JP6779817B2 - Paper leaf processing equipment, paper leaf processing method, and paper leaf processing program - Google Patents

Description

Embodiments of the present invention relate to a paper leaf processing apparatus, a paper leaf processing method, and a paper leaf processing program.

There is known a paper leaf processing device that inspects paper leaves such as inserted banknotes and sorts them according to the type of paper leaves. There are different generations (series) of the same denomination with very similar print patterns in the types of paper leaves, but from the viewpoint of improving the performance of authenticity discrimination, the identification of the ticket type and the identification of the generation Need to be treated as separate categories. However, when the characteristics of regions that differ depending on the generation are lost due to dirt, scratches, etc., the generation may not be correctly identified and the performance of ticket type discrimination may be deteriorated.

Japanese Patent No. 5111794

An object to be solved by the present invention is to provide a paper leaf processing apparatus, a paper leaf processing method, and a paper leaf processing program capable of improving the performance of determining the ticket type of paper sheets. ..

The paper leaf processing apparatus of the embodiment includes an imaging unit, a storage unit, a first ticket type identification unit, a stain degree measurement unit, a second ticket type identification unit, and a ticket type determination unit. The imaging unit captures paper sheets. The storage unit stores a first reference pattern for identifying the ticket type of the paper leaf and a second reference pattern for identifying the generation for each ticket type. The first ticket type identification unit is based on the degree of similarity between the image of the paper leaves captured by the imaging unit and the first reference pattern stored in the storage unit, and the ticket type of the paper leaves is To identify. The stain degree measuring unit extracts at least one partial region from the image of the paper leaf based on the ticket type identified by the first ticket type identification unit, and measures the stain degree with respect to the extracted partial region. The second ticket type identification unit identifies the generation of the paper leaf ticket type based on the degree of similarity between the image of the partial region and the second reference pattern stored in the storage unit. The ticket type determination unit determines the ticket type of the paper sheets based on the identification result by the second ticket type identification unit and the stain degree measured by the stain degree measuring unit.

The figure for demonstrating the structure of the paper leaf processing apparatus of 1st Embodiment. The figure for demonstrating that the ticket type of a paper leaf is determined by weighting according to the degree of pollution of the paper leaf P. The figure for demonstrating the setting example of the feature extraction target area. The figure for demonstrating the setting example of a partial area. The flowchart for demonstrating the ticket type detection process of 1st Embodiment. The figure for demonstrating that the ticket type of a paper leaf is determined by the correction according to the degree of contamination of the paper leaf P. The flowchart for demonstrating the ticket type detection process of 2nd Embodiment.

Hereinafter, the paper leaf processing apparatus, the paper leaf processing method, and the paper leaf processing program of the embodiment will be described with reference to the drawings.

(First Embodiment)
FIG. 1 is a diagram for explaining the configuration of the paper leaf processing apparatus of the first embodiment. The paper leaf processing device 100 of the first embodiment identifies, for example, the type of paper leaf, and distributes and seals the regular ticket, the non-loss ticket, and the exclusion ticket to each accumulation portion. A regular ticket is, for example, a normal paper leaf that has been determined to be re-distributed. The non-performing ticket is, for example, paper leaves that are determined to be impossible to be distributed due to stains or the like. The exclusion ticket is, for example, a paper leaf whose type cannot be identified by the paper leaf processing device 100 or a paper leaf determined to be a fake.

The paper leaf processing device 100 includes, for example, a supply unit 110, an extraction unit 120, a transport state detection unit 130, a detection unit 140, a thickness detection unit 150, an accumulation unit 160, and an exclusion ticket accumulation unit 170. A control unit 180 and a storage unit 190 are provided. Some or all of the functions of the transport state detection unit 130, the detection unit 140, the thickness detection unit 150, and the control unit 180 are various programs in which a processor such as a CPU (Central Processing Unit) is stored in the storage unit 190. It is realized by executing. The program may be downloaded from an external server via the network NW, or may be installed in a portable storage medium such as an SD card. Further, some or all of the functions provided by the transport state detection unit 130, the detection unit 140, the thickness detection unit 150, and the control unit 180 are LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA ( It may be realized by hardware such as Field-Programmable Gate Array), or it may be realized by collaboration between software and hardware.

