination of a banknote to be identified by machine learning based on the pixel value (output value) of each pixel of the external reflection image and the infrared transmission image. Therefore, the infrared reflection image reference data and the infrared transmission image reference data indicate the reference values of the pixel values of the respective pixels of the infrared reflection image and the infrared transmission image of the bill to be authenticated. be.

The size reference value is a threshold used as a criterion for determining the size of the abnormal region in the authenticity processing by the authenticity determination unit 12 .

The recognition unit 11 compares the feature pattern of the banknote image acquired by the image acquisition unit 21 with a denomination identification template, which is a feature pattern for each denomination of the banknote, to determine the denomination of the banknote.

The authenticity determination unit 12 determines the authenticity of the banknote based on the image of the banknote obtained by irradiating the infrared light, the details of which will be described later. Further, the authenticity determination unit 12 compares the detection signals of the magnetic detection unit 22 and the UV detection unit 23 with the reference data for authenticity identification to determine the authenticity of the banknote. In this way, the authenticity determination unit 12 performs a plurality of types of authenticity determination processing on banknotes, determines that the banknote is genuine when all the determination results are true, and determines one of the determination results to be false. When , it is determined that the bill is a counterfeit bill.

<Configuration of Image Acquisition Unit>
The configuration of the image acquisition unit 21 will be described with reference to FIG. As shown in FIG. 4, the image acquisition section 21 includes optical line sensors 110 and 120 arranged to face each other. Between the optical line sensors 110 and 120 is formed a gap through which the banknotes BN are conveyed, and this gap constitutes a part of the conveyance path 311 of the banknote processing apparatus. The optical line sensors 110 and 120 are positioned above and below the transport path 311, respectively.

The optical line sensor 110 includes a reflection light source 111 , a condenser lens 112 and a light receiving section 113 . The light source 111 for reflection irradiates the upper surface of the banknote BN with light of a predetermined wavelength (invisible light such as infrared light and visible light such as monochromatic light such as red, green, and blue and white light). The condenser lens 112 collects the light emitted from the reflection light source 211 and reflected by the bill BN. The light-receiving unit 113 includes a plurality of light-receiving elements (not shown) arranged in a line in a direction (main-scanning direction) orthogonal to the paper money BN conveying direction (sub-scanning direction). It converts the focused light into an electrical signal. The optical line sensor 110 converts the electric signal converted by the light receiving unit 113 into a digital signal and outputs the digital signal.

The optical line sensor 120 includes a reflection light source 121 , a condenser lens 122 , a light receiving section 123 and a transmission light source 124 . The reflective light source 121 and the transmissive light source 124 each emit light of a predetermined wavelength (invisible light such as infrared light, monochromatic light such as red, green, blue, etc., and visible light such as white light) on the lower surface of the banknote BN. ). The condenser lens 122 collects the light emitted from the reflection light source 121 and reflected by the bill BN. The light-receiving unit 123 includes a plurality of light-receiving elements (not shown) arranged in a line in a direction orthogonal to the direction in which the banknotes BN are conveyed, and converts the light condensed by the condensing lens 122 into electrical signals. do. The optical line sensor 120 converts the electrical signal converted by the light receiving unit 123 into a digital signal and outputs the digital signal.

The transmission light source 124 is arranged on the optical axis of the condenser lens 112 of the optical line sensor 110 , and part of the light emitted from the transmission light source 124 passes through the bill BN, The light is condensed by the condensing lens 112 and detected by the light receiving section 113 .

Each of the optical line sensors 110 and 120 repeatedly captures an image (exposure of the light receiving element) of the banknote BN being conveyed in the conveying direction at regular time intervals, and outputs a signal. An image of the entire bill BN is acquired (image acquisition step). Specifically, the image acquiring unit 21 acquires a reflected image of the upper surface of the banknote BN and a transmitted image of the banknote BN based on the output signal of the optical line sensor 110, and acquires a banknote image based on the output signal of the optical line sensor 120. Acquire a reflection image of the bottom surface of the BN. Further, the image acquiring unit 21 acquires an infrared reflected image of the upper surface of the banknote BN and an infrared reflected image of the lower surface of the banknote BN as the reflected image of the banknote BN. Furthermore, the image acquisition unit 21 acquires an infrared transmission image of the banknote BN as the transmission image of the banknote BN.

