Paper sheet type identification device and paper sheet type identification method

Abstract

To provide a paper sheet identification apparatus, a paper sheet identification method, and a paper sheet identification program capable of improving paper sheet identification accuracy.SOLUTION: A paper sheet identification apparatus for identifying a paper sheet provided with an identification target, comprises: a light source for irradiating a paper sheet with light; a light receiving unit for receiving light coming from the paper sheet; and a control unit for acquiring output data of the light receiving unit. The control unit acquires first data that is output data of the light receiving unit corresponding to an area including the identification target and second data that is output data of the light receiving unit corresponding to an area not including the identification target, generates third data where the first data is corrected by the second data, and identifies the paper sheet based on the third data.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a paper sheet discrimination device, a paper sheet discrimination method, and a paper sheet discrimination program.

Background Art

[0002] In a paper sheet discrimination device for discriminating paper sheets such as banknotes, various sensors are used to acquire the characteristics of the paper sheets. Then, based on the acquired characteristics of the paper sheets, it is generally performed to discriminate (judge) the type (currency denomination), authenticity, integrity, etc. of the paper sheets.

[0003] For example, Patent Documents 1 and 2 disclose an optical sensor that irradiates banknotes with infrared light of a plurality of wavelengths from a light source and receives the light reflected or transmitted by the banknotes with a light receiving unit.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, due to environmental factors such as variations in the characteristics of each element of the light emitting element (for example, LED) of the light source, shift of the peak wavelength due to temperature, and variation in the transmittance of the light guide of the light source (for example, a light guide made of acrylic resin) according to the wavelength, the output data of the light receiving unit may vary. In that case, since the discrimination process of the paper sheets is performed based on the varying output data, the discrimination accuracy of the paper sheets will decrease. Further, since the variation in the output data due to environmental factors is particularly prominent in the infrared region, when performing the discrimination process of the paper sheets based on the output data in the infrared region, the accuracy is particularly likely to deteriorate.

[0006] Further, when irradiating a banknote with light of multiple wavelengths and identifying paper-like materials based on output data related to the light of multiple wavelengths acquired from a light-receiving unit, it is common to perform the identification process using only the output data related to the light of each wavelength. However, in that case, the authenticity separation performance of the identification object (e.g., special ink) provided on the paper-like materials may not be sufficient. If the authenticity separation performance of the identification object is insufficient, it will lead to a decrease in the identification accuracy of the paper-like materials.

[0007] The present disclosure has been made in view of the above situation, and an object thereof is to provide a paper-like material identification device, a paper-like material identification method, and a paper-like material identification program capable of improving the identification accuracy of paper-like materials.

Means for Solving the Problems

[0008] In order to solve the above-described problems and achieve the object, (1) a paper-like material identification device according to a first aspect of the present disclosure is a paper-like material identification device for identifying paper-like materials provided with an identification object, including a light source that irradiates the paper-like materials with light, a light-receiving unit that receives the light coming from the paper-like materials, and a control unit that acquires output data of the light-receiving unit. The control unit acquires first data that is the output data of the light-receiving unit corresponding to a region including the identification object, and second data that is the output data of the light-receiving unit corresponding to a region not including the identification object, generates third data obtained by correcting the first data with the second data, and identifies the paper-like materials based on the third data.

[0009] (2) In the paper-like material identification device according to (1) above, the light source may irradiate the paper-like materials with light of multiple wavelengths, the light-receiving unit may receive the light of multiple wavelengths coming from the paper-like materials, the first data and the second data may each include data related to the light of the multiple wavelengths, the control unit may generate third data related to multiple wavelengths obtained by correcting the first data related to the light of the multiple wavelengths with the second data related to the light of the same corresponding wavelength, and may identify the paper-like materials based on the third data related to the light of the multiple wavelengths.