For example, a plurality of sheets of paper are collectively loaded in the supply unit 110. The take-out unit 120 takes out paper sheets one by one from the supply unit 110 and supplies them to the transport path 200.

The transport state detection unit 130 detects the transport state of the paper sheets transported on the transport path 200, such as the transport position, the transport skew, and the transport gap. The transport position is the transport center of the paper sheets when the paper sheets are transported. The transport skew is the inclination of transport of paper sheets with respect to the transport direction of the paper sheets when the paper sheets are transported. The transport gap is the distance between the rear end in the transport direction of the paper sheets transported first on the transport path 200 and the tip in the transport direction of the paper leaves transported next.
For example, the transport state detection unit 130 has high reflection from the paper surface in the portion where the paper sheets are present and low reflectance in the portion where the paper leaves are not present. Therefore, the level difference between the two is binarized at a predetermined threshold value. Identify the location of paper leaves. In addition, the transport state detection unit 130 measures the deviation of the transport position from the center line of the transport path 200 for paper sheets.

The detection unit 140 detects the ticket type information such as the ticket type information of the paper leaf P, the authenticity (genuine or fake), the correct loss (regular ticket or the lost ticket), and the serial number. The detection unit 140 includes, for example, a reading unit 141, a ticket type detection unit 142, a authenticity detection unit 143, a positive / loss determination unit 144, and a serial number detection unit 145. The reading unit 141 is an example of an “imaging unit”.

The reading unit 141 captures an image region including paper sheets P transported on the transport path 200. The reading unit 141 is, for example, an image reading sensor, a CCD (Charge Coupled Device) camera, and a CIS (Contact Image Sensor) camera.

The ticket type detection unit 142 detects, for example, ticket type information such as the type of paper leaves, the front and back sides of the paper leaves to be transported, and the forward / reverse (upright or inverted). The details of the function of the ticket type detection unit 142 will be described later.

The authenticity detection unit 143 determines whether the paper leaves are genuine tickets (genuine paper leaves) or fake tickets (fake paper leaves) based on the ticket type or generation information of the paper leaves by the ticket type detection unit 142. ) Is detected. The authenticity detection unit 143 detects, for example, the physical characteristics and magnetic characteristics of the paper sheets transported by the transport path 200, and detects whether the ticket is a genuine ticket or a fake ticket based on the detection result. To do. The physical characteristics are, for example, fluorescence characteristics and infrared characteristics contained in paper sheets. The magnetic property is, for example, the amount of magnetic material contained in paper sheets.

The positive / loss determination unit 144 determines that the paper leaves that are determined to be genuine tickets by the authenticity detection unit 143 are genuine tickets when it is determined that the paper sheets can be recirculated. To do. The state in which redistribution is possible is, for example, a state in which stains or breakage of paper sheets are less than a preset threshold value. Further, when the positive / loss determination unit 144 determines that the paper leaves determined to be genuine by the authenticity detection unit 143 are in a state in which redistribution is impossible, the positive / loss determination unit 144 uses the paper leaves as a loss ticket. Determine if there is. The state in which redistribution is impossible is, for example, a state in which stains or breakage of paper sheets are equal to or higher than a preset threshold value.

The serial number detection unit 145 reads the serial number printed on the paper leaf P from the image of the paper leaf. For example, the serial number detection unit 145 performs image processing such as character analysis on the image of the paper leaf, and detects the serial number or the like described on the paper leaf.

The thickness detection unit 150 detects the thickness of paper sheets. For example, when two sheets of paper are transported in an overlapping manner, the thickness detecting unit 150 detects the thickness of the two sheets. Under the control of the control unit 180, the stacking unit 160 classifies and seals the paper sheets based on the processing results of the transport state detection unit 130, the detection unit 140, and the thickness detection unit 150. The collection unit 160 includes, for example, a regular ticket collection unit 161 and a loss ticket collection unit 162. Paper leaves determined to be genuine tickets by the comprehensive determination unit 182 are accumulated in the regular ticket collection unit 161 for each ticket type (for example, ticket types A, B, ...). In the loss ticket collection unit 162, paper sheets whose loss tickets have been determined by the comprehensive determination unit 182 are collected for each ticket type.