<Structure of Authenticity Determination Unit>
The configuration (function) of the authenticity determination unit 12 will be described with reference to FIGS. As shown in FIG. 3, the authenticity determination section 12 has a primary determination section 12a, a secondary determination section 12b, and a main determination section 12c.

As shown in FIG. 5, the primary determination unit 12a obtains an infrared reflected image 210 of a banknote (entire printing area) as a first infrared image and infrared reflected image reference data (identification unit 11) as first reference data. Infrared reflection image reference data corresponding to the denomination identified by) is compared with the infrared reflection image 210, and an abnormal area that is an area outside the allowable range for the infrared reflection image reference data 211 exists (primary determination step). As a result, it is possible to detect, as the abnormal region 211, a soiled location due to oil stains, a local soiled location, and/or a counterfeit location.

More specifically, the primary determination unit 12a compares the pixel value of each pixel of the infrared reflected image 210 with the corresponding reference value included in the infrared reflected image reference data, and determines that the pixel value is smaller than the reference value. If there are pixels having , a region composed of those pixels is specified as an abnormal region 211 .

As shown in FIG. 6 , when one or more abnormal regions 211 exist in the infrared reflection image 210, the secondary determination unit 12b determines the infrared transmission of the banknote (entire printing region) as the second infrared image. Each of one or more determination target regions 221 corresponding to one or more abnormal regions 211 in the image 220, and infrared transmission image reference data as second reference data (corresponding to the denomination identified by the identification unit 11 Infrared transmission image reference data) is compared with the infrared transmission image reference data) to perform secondary determination processing to determine whether each determination target region 221 is within an allowable range with respect to the infrared transmission image reference data (secondary determination processing). judgment step). Accordingly, it is possible to determine whether or not the abnormal region 211 and the determination target region 221 are soiled portions due to oil stains.

More specifically, the secondary determination unit 12b corresponds to the one or more abnormal regions 211 in the infrared transmission image 220 (that is, the same location as the one or more first abnormal regions 211). is specified as the determination target region 221 . Then, the secondary determination unit 12b compares the pixel value of each pixel in each determination target region 221 with the corresponding reference value included in the infrared transmission image reference data, and determines that the pixel value of each pixel is higher than the reference value. If it is larger, it is determined that the determination target region 221 is within the allowable range with respect to the reference data for the infrared transmission image. It is judged that it is not within the allowable range with respect to the reference data.

When the secondary determination unit 12b determines that at least one determination target region 221 is within the allowable range with respect to the infrared transmission image reference data, the main determination unit 12c determines that it is within the allowable range. Authenticity determination processing is performed on the infrared reflected image 210 excluding at least one or more abnormal regions 211 corresponding to one or more determination target regions 221 (main determination step). As a result, when the abnormal area 211 is an oil-stained area, authenticity determination can be performed for the area excluding the area, thereby reducing erroneous determination of oil-stained notes as counterfeit notes. can be done.

More specifically, when the secondary determination unit 12b determines that at least one determination target region 221 is within the allowable range with respect to the infrared transmission image reference data, the main determination unit 12c determines whether the infrared reflection image In 210, a region excluding at least one or more abnormal regions 211 corresponding to one or more determination target regions 221 determined to be within the allowable range (that is, at the same locations as the one or more determination target regions 221). It is assumed to be an authenticity determination area to be subjected to the authenticity determination process. Then, the main judging section 12c performs authenticity judgment processing on the authenticity judgment region by a general method. For example, in the examples shown in FIGS. 5 and 6, the abnormal region 211 on the right side of the infrared reflection image 210 corresponds to the reference value corresponding to the pixel value of each pixel in the determination target region 221 on the right side of the corresponding infrared transmission image 220. Excluded from the authenticity area because it is larger.

Further, when the secondary determination unit 12b determines that at least one determination target region 221 is not within the allowable range with respect to the infrared transmission image reference data, the main determination unit 12c performs the following processing. That is, the main determination unit 12c determines the size of each of the one or more abnormal regions 211 corresponding to the one or more determination target regions 221 determined not to be within the allowable range, and the size reference value stored in the storage unit 30. are compared, and if the size is smaller than the size reference value, authenticity determination processing is performed on the infrared reflected image 210 excluding at least the abnormal region 211 (second main determination step). As a result, when the abnormal area 211 is a small-sized, partially soiled area, authenticity determination can be performed for the area excluding that area, so that a defaced ticket due to local soiling is determined to be a forged ticket. erroneous determination can be reduced.