[0010] (3) In the paper sheet discrimination device according to (2) above, the control unit may calculate first multiplication data, which is data obtained by multiplying data related to light of a first wavelength and a second wavelength among the first data related to light of the plurality of wavelengths, and second multiplication data, which is data obtained by multiplying data related to light of the first wavelength and the second wavelength among the second data related to light of the plurality of wavelengths. The control unit may generate fourth data obtained by correcting the first multiplication data with the second multiplication data, and may discriminate paper sheets based on the third data related to light of the plurality of wavelengths and the fourth data.

[0011] (4) In the paper sheet discrimination device according to any one of (1) to (3) above, the control unit may use, as the second data, a representative value of output data of a region not including the object to be discriminated.

[0012] (5) In the paper sheet discrimination device according to any one of (1) to (4) above, the light source may include a rod-shaped light guide made of an acrylic resin and a light emitting element facing at least one of two end faces of the light guide, and the light source may irradiate paper sheets with light through the light guide.

[0013] (6) In the paper sheet discrimination device according to any one of (1) to (5) above, the light source may irradiate paper sheets with linearly shaped light in the main scanning direction, the light receiving unit may receive linearly shaped light in the main scanning direction coming from the paper sheets, and the control unit may use, as the second data, output data corresponding to the position in the main scanning direction of the region including the object to be discriminated.

[0014] (7) The paper sheet discrimination device according to the second aspect of the present disclosure is a paper sheet discrimination device that discriminates paper sheets provided with an object to be discriminated, and includes a light source that irradiates the paper sheets with light of a plurality of wavelengths, a light receiving unit that receives the light of the plurality of wavelengths coming from the paper sheets, and a control unit that acquires output data related to the light of the plurality of wavelengths of the light receiving unit. The control unit calculates multiplication data that is data obtained by multiplying data related to the light of a first wavelength and a second wavelength among the acquired output data related to the light of the plurality of wavelengths, and discriminates the paper sheets based on the output data related to the light of the plurality of wavelengths and the multiplication data.

[0015] (8) In the paper sheet discrimination device according to any one of (1) to (7) above, the light source may irradiate the paper sheets with infrared light, and the infrared light may include light having a wavelength of 850 nm or more and 950 nm or less.

[0016] (9) In the paper sheet discrimination device according to any one of (1) to (8) above, the light receiving unit may receive the light irradiated from the light source and reflected by the paper sheets, and the output data may include data related to the light reflected by the paper sheets.

[0017] (10) In the paper sheet discrimination device according to any one of (1) to (9) above, the paper sheets to be discriminated may include at least one of an ink whose reflectance decreases as the wavelength increases in the infrared region and an ink whose reflectance increases as the wavelength increases in the infrared region as the object to be discriminated.

[0018] (11) The paper sheet discrimination method according to the third aspect of the present disclosure is a paper sheet discrimination method that discriminates paper sheets provided with an object to be discriminated, and includes a step (A) of acquiring output data from a light receiving unit that has received light irradiated from a light source and coming from the paper sheets, a step (B) of acquiring first data that is the output data of the light receiving unit corresponding to a region including the object to be discriminated and second data that is the output data of the light receiving unit corresponding to a region not including the object to be discriminated, a step (C) of generating third data obtained by correcting the first data with the second data, and a step (D) of discriminating the paper sheets based on the third data.

[0019] (12) In the method for identifying paper sheets according to (11) above, the light source may irradiate the paper sheets with light of a plurality of wavelengths, the light receiving unit may receive light of a plurality of wavelengths arriving from the paper sheets, the first data and the second data may each include data related to the light of the plurality of wavelengths, and in step (C) above, third data related to a plurality of wavelengths may be generated by correcting the first data related to the light of the plurality of wavelengths with the second data related to the light of the same corresponding wavelength, respectively. In step (D) above, the paper sheets may be identified based on the third data related to the light of the plurality of wavelengths.