The paper leaf whose type or the like cannot be identified based on the processing results of the transport state detection unit 130, the detection unit 140, and the thickness detection unit 150 under the control of the control unit 180. Collect or seal the species.

The control unit 180 includes, for example, a main control unit 181, a comprehensive determination unit 182, and an operation unit 183. The main control unit 181 controls each function of the paper leaf processing device 100. For example, the main control unit 181 rotates the gates G1 and G2 included in the paper leaf processing device 100 based on the determination result by the comprehensive determination unit 182 to transport the paper sheets to a predetermined transfer destination. For example, the main control unit 181 rotates the distribution gate G1 to the left (counterclockwise) when the comprehensive determination unit 182 determines that the paper sheets are genuine tickets, and further turns the distribution gate G2 to the right. By rotating it (clockwise), the paper sheets are collected in the regular ticket collecting part 161 of the collecting part 160. Further, the main control unit 181 rotates the distribution gate G1 counterclockwise (counterclockwise) when the comprehensive determination unit 182 determines that the paper sheets are bad tickets, and further, the distribution gate G2 is left (counterclockwise). By rotating it counterclockwise), the paper sheets are accumulated in the loss ticket accumulation unit 162 of the collection unit 160. Further, when the comprehensive determination unit 182 determines that the paper leaves are exclusion tickets, the main control unit 181 rotates the distribution gate G1 to the right (clockwise) to collect the paper leaves. It is accumulated in the unit 170.

The comprehensive determination unit 182 includes a transport state detection result by the transport state detection unit 130, a ticket type determination result by the ticket type detection unit 142, a authenticity detection result by the authenticity detection unit 143, and a positive / loss determination result by the positive / loss determination unit 144. The serial number detection result by the serial number detection unit 145 and the thickness detection result by the thickness detection unit 150 are comprehensively judged, and the ticket type of the paper leaf, whether the paper leaf is a genuine ticket, or a loss ticket. It is determined whether the ticket is an exclusion ticket or the like.

The operation unit 183 is, for example, a keyboard, a mouse, and a liquid crystal display. The operation unit 183 sets the operation mode of the paper leaf processing device 100, sets the partial area of the paper leaf processing device P, displays the processing result, and sends the first reference pattern 191 and the second reference pattern 192 to the storage unit 190. Accepts operations related to registration, etc. from the operator. The first reference pattern 191 is, for example, set with characteristic information regarding the contour shape, color, pattern, pattern, etc. of the target area for each type of paper sheet. The first reference pattern 191 is used for identifying, for example, paper leaf ticket types (for example, 10,000 yen, 5,000 yen, 1,000 yen, 10 dollars, 20 dollars, 50 dollars, 100 dollars, etc.). The second reference pattern 192 is, for example, for each ticket type and generation of paper leaves, and feature information is set for at least one partial region of the paper leaves set for each ticket type. It is a thing. The partial area is set, for example, by the operator selecting an area having a difference among a plurality of ticket types by the operation unit 183. Further, the partial area may be set as a preset area (for example, a predetermined area from a reference position such as the center of paper sheets or the upper left). The second reference pattern is used, for example, to identify the generation of paper sheets (for example, new bills, old bills).

The storage unit 190 is composed of, for example, an HDD (Hard Disc Drive), a flash memory, an EEPROM (Electrically Erasable Programmable Read Only Memory), a ROM (Read Only Memory), a RAM (Random Access Memory), or the like. The storage unit 190 stores various information and programs related to the paper leaf processing apparatus 100. For example, a first reference pattern 191 and a second reference pattern 192 are stored in the storage unit 190.

Next, a specific example of ticket type detection of paper sheets by the ticket type detection unit 142 of the first embodiment will be described. FIG. 2 is a diagram for explaining that the ticket type of the paper leaf is determined by weighting according to the degree of contamination of the paper leaf P. FIG. 2 shows a reading unit 141, a ticket type detecting unit 142, and a control unit 180 in each configuration of the paper leaf processing apparatus 100.

The reading unit 141 detects the reflected light, which is a physical characteristic of the paper sheets P transported in the direction of arrow A by the transport path 200. The reading unit 141 is, for example, an image reading sensor having an LED (Light Emitting Diode) array as a light emitting unit and a photodiode array or a CCD sensor as a light receiving unit.