More specifically, when the secondary determination unit 12b determines that at least one determination target region 221 is not within the allowable range with respect to the infrared transmission image reference data, the main determination unit 12c determines that it is not within the allowable range. One or more abnormal regions 211 corresponding to the determined one or more determination target regions 221 (that is, at the same locations as the one or more determination target regions 221) are specified, and the size of each is calculated. Further, the main determination unit 12c compares the calculated size of each abnormal region 211 with the size reference value stored in the storage unit 30. If the size is smaller than the size reference value, the infrared reflection image 210 An area excluding the abnormal area (an abnormal area whose size is less than the size reference value) 211 is set as an authenticity determination area. Then, the main judging section 12c performs authenticity judgment processing on the authenticity judgment region by a general method. For example, in the examples shown in FIGS. 5 and 6, the pixel values of the respective pixels in the central and left determination target regions 221 of the infrared transmission image 220 are equal to or less than the corresponding reference values, but in the infrared reflection image 210 , the sizes of the corresponding left abnormal regions 211 are smaller than the size reference value, so these abnormal regions 211 are excluded from the authenticity determination region. On the other hand, in the infrared reflection image 210, since the size of the corresponding central abnormal area 211 is equal to or larger than the size reference value, this abnormal area 211 is not excluded from the authenticity determination area.

As a method for calculating the size of each abnormal region 211 by the secondary determination unit 12b, for example, after binarizing the infrared reflection image 210, filtering or labeling is performed, and pixels constituting each abnormal region 211 A method of calculating the number of

When using filter processing, for example, first, the infrared reflection image 210 is binarized, and the binarized banknote region is reversed in black and white. As a result, as shown in the upper part of FIG. 7, a portion where the infrared reflection output is low and where there is a suspicion of forgery becomes a white pixel. Next, predetermined filter processing is performed. Then, the pixel value of each pixel is compared with a predetermined threshold value, and pixels exceeding the threshold value are regarded as counterfeit pixels, and the number of such pixels is counted. If the threshold is set to 3, for example, in the left case of FIG. 7, the central four pixels are within the allowable range of the threshold and no forged pixels are detected. On the other hand, in the case on the right side of FIG. 7, the central four pixels are outside the allowable threshold range and are detected as counterfeit pixels.

<Bill identification processing>
Processing by the banknote identification device 1 will be described with reference to FIG. This processing is repeated one by one for the bills carried into the bill identification device 1 .

When the bill is carried into the bill identification device 1 (S11: YES), the identification unit 11 acquires the images of the upper and lower surfaces of the bill acquired by the image acquisition unit 21, the denomination identification template, and , the denomination of the banknote is identified (S12).

Next, as described above, the primary determination unit 12a determines the infrared reflected image (first infrared image) 210 of the bill and the infrared reflected image reference data (first infrared image) corresponding to the denomination identified in step S12. 1 reference data) to perform primary determination processing to determine whether or not there is an abnormal region 211 outside the allowable range for the reference data for the infrared reflected image 210 in the infrared reflected image 210 ( S13).

Next, when one or more abnormal regions 211 are present in the infrared reflection image 210, the secondary determination unit 12b determines one of the infrared transmission images (second infrared images) 220 of the banknote as described above. One or more determination target regions 221 corresponding to the above abnormal regions 211, respectively, and the infrared transmission image reference data (second reference data) corresponding to the denomination identified in step S12 are compared, and each determination A secondary determination process is performed to determine whether or not the target region 221 is within the allowable range with respect to the reference data for infrared transmission image (S14).

When it is determined in step S14 that at least one determination target region 221 is within the allowable range with respect to the infrared transmission image reference data, the main determination unit 12c determines that it is within the allowable range as described above. One or more abnormal regions 211 respectively corresponding to one or more determined determination target regions 221 are excluded from the authenticity determination region of the infrared reflection image 210 (S15).

In step S14, when it is determined that at least one determination target region 221 is not within the allowable range with respect to the infrared transmission image reference data, each of the one or more determination target regions 221 determined not to be within the allowable range. The size of each of the corresponding one or more abnormal regions 211 is compared with the size reference value, and if the size is smaller than the size reference value, the abnormal region 211 is further excluded from the authenticity determination region of the infrared reflection image 210. (S15).