[0020] (13) In the method for identifying paper sheets according to (12) above, a step (E) of calculating a first multiplication data which is data obtained by multiplying the data related to the light of the first wavelength and the second wavelength among the first data related to the light of the plurality of wavelengths, and a second multiplication data which is data obtained by multiplying the data related to the light of the first wavelength and the second wavelength among the second data related to the light of the plurality of wavelengths may be further provided. In step (C) above, fourth data obtained by correcting the first multiplication data with the second multiplication data may be generated. In step (D) above, the paper sheets may be identified based on the third data related to the light of the plurality of wavelengths and the fourth data.

[0021] (14) In the method for identifying paper sheets according to any one of (11) to (13) above, in step (C) above, as the second data, a representative value of the output data of the region not including the object to be identified may be used.

[0022] (15) In the method for identifying paper sheets according to any one of (11) to (14) above, the light source may include a rod-shaped light guide made of an acrylic resin and a light emitting element facing at least one of the two end faces of the light guide, and the light source may irradiate the paper sheets with light through the light guide.

[0023] (16) In the method for identifying paper sheets according to any one of (11) to (15) above, the light source may irradiate the paper sheets with linearly shaped light in the main scanning direction, the light receiving unit may receive the linearly shaped light in the main scanning direction coming from the paper sheets, and in step (C) above, as the second data, output data corresponding to the position in the main scanning direction of the region including the object to be identified may be used.

[0024] (17) The method for identifying paper sheets according to the fourth aspect of the present disclosure is a method for identifying paper sheets provided with an object to be identified, including: a step of obtaining output data related to the plurality of wavelengths of light received by a light receiving unit that receives the light of the plurality of wavelengths irradiated from a light source and coming from the paper sheets; a step of calculating multiplication data that is data obtained by multiplying the data related to the light of the first wavelength and the second wavelength among the output data related to the plurality of wavelengths of light obtained; and a step of identifying the paper sheets based on the output data related to the plurality of wavelengths of light and the multiplication data.

[0025] (18) In the method for identifying paper sheets according to any one of (11) to (17) above, the light source may irradiate the paper sheets with infrared light, and the infrared light may include light having a wavelength of 850 nm or more and 950 nm or less.

[0026] (19) In the method for identifying paper sheets according to any one of (11) to (18) above, the light receiving unit may receive the light irradiated from the light source and reflected by the paper sheets, and the output data may include data related to the light reflected by the paper sheets.

[0027] (20) In the method for identifying paper sheets according to any one of (11) to (19) above, the paper sheets to be identified may include at least one of an ink whose reflectance decreases as the wavelength increases in the infrared region and an ink whose reflectance increases as the wavelength increases in the infrared region as the object to be identified.

[0028] (21) The paper sheet discrimination program according to the fifth aspect of the present disclosure is a paper sheet discrimination program for discriminating a paper sheet on which an object to be discriminated is provided using a paper sheet discrimination device, including: a process (A) of acquiring output data from a light receiving unit that receives light irradiated from a light source and arriving from the paper sheet; a process (B) of acquiring first data that is the output data of the light receiving unit corresponding to a region including the object to be discriminated and second data that is the output data of the light receiving unit corresponding to a region not including the object to be discriminated; a process (C) of generating third data obtained by correcting the first data with the second data; and a process (D) of discriminating the paper sheet based on the third data, and causing the paper sheet discrimination device to execute these processes.

[0029] (22) In the paper sheet discrimination program described in (21) above, the light source may irradiate the paper sheet with light of a plurality of wavelengths, the light receiving unit may receive light of a plurality of wavelengths arriving from the paper sheet, the first data and the second data may each include data related to the light of the plurality of wavelengths, in the above process (C), third data related to a plurality of wavelengths obtained by correcting the first data related to the light of the plurality of wavelengths with the second data related to the light of the same corresponding wavelength may be generated, and in the above process (D), the paper sheet may be discriminated based on the third data related to the light of the plurality of wavelengths.