The ticket type detection unit 142 includes, for example, a first ticket type identification unit 142a, a stain degree measurement unit 142b, a second ticket type identification unit 142c, and a ticket type determination unit 142d. The first ticket type identification unit 142a sets the feature extraction target area from the image of the paper sheets P read by the reading unit 141. The first ticket type identification unit 142a calculates, for example, the end point of the paper leaf region and the position of the center of gravity of the paper leaf region based on the contour information of the paper leaf P, and the paper leaves are based on the center of gravity position. Set the entire area.

FIG. 3 is a diagram for explaining a setting example of the feature extraction target area. In FIG. 3, two paper sheets P1 and P2 are represented. The first ticket type identification unit 142a sets the regions 300 and 302 corresponding to the contours of the paper sheets P1 and P2 from the images of the paper leaves P1 and P2, based on the contour information and the like. The first ticket type identification unit 142a may divide the regions of the paper sheets P1 and P2 into a plurality of grid-like uniform block units to set a plurality of regions.

In addition, the first ticket type identification unit 142a performs feature extraction on the set feature extraction target area. The first ticket type identification unit 142a may be characterized by, for example, the shading value of each pixel in the feature extraction target region or the average shading value of a plurality of pixels, or the differential value thereof. Further, the first ticket type identification unit 142a may, for example, extract feature information regarding the contour shape, pattern, pattern, etc. of the feature extraction target area.

Further, the first ticket type identification unit 142a is similar to the feature information extracted from the feature extraction target area and the reference pattern for each ticket type included in the first reference pattern 191 stored in the storage unit 190. Calculate the degree. For example, assuming that the number of ticket types to be identified is N (N is a natural number of 1 or more), the first ticket type identification unit 142a has a similarity Si (i: 1 to 1) with the N reference patterns. N) is calculated. The similarity can be calculated by using, for example, the matching rate when each feature information is compared, the comparison result between pixels, the simple similarity method or the compound similarity method. In addition, the first ticket type identification unit 142a makes a first determination as to which ticket type the paper leaf P belongs to, based on the calculated similarity. In the first determination, if the ticket type of the paper sheet P having the maximum value among the similarity Si of each ticket type and the similarity is equal to or higher than the threshold value, the ticket type is regarded as the first determination result. To do.

The fouling degree measuring unit 142b sets at least one partial region for identifying the generation from the image of the paper leaf P. FIG. 4 is a diagram for explaining a setting example of the partial area. In FIG. 4, the paper leaves P2 of the new bill and the paper leaves P2'of the old bill are shown. For example, when the generation of paper leaf P2 changes, the printing pattern is very similar because only the information in a part of the area is changed as compared with the series one generation ago. Therefore, the fouling degree measuring unit 142b sets the partial regions 304 and 306 in which the features changed by the generation are embedded from the images of the paper sheets P2 and P2', respectively. At least one partial area is set for the ticket type. By using this partial region, it is possible to reduce the amount of information when measuring the degree of fouling and identifying the generation, so that efficient and quick identification processing can be realized.

The stain degree measuring unit 142b extracts at least one partial area corresponding to the ticket type based on the first determination result, and measures the stain degree of each extracted partial area. For example, the stain degree measuring unit 142b compares the luminance distribution of each pixel in the extracted partial region with the luminance distribution of each pixel in the beautiful paper leaf partial region without stains, and the similarity of the distribution and the like. Measure the degree of pollution according to. In addition, the stain degree measuring unit 142b determines the degree of reading of physical characteristics and magnetic characteristics due to stains and stains adhering to each partial region, or creases and wrinkles of paper sheets P contained in the partial regions. It may be measured as. Further, the fouling degree measuring unit 142b may obtain the fouling feature information in the partial region and measure the fouling degree in association with the obtained feature amount of the fouling feature.

The second ticket type identification unit 142c identifies the generation for the ticket type identified by the first ticket type identification unit 142a. For example, the second ticket type identification unit 142c extracts features from the partial region where the degree of fouling is measured. The second ticket type identification unit 142c may be characterized by, for example, the shading value of each pixel in the partial region or the average shading value of a plurality of pixels, or the differential value thereof. In addition, the second ticket type identification unit 142c may, for example, extract feature information regarding the contour shape, pattern, pattern, etc. of the partial region.