Then, as described above, the main determination unit 12c determines the authenticity of the banknote by performing the authenticity determination process on the authenticity determination area specified in step S15 (S16).

The processing related to authenticity determination in steps S13 to S16 is performed for each of the upper and lower surfaces of the banknote. That is, the above authenticity determination processing based on the infrared reflected image 210 of the upper surface of the banknote and the infrared transmitted image 220 of the banknote, and based on the infrared reflected image 210 of the lower surface of the banknote and the infrared transmitted image 220 of the banknote The authenticity determination processing described above is performed.

Further, the authenticity determination unit 12 compares the detection signals of the magnetic detection unit 22 and the UV detection unit 23 with reference data for authenticity identification to determine the authenticity of the banknote (S17).

If the authenticity determination results in steps S16 and S17 are both true (S18: YES), the authenticity determination unit 12 determines that the banknote is genuine (S19), and determines authenticity in steps S16 and S17. If at least one of the results is false (S18: NO), the authenticity determination unit 12 determines that the banknote is a counterfeit note (S20).

When the banknote is determined to be genuine, the fitness determination unit 13 determines the fitness of the banknote (S21).

Then, the control unit 10 unloads the banknote for which the determination of authenticity and fitness has been completed from the banknote recognition device 1 (S22), and the processing by the banknote recognition device 1 ends.

As described above, in the present embodiment, the primary determination unit 12a detects a suspected forgery as the abnormal region 211 based on the infrared reflected image 210 of the banknote, and the secondary determination unit 12b detects the infrared image. Based on the transmission image 220, it is determined whether or not the determination target region 221 corresponding to the abnormal region 211 is a dirty location due to oil stain. Since the unit 12c performs the authenticity determination process on the authenticity determination area excluding at least the abnormal area 211 in the infrared reflection image 210, it is possible to reduce the erroneous determination that a ticket stained with oil is a counterfeit ticket. .

Further, in the present embodiment, even when the secondary determination unit 12b determines that the determination target region 221 is a forgery location, the main determination unit 12c determines whether the abnormal region 211 corresponding to the determination target region 221 Based on the size, it is determined whether or not the abnormal region 211 is a localized dirt spot. Then, if the abnormal region 211 is a localized stain, the main determination unit 12c also excludes the abnormal region 211 from the authenticity determination region and performs authenticity determination processing. It is possible to reduce erroneous determination of a damaged ticket as a counterfeit ticket.

In the above-described embodiment, when the determination is performed in the order of the reflected infrared image 210 and the transmitted infrared image 220, that is, the first infrared image is the reflected infrared image 210, and the primary determination unit 12a determines the reflected infrared image. 210 and the reference data for the infrared reflected image, the second infrared image is the infrared transmitted image 220, and the secondary determination unit 12b determines the determination target region 221 of the infrared transmitted image 220 and the reference data for the infrared transmitted image. Although the case of comparing with reference data has been described, determination may be performed in order of the infrared transmission image 220 and the infrared reflection image 210 . That is, the first infrared image is the infrared transmission image 220, the primary determination unit 12a compares the infrared transmission image 220 with the infrared transmission image reference data, and the second infrared image is the infrared reflection image 210. and the secondary determination unit 12b may compare the determination target region of the infrared reflected image 210 with the infrared reflected image reference data. In this case, the order of processing is basically the same as when determination is made in the order of the infrared reflection image 210 and the infrared transmission image 220. For example, the processing is carried out in the order of (1) to (3) below. Is possible.
(1) Compare the infrared transmission image 220 with the reference data for the infrared transmission image, and check whether there is an abnormal area in the infrared transmission image 220 that is out of the allowable range for the reference data for the infrared transmission image. A primary determination is made to determine whether or not
(2) When an abnormal area exists in the infrared transmission image 220, the determination target area, which is the area corresponding to the abnormal area of the infrared reflection image 210, is compared with the infrared reflection image reference data, A secondary determination is made to determine whether or not the determination target area is within the allowable range with respect to the infrared reflection image reference data.
(3) If the secondary determination determines that the determination target area is within the allowable range with respect to the infrared reflection image reference data, a true/false determination is made for the area excluding at least the abnormal area of the infrared transmission image 220 . Perform judgment processing.

Although the embodiments of the present invention have been described above with reference to the drawings, the present invention is not limited to the above embodiments. Moreover, the configuration of each embodiment may be appropriately combined or changed without departing from the gist of the present invention.