[0030] (23) In the paper sheet discrimination program described in (22) above, it may further include a process (D) of calculating first multiplication data that is data obtained by multiplying the data related to the light of the first wavelength and the second wavelength among the first data related to the light of the plurality of wavelengths, and second multiplication data that is data obtained by multiplying the data related to the light of the first wavelength and the second wavelength among the second data related to the light of the plurality of wavelengths, in the above process (C), fourth data obtained by correcting the first multiplication data with the second multiplication data may be generated, and in the above process (D), the paper sheet may be discriminated based on the third data related to the light of the plurality of wavelengths and the fourth data.

[0031] (24) In the method for identifying paper sheets according to any one of (21) to (23) above, in the above process (C), as the second data, a representative value of the output data of the region not including the object to be identified may be used.

[0032] (25) In the paper sheet identification program according to any one of (21) to (24) above, the light source may include a rod-shaped light guide made of an acrylic resin and a light emitting element facing at least one of the two end faces of the light guide, and the light source may irradiate the paper sheets with light through the light guide.

[0033] (26) In the paper sheet identification program according to any one of (21) to (25) above, the light source may irradiate the paper sheets with linearly shaped light in the main scanning direction, the light receiving unit may receive the linearly shaped light in the main scanning direction coming from the paper sheets, and in the above process (C), as the second data, output data corresponding to the position in the main scanning direction of the region including the object to be identified may be used.

[0034] (27) The paper sheet identification program according to the sixth aspect of the present disclosure is a paper sheet identification program for identifying a paper sheet provided with an object to be identified using a paper sheet identification device, and includes a process of acquiring output data related to the plurality of wavelengths of light received by a light receiving unit that has received the light of the plurality of wavelengths irradiated from a light source and coming from the paper sheet, a process of calculating multiplication data that is data obtained by multiplying the data related to the light of the first wavelength and the second wavelength among the output data related to the acquired plurality of wavelengths of light, and a process of identifying the paper sheet based on the output data related to the plurality of wavelengths of light and the multiplication data, and causing the paper sheet identification device to execute the processes.

[0035] (28) In the paper sheet identification program according to any one of (21) to (27) above, the light source may irradiate the paper sheets with infrared light, and the infrared light may include light having a wavelength of 850 nm or more and 950 nm or less.

[0036] (29) In the paper sheet discrimination program according to any one of (21) to (28) above, the light receiving unit may receive light irradiated from the light source and reflected by the paper sheet, and the output data may include data related to the light reflected by the paper sheet.

[0037] (30) In the paper sheet discrimination method according to any one of (21) to (29) above, the paper sheet to be discriminated may include at least one of an ink whose reflectance decreases as the wavelength increases in the infrared region and an ink whose reflectance increases as the wavelength increases in the infrared region as the object to be discriminated.

Effect of the Invention

[0038] According to the present disclosure, it is possible to provide a paper sheet discrimination device, a paper sheet discrimination method, and a paper sheet discrimination program capable of improving the discrimination accuracy of paper sheets.

Brief Description of the Drawings

[0039]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Embodiments for Carrying Out the Invention

[0040] Hereinafter, embodiments of the paper sheet discrimination device, the paper sheet discrimination method, and the paper sheet discrimination program according to the present disclosure will be described with reference to the drawings. As the paper sheets targeted by the present disclosure, various paper sheets such as banknotes, checks, gift certificates, promissory notes, forms, securities, and card-shaped media can be applied. However, hereinafter, the present disclosure will be described by taking a device for banknotes as an example. Note that the paper sheet discrimination program may be introduced in advance into the paper sheet discrimination device, or may be recorded on a computer-readable recording medium or provided to the operator via a network. In the following description, the same reference numerals are commonly used between different drawings for the same part or parts having the same function, and the repeated description thereof will be omitted as appropriate. In addition, in the drawings for explaining the structure, an XYZ coordinate system orthogonal to each other is appropriately shown.