Further, the second ticket type identification unit 142c calculates the degree of similarity between the extracted feature information and the second reference pattern 192 stored in the storage unit 190. For example, assuming that the number of generations to be identified is M (M is a natural number of 1 or more), the second ticket type identification unit 142c has a degree of similarity Si (i: 1 to M) with M reference patterns. ) Is calculated. The similarity can be calculated by using, for example, the matching rate when each feature information is compared, the comparison result between pixels, the simple similarity method or the compound similarity method. In addition, the second ticket type identification unit 142c makes a second determination as to which generation the paper leaf P belongs to, based on the calculated similarity. In the second determination, when the similarity is equal to or higher than the threshold value among the similarity Sis of each generation, the ticket type is used as the second determination result.

The ticket type determination unit 142d determines the final ticket type of the paper leaf P based on the second determination result and the stain degree measured by the stain degree measurement unit 142b. The ticket type determination unit 142d weights the similarity of the partial area according to the measured degree of fouling in the partial area. For example, the ticket type determination unit 142d multiplies the similarity by the weight "0" when the degree of contamination of the partial area is equal to or more than the threshold value, and multiplies the degree of similarity by "1" when the degree of contamination is less than the threshold value. To do. As a result, the ticket type determination unit 142d can determine the ticket type based on the partial area having a low degree of contamination, and can improve the reliability of the determination result. Further, the ticket type determination unit 142d may multiply the similarity by the reciprocal of the degree of contamination as a weight. As a result, if the partial area is cleaner, the similarity value can be increased. Therefore, the reliability of the determination result can be improved.

FIG. 5 is a flowchart for explaining the ticket type detection process of the first embodiment. First, the main control unit 181 detects that the paper leaf P has reached the imaging position of the reading unit 141 (step S100). When the transport position is detected, the reading unit 141 acquires the scanned image of the paper sheets P under the control of the main control unit 181 (step S102). Next, the first ticket type identification unit 142a sets the feature extraction target area based on the read image of the acquired paper sheets P (step S104).

Next, the first ticket type identification unit 142a performs feature extraction from the feature extraction target area (step S106). Next, the first ticket type identification unit 142a calculates the degree of similarity between the extracted feature information and the first reference pattern 191 stored in the storage unit 190 (step S108). Next, the first ticket type identification unit 142a makes a first determination as to which ticket type it belongs to based on the calculated similarity (step S110). Next, the stain degree measuring unit 142b sets the partial area used for identification by the second ticket type identification unit 142c based on the first determination result (step S112).

Next, the fouling degree measuring unit 142b measures the fouling degree with respect to the set partial region (step S114). Next, the second ticket type identification unit 142c extracts features from the partial region where the degree of fouling is measured (step S116). Next, the second ticket type identification unit 142c calculates the similarity between the feature information in the extracted partial region and the second reference pattern 192 of each ticket type stored in the storage unit 190 (step S118). ..

Next, the ticket type determination unit 142d makes a second determination of which ticket type belongs to which generation based on the calculated similarity (step S120). Next, the ticket type determination unit 142d weights the second determination result according to the measured degree of contamination in the partial region (step S122). Next, the ticket type determination unit 142d determines the final ticket type of the paper leaf P based on the weighted second determination result (step S124).

As described above, according to the paper leaf processing apparatus 100 of the first embodiment, for example, the paper leaves with advanced stain (for example, the region having a partial difference in the printed pattern is stained or faded). Even if the paper leaves are in a state where the characteristics are lost), the ticket type of the paper leaves can be determined by weighting according to the measured degree of fouling in the partial region. As a result, it is possible to reduce misreading of the ticket type of paper leaves and improve the performance of discriminating the ticket type of paper leaves. In addition, it is possible to improve the performance of authenticity discrimination corresponding to the ticket type.