INDUSTRIAL APPLICABILITY As described above, the present invention is a technique useful for reducing erroneous determination of a damaged bill as a counterfeit bill in a banknote validating device and a banknote validating method.

1: Banknote identification device 10: Control unit 11: Identification unit 12: Authenticity determination unit 12a: Primary determination unit 12b: Secondary determination unit 12c: Main determination unit 13: Damage determination unit 20: Detection unit 21: Image acquisition unit 22: Magnetic detection unit 23: UV detection unit 30: Storage units 110, 120: Optical line sensors 111, 121: Light sources for reflection 112, 122: Collecting lenses 113, 123: Light receiving unit 124: Light source for transmission 210: Infrared Reflection image 211: Abnormal region 220: Infrared transmission image 221: Judgment target region 300: Banknote processing device 301: Hopper 302: Reject unit 303: Operation unit 305: Display units 306a to 306d: Stacking unit 310: Housing 311: Conveyance Road BN: Paper money

Claims (5)

A banknote identification device for identifying banknotes,
an image acquisition unit that acquires an infrared reflection image and an infrared transmission image of the banknote;
a storage unit for storing infrared reflection image reference data and infrared transmission image reference data based on genuine bills;
The infrared reflected image acquired by the image acquisition unit is compared with the infrared reflected image reference data , and the infrared reflected image reference data is stored in the infrared reflected image. A primary determination unit that determines whether there is an abnormal area outside the allowable range;
When the abnormal region exists in the infrared reflection image , a determination target region that is a region corresponding to the abnormal region of the infrared transmission image acquired by the image acquisition unit ; a secondary determination unit that compares the determination target region with the transmission image reference data and determines whether or not the determination target region is within an allowable range with respect to the infrared transmission image reference data ;
When the secondary determination unit determines that the determination target area is within the allowable range with respect to the infrared transmission image reference data , for the area excluding at least the abnormal area of the infrared reflection image a main determination unit that performs authenticity determination processing based on the infrared reflection image ;
A bill identification device comprising: The storage unit further stores a reference value for the size of the abnormal region,
The main determination unit determines that the abnormal region exists in the infrared reflection image and that the determination target region is not within an allowable range with respect to the infrared transmission image reference data by the secondary determination unit. when the size of the abnormal region is compared with the reference value stored in the storage unit, and if the size of the abnormal region is smaller than the reference value, at least the abnormal region of the infrared reflection image is 2. The banknote identification device according to claim 1, wherein authenticity determination processing is performed on the excluded area. The infrared reflection image reference data includes a reference value of a pixel value of each pixel of the infrared reflection image,
The infrared transmission image reference data includes a reference value of a pixel value of each pixel of the infrared transmission image,
The primary determination unit determines, as the abnormal region, an area composed of pixels having a pixel value smaller than a corresponding reference value included in the infrared reflection image reference data in the infrared reflection image,
The secondary determination unit determines the determination target region from the infrared transmission image reference data when a pixel value of each pixel in the determination target region is larger than a corresponding reference value included in the infrared transmission image reference data. 3. The banknote identification device according to claim 1, wherein the banknote validating device determines that the value is within the allowable range for the banknote validating device. A banknote processing apparatus comprising the banknote identification device according to any one of claims 1 to 3 . A bill identification method for identifying bills with a bill identification device ,
an image acquisition step in which the image acquisition unit acquires an infrared reflection image and an infrared transmission image of the banknote;
A primary determination unit compares the infrared reflection image acquired in the image acquisition step with reference data for an infrared reflection image based on a genuine banknote, and the infrared reflection image is included in the infrared reflection image . a primary determination step of determining whether or not there is an abnormal area outside the allowable range for the reflected image reference data ;
A secondary determination unit determines a determination target region that is a region corresponding to the abnormal region of the infrared transmission image acquired in the image acquisition step when the abnormal region exists in the infrared reflection image. is compared with infrared transmission image reference data based on a genuine banknote to determine whether or not the determination target region is within an allowable range with respect to the infrared transmission image reference data. a determination step;
When the secondary determination step determines that the determination target area is within the allowable range with respect to the infrared transmission image reference data , the main determination unit determines at least the abnormal area of the infrared reflection image. A main determination step of performing authenticity determination processing based on the infrared reflection image for the area except
A banknote identification method, comprising:

Images