[0041] (Embodiment 1) With reference to FIG. 1, the configuration of the paper sheet discrimination device according to this embodiment will be described. FIG. 1 is a schematic diagram for explaining an example of the configuration of the paper sheet discrimination device according to this embodiment, and is a view of the banknote conveyance path seen from the side. As shown in FIG. 1, the paper sheet discrimination device 1a according to this embodiment includes a light source 11a that irradiates light onto a banknote BN, a light receiving unit 13a that receives the light arriving from the banknote BN, and a control unit 20a that acquires the output data of the light receiving unit 13a. For example, it can be mounted and used in a paper sheet processing device that processes banknotes. The banknote BN to be discriminated may be conveyed in the X direction within the XY plane.

[0042] FIG. 2 is an example of a planar schematic diagram showing an example of the banknote to be discriminated in this embodiment. FIG. 3 is an example of a graph showing the reflectance in the infrared region of the ink provided on the banknote to be discriminated in this embodiment. As shown in FIG. 2, on at least one main surface of the banknote BN to be discriminated in this embodiment, a discrimination object S is provided (for example, printed). On the main surface of the banknote BN, for example, a rectangular region ROI including the discrimination object S A and, for example, a rectangular region ROI that does not include the discrimination object S B are set.

[0043] The banknote BN to be discriminated may include, as the discrimination object S, at least one of an ink (hereinafter, negative ink) whose reflectance decreases as the wavelength increases in the infrared region and an ink (hereinafter, positive ink) whose reflectance increases as the wavelength increases in the infrared region, as shown in FIG. 3. According to the paper sheet discrimination device 1a, it is possible to accurately discriminate a banknote BN including such an ink. Hereinafter, negative ink and positive ink may be collectively referred to as special ink. In FIG. 3, IR1 is, for example, 800 nm, IR2 is, for example, 870 nm, and IR3 is 940 nm.

[0044] The light source 11a irradiates light onto the banknote BN. The light irradiated by the light source 11a may be light in a wavelength band including the peak wavelength and wavelengths in its vicinity. The type (wavelength) of the light irradiated from the light source 11a is not particularly limited, and examples include visible light such as white light, red light, green light, and blue light, and infrared light.

[0045] The light receiving unit 13a receives the light arriving from the banknote BN. That is, it can function as an optical sensor. The light receiving unit 13a may receive the light irradiated from the light source 11a and reflected by the banknote BN. That is, the light receiving unit 13a may receive the light reflected by the banknote BN while the light source 11a irradiates light. At this time, the light receiving unit 13a can function as a sensor having sensitivity at least in the wavelength band of the light irradiated from the light source 11a. The light receiving unit 13a may output an electrical signal corresponding to the amount of received light as output data. More specifically, the light receiving unit 13a may include a light receiving element, the light receiving element may receive light and convert it into an electrical signal corresponding to the incident light amount, and the light receiving unit 13a may output the electrical signal. Here, the "light amount" means a physical quantity proportional to the radiant intensity and incident time of the incident light.

[0046] FIG. 4 is a schematic diagram for explaining an example of the configuration of the paper sheet discrimination device according to the present embodiment, and is a view seen from an oblique direction. As shown in FIG. 4, the light source 11a and the light receiving unit 13a may constitute an optical line sensor 14a extending in the Y direction. In this case, the Y direction corresponds to the main scanning direction of the optical line sensor 14a, and the X direction corresponds to the sub-scanning direction of the optical line sensor 14a. The light source 11a may irradiate light linearly extending in the Y direction. The light receiving unit 13a may include a plurality of light receiving elements (light receiving pixels) arranged in a row in the Y direction and may constitute a linear image sensor.