(Second Embodiment)
Next, the configuration of the second embodiment of the paper leaf processing apparatus will be described. The paper leaf processing apparatus of the second embodiment is different from the first embodiment in that the ticket type detection unit 142 is provided with the correction unit 142e. Therefore, in the following description, the function of the correction unit 142e will be mainly described. Further, in the following description, the same name and reference numeral will be used for the configuration having the same function as the ticket type detection unit 142 of the first embodiment, and specific description thereof will be omitted.

FIG. 6 is a diagram for explaining that the ticket type of the paper leaf is determined by the correction according to the degree of contamination of the paper leaf P. The ticket type detection unit 142A shown in FIG. 6 includes, for example, a first ticket type identification unit 142a, a stain degree measurement unit 142b, a second ticket type identification unit 142c, a ticket type determination unit 142d, and a correction unit 142e. And.

The correction unit 142e corrects the image of the partial region when, for example, the stain degree for each partial region measured by the stain degree measuring unit 142b is equal to or greater than the threshold value. The correction unit 142e corrects the image of the partial region by using, for example, a histogram equalization method that emphasizes the contrast by density conversion. Further, the correction unit 142e may store information about the brightness standard in a clean state in advance in the storage unit 190 or the like, and perform brightness conversion so that the brightness of the partial area becomes the reference value. The brightness conversion is, for example, image processing such as gamma correction.

Further, the correction unit 142e changes the value of the parameter (for example, the setting parameter for setting the contrast magnitude) when correcting the image according to the degree of contamination of each partial region measured by the degree of contamination measurement unit 142b. May be corrected. As a result, finer image correction can be performed according to the degree of fouling.

The second ticket type identification unit 142c calculates the similarity between the image of the partial region corrected by the correction unit 142e and the second reference pattern 192 stored in the storage unit 190, and identifies the generation ( Second judgment). In addition, the ticket type determination unit 142d determines the final ticket type of the paper leaf P based on the generation identification result.

FIG. 7 is a flowchart for explaining the ticket type detection process of the second embodiment. In the ticket type detection process of the second embodiment, the process of step S122 is deleted and the processes of steps S130 and S132 are added as compared with the ticket type detection process of the first embodiment. Therefore, in the following, the processing of step S130 and step S132 will be mainly described.

In the process of step S114, the correction unit 142e measures the degree of contamination of the partial region by the degree of contamination measurement unit 142b, and then determines whether or not the degree of contamination is equal to or greater than the threshold value (step S130). When the degree of fouling is equal to or higher than the threshold value, the correction unit 142e corrects the image of the partial region (step S132), and then executes the processes after step S116. In the process of step S124, the ticket type determination unit 142d determines the final ticket type based on the second determination result of the ticket type.

As described above, according to the paper leaf processing apparatus of the second embodiment, the paper leaf ticket is determined by correcting the partial image based on the degree of fouling and determining the paper leaf ticket type. It is possible to reduce misreading of seeds and improve the performance of discriminating the ticket type of paper leaves. In addition, it is possible to improve the performance of authenticity discrimination corresponding to the ticket type. The first and second embodiments may be combined with a part or all of the other embodiments.

According to at least one embodiment described above, the paper leaf processing apparatus 100 has an imaging unit (reading unit 141) that images the paper leaves P and a first type for identifying the ticket type of the paper leaves P. The reference pattern of the above and the second reference pattern for identifying the generation for each ticket type are stored in the storage unit 190, and the image of the paper leaf P captured by the imaging unit and the storage unit 190. Based on the degree of similarity with the first reference pattern 191, the first ticket type identification unit 142a for identifying the ticket type of the paper leaf P, and the first ticket type identification unit 142a from the image of the paper leaf P A stain degree measuring unit 142b that extracts at least one partial area based on the identified ticket type and measures the degree of contamination of the extracted partial area, an image of the partial area, and a second stored in the storage unit 190. Based on the similarity with the reference pattern 192, the identification result by the second ticket type identification unit 142c for identifying the generation of the ticket type of the paper leaf P, the second ticket type identification unit 142c, and the stain degree measurement By having the ticket type determining unit 142d for determining the type of paper leaves based on the degree of contamination measured by the unit 142b, the performance of determining the ticket type of paper leaves can be improved.

Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention as well as the invention described in the claims and the equivalent scope thereof.