[0047] Further, the lengths of the light source 11a and the light receiving unit 13a in the Y direction (main scanning direction) may be longer than the length of the banknote BN in the Y direction. Then, the light source 11a may linearly irradiate light over the entire Y direction of the banknote BN, and the light receiving unit 13a may receive the light reflected over the entire Y direction of the banknote BN. That is, the light receiving unit 13a may output an electrical signal corresponding to the incident light amount on a plurality of channels corresponding to a plurality of light receiving elements (positions in the Y direction). The channels are numbers assigned to the light receiving elements in order in the Y direction. At this time, the light receiving unit 13a may output, as output data, line data which is data related to the light simultaneously received on each channel. While conveying the banknote BN in the X direction (sub-scanning direction), by repeating the irradiation of light by this light source 11a and the light reception by the light receiving unit 13a, data related to the reflected light of the entire banknote BN may be acquired.

[0048] FIG. 5 is a schematic diagram for explaining an example of the configuration of the paper sheet discrimination device according to the present embodiment, and is a view of the banknote conveyance path as seen from above. As shown in FIG. 5, the light source 11a may include a light guide 15a and light emitting elements 17a respectively facing two end faces 15aa of the light guide 15a, and may irradiate the banknote BN with light via the light guide 15a.

[0049] The light guide 15a is a transparent rod-shaped optical member, which guides the light from the light emitting element 17a and irradiates the banknote BN, which is the irradiation target, with linear light, and linearizes the light emitted from the light emitting element 17a.

[0050] The light guide 15a may be made of an acrylic resin. Since the light guide 15a made of an acrylic resin has a great influence on the output data of the light receiving unit 13a, in this case, the variation of the first data described later can be reduced particularly effectively. Therefore, it is possible to particularly effectively improve the discrimination accuracy of the banknote BN.

[0051] The light-emitting element 17a is an element that emits light toward the opposing end faces 15aa. For example, an LED (Light Emitting Diode) can be used. Note that a plurality of light-emitting elements 17a may be provided with respect to the corresponding end faces. Also, the light-emitting element 17a may be arranged to face only one of the two end faces 15aa.

[0052] The light source 11a may irradiate the banknote BN with infrared light including light having a wavelength of 850 nm or more and 950 nm or less. Since the transmittance of the light guide 15a (for example, a light guide made of an acrylic resin) of the light source 11a varies particularly greatly in the infrared region near 900 nm, in the case of the above configuration, the variation in output data (first data described later) can be particularly effectively reduced. Therefore, it is possible to particularly effectively improve the discrimination accuracy of the banknote BN. Also, it is possible to accurately discriminate a banknote BN including an ink (for example, a special ink) whose reflectance varies in the infrared region near 900 nm as the discrimination object S.

[0053] Each light-receiving pixel of the light-receiving unit 13a may include a light-receiving element having sensitivity over the entire region of a plurality of different wavelength bands, or may include a plurality of types of light-receiving elements that selectively receive light in different wavelength bands. In the former case, the light source 11a may irradiate the banknote BN with light of a plurality of wavelengths in sequence, and the light-receiving unit 13a may receive the light of the corresponding wavelength in accordance with the irradiation timing of the light of each wavelength. In the latter case, the light source 11a may irradiate the banknote BN with light of a plurality of wavelengths simultaneously, and the light-receiving unit 13a may receive the light of a plurality of wavelengths with a plurality of types of light-receiving elements respectively.

[0054] The control unit 20a performs a process of acquiring the output data of the light-receiving unit 13a. That is, data corresponding to the amount of light received by the light-receiving unit 13a is acquired. The output data of the light-receiving unit 13a acquired by the control unit 20a may be digitized. The control unit 20a may acquire image data of the entire banknote BN as the output data of the light-receiving unit 13a.

[0055] FIG. 6 is a schematic diagram showing image data of the entire banknote. The image data of the entire banknote BN is data (two-dimensional data) obtained by imaging the entire banknote BN, and as shown in FIG. 6, it may be composed of a plurality of pixels Pix arranged in a matrix in the Y direction (main scanning direction) and the X direction (sub-scanning direction). The address of each pixel Pix may be specified by the channel of the light receiving unit 13a corresponding to the position in the Y direction and the line corresponding to the position in the X direction. The line is a number sequentially assigned to the line data sequentially output by the light receiving unit 13a.

[0056] The output data of the light receiving unit 13a acquired by the control unit 20a may include data related to the light reflected by the banknote BN. Thereby, it is possible to accurately identify the banknote BN including the ink (for example, special ink) having characteristics in the reflectance as the identification object S.

[0057] Further, the control unit 20a may acquire, as the output data of the light receiving unit 13a, image data related to the reflected light of the entire banknote BN. Hereinafter, the image data related to the reflected light is referred to as reflected image data.

[0058] Note that the resolution of the output data acquired by the control unit 20a may be the same as or different from the resolution of the output data of the light receiving unit 13a, and may be low, for example, in the Y direction (main scanning direction) and the X direction (sub-scanning direction).

[0059] The control unit 20a may control each part of the paper sheet discrimination device 1a, and may be composed of, for example, a program for realizing various processes including a paper sheet discrimination program, a CPU (Central Processing Unit) that executes the program, and various hardware (for example, FPGA (Field Programmable Gate Array)) controlled by the CPU.

[0060] The control unit 20a is the first data that is the output data of the light receiving unit 13a corresponding to the region ROI A (see FIG. 2) including the identification object S, and the region ROI not including the identification object SB Perform a process of acquiring the second data, which is the output data of the light receiving unit 13a corresponding to (refer to FIG. 2).

[0061] Both the first data and the second data may be part of the reflected image data of the entire banknote BN, that is, the reflected image data of a part of the banknote BN. Region ROI A and ROI B may be preset according to the denomination of the banknote BN, and the control unit 20a may use the regions ROI A and ROI B Based on the position information, the first data and the second data may be extracted from the output data of the light receiving unit 13a (for example, the reflected image data of the entire banknote BN).

[0062] Then, the control unit 20a performs a process of generating third data obtained by correcting the first data with the second data (hereinafter sometimes referred to as a correction process), and performs a process of identifying the banknote BN based on the third data (hereinafter sometimes referred to as an identification process). Due to environmental factors such as variations in the characteristics of each element of the light emitting element 17a (for example, an LED) of the light source 11a, the shift of the peak wavelength due to temperature, the variation of the transmittance of the light guide 15a (for example, a light guide made of acrylic resin) of the light source 11a according to the wavelength, and variations in the characteristics of the light receiving element itself of the light receiving unit 13a, the output data of the light receiving unit 13a may vary. However, according to the present embodiment, the first data, which is the output data of the light receiving unit 13a corresponding to the region ROI A including the identification object S, is corrected with the second data, which is the output data of the light receiving unit 13a corresponding to the region ROI B excluding the identification object S, to generate the third data. Therefore, variations in the output data (especially the first data) caused by the above environmental factors can be reduced. And since the banknote BN is identified based on the third data, which is the corrected data, the banknote BN can be identified based on the data with reduced variations. Therefore, it is possible to improve the identification accuracy of the banknote BN.

[0063] In the correction process, the control unit 20a may generate the third data by normalizing the first data with the second data. For example, a process of dividing each output value (pixel value) of the first data by the output value related to the second data may be performed.

[0064] Further, the control unit 20a may use, as the second data, a representative value (for example, an average value, a median value, etc.) of the output data of the light receiving unit 13a corresponding to the region ROI B that does not include the identification target object S. For example, each output value (pixel value) of the first data may be normalized (divided) using the average value of the output values (pixel values) included in the reflected image data of the region ROI B that does not include the identification target object S.

[0065] The light source 11a may irradiate the banknote BN with light of a plurality of wavelengths, the light receiving unit 13a may receive the light of a plurality of wavelengths arriving from the banknote BN, the first data and the second data may each include data related to the light of a plurality of wavelengths, and in the correction process, the control unit 20a may generate the third data related to the light of a plurality of wavelengths by correcting the first data related to the light of a plurality of wavelengths with the second data related to the light of the same corresponding wavelength respectively, and in the identification process, the banknote BN may be identified based on the third data related to the light of a plurality of wavelengths. Thereby, it is possible to accurately identify the banknote BN provided with the identification target object S (for example, special ink) whose characteristics (for example, reflectance) change according to the wavelength.