100 ... Paper leaf processing device, 110 ... Supply unit, 120 ... Extraction unit, 130 ... Transport state detection unit, 140 ... Detection unit, 141 ... Reading unit, 142 ... Ticket type detection unit, 142a ... First ticket type identification Unit, 142b ... Stain degree measurement unit, 142c ... Second ticket type identification unit, 142d ... Ticket type determination unit, 142e ... Correction unit, 143 ... Authenticity detection unit, 144 ... Positive loss determination unit, 145 ... Serial number detection Unit, 150 ... Thickness detection unit, 160 ... Accumulation unit, 170 ... Exclusion ticket accumulation unit, 180 ... Control unit 180 ... Storage unit

Claims (6)

An imaging unit that captures paper leaves and
A storage unit that stores a first reference pattern for identifying the ticket type of the paper leaf and a second reference pattern for identifying the generation for each ticket type.
First ticket type identification for identifying the ticket type of the paper leaf based on the similarity between the image of the paper leaf image captured by the imaging unit and the first reference pattern stored in the storage unit. Department and
An stain degree measuring unit that extracts at least one partial region from the image of the paper sheets based on the ticket type identified by the first ticket type identification unit and measures the degree of contamination of the extracted partial region.
A second ticket type identification unit that identifies the generation of the paper leaf ticket type based on the similarity between the image of the partial region and the second reference pattern stored in the storage unit.
Based on the identification result by the second ticket type identification unit and the stain degree measured by the stain degree measuring unit, the ticket type determination unit that determines the ticket type of the paper sheets
Paper leaf processing device equipped with. The ticket type determination unit weights the identification result by the second ticket type identification unit according to the degree of contamination of the partial area measured by the stain degree measurement unit, and based on the weighted identification result, the ticket type determination unit weights the identification result. Determining the type of paper leaves,
The paper leaf processing apparatus according to claim 1. An imaging unit that captures paper leaves and
A storage unit that stores a first reference pattern for identifying the ticket type of the paper leaf and a second reference pattern for identifying the generation for each ticket type.
First ticket type identification for identifying the ticket type of the paper leaf based on the similarity between the image of the paper leaf image captured by the imaging unit and the first reference pattern stored in the storage unit. Department and
An stain degree measuring unit that extracts at least one partial region from the image of the paper sheets based on the ticket type identified by the first ticket type identification unit and measures the degree of contamination of the extracted partial region.
A correction unit that corrects the image of the partial region based on the stain degree measured by the stain degree measuring unit, and a correction unit.
A second that identifies the generation of the paper leaf ticket type based on the degree of similarity between the image of the partial region corrected by the correction unit and the second reference pattern stored in the storage unit. Ticket type identification department and
Based on the identification result by the second ticket type identification unit, the ticket type determination unit that determines the type of paper leaves, and the ticket type determination unit.
Paper leaf processing device equipped with. The correction unit corrects an image of a partial region having a degree of fouling equal to or higher than a threshold value among the extracted at least one partial region.
The paper leaf processing apparatus according to claim 3. The computer
The ticket of the paper leaf based on the similarity between the image of the paper leaf captured by the imaging unit and the first reference pattern for identifying the ticket type of the paper leaf stored in the storage unit. Identify the species,
At least one partial region was extracted from the image of the paper leaf based on the identified ticket type.
The degree of fouling of the extracted partial area was measured and
The generation of the paper leaf ticket type is identified based on the similarity between the image of the partial region and the second reference pattern for identifying the generation of each ticket type stored in the storage unit. ,
The ticket type of the paper leaf is determined based on the identified generation of the paper leaf ticket type and the measured degree of contamination.
Paper leaf processing method. On the computer
The ticket of the paper leaf based on the similarity between the image of the paper leaf captured by the imaging unit and the first reference pattern for identifying the ticket type of the paper leaf stored in the storage unit. Let them identify the species
At least one partial region is extracted from the image of the paper leaf based on the identified ticket type.
The degree of contamination of the extracted partial region was measured, and
The generation of the paper leaf ticket type is identified based on the similarity between the image of the partial region and the second reference pattern for identifying the generation of each ticket type stored in the storage unit. ,
The ticket type of the paper leaf is determined based on the generation of the identified paper leaf ticket type and the measured degree of contamination.
Paper leaf processing program.

Images