[0066] Also, in this case, the control unit 20a may perform a process (hereinafter sometimes referred to as a multiplication process) of calculating first multiplication data, which is data obtained by multiplying data related to light of a first wavelength and a second wavelength among data related to light of a plurality of wavelengths, and second multiplication data, which is data obtained by multiplying data related to light of a first wavelength and a second wavelength among data related to light of a second plurality of wavelengths. In the correction process, a process of further generating fourth data obtained by correcting the first multiplication data with the second multiplication data may be performed. In the identification process, the banknote BN may be identified based on third data related to light of a plurality of wavelengths and the fourth data. Thereby, the separation performance of the authenticity of the object to be identified S (especially special ink) can be improved. Therefore, it is possible to further improve the identification accuracy of the banknote BN.

[0067] In general inks, such as infrared-absorbing ink and infrared-nonabsorbing ink, there is almost no difference in reflectance in the infrared region. In the space of output data related to infrared light, each output is a vector (1, 1, 1) passing through the origin T distributed in the direction. On the other hand, special ink is not like this. Therefore, the product of output data related to light of a plurality of wavelengths is more easily affected by general inks than by special inks, contributing to an improvement in the degree of separation between special inks and general inks.

[0068] Note that the "light of a plurality of wavelengths" is light having mutually different wavelength bands and includes at least light of a first wavelength and light of a second wavelength. For example, it may be light of two wavelengths, that is, light of a first wavelength and light of a second wavelength, or light of three wavelengths, that is, light of a first wavelength, light of a second wavelength, and light of a third wavelength. The light of a plurality of wavelengths may be, for example, light having mutually different colors in the case of visible light, or light in which only a part of the wavelength bands overlaps or light in which the wavelength bands do not overlap with each other in the case of infrared light and ultraviolet light.

[0069] Further, the "first data (second data) related to light of multiple wavelengths" is the first data (second data) based on the data respectively output when the light receiving unit 13a receives light of each wavelength, and includes the first data (second data) related to light of the first wavelength to the first data (second data) related to light of the Nth (N is an integer of 2 or more) wavelength.

[0070] When using light of two wavelengths, in the correction process, the control unit 20a may generate third data related to light of the first wavelength (hereinafter referred to as the third data of λ1), which is obtained by correcting the first data related to light of the first wavelength (hereinafter referred to as the first data of λ1) with the second data related to light of the first wavelength (hereinafter referred to as the second data of λ1). Also, the control unit 20a may generate third data related to light of the second wavelength (hereinafter referred to as the third data of λ2), which is obtained by correcting the first data related to light of the second wavelength (hereinafter referred to as the first data of λ2) with the second data related to light of the second wavelength (hereinafter referred to as the second data of λ2). When using light of three wavelengths, in the correction process, the control unit 20a may further generate third data related to light of the third wavelength (hereinafter referred to as the third data of λ3), which is obtained by correcting the first data related to light of the third wavelength (hereinafter referred to as the first data of λ3) with the second data related to light of the third wavelength (hereinafter referred to as the second data of λ1).

[0071] Also, when using light of two wavelengths, in the multiplication process, the control unit 20a may calculate, as the first multiplication data, data obtained by multiplying the first data of λ1 by the first data of λ2 (hereinafter referred to as the first data of λ1×λ2), and may calculate, as the second multiplication data, data obtained by multiplying the second data of λ1 by the second data of λ2 (hereinafter referred to as the second data of λ1×λ2). In the correction process, the control unit 20a may generate, as the fourth data, data obtained by correcting the first data of λ1×λ2 with the second data of λ1×λ2 (hereinafter referred to as the fourth data of λ1×λ2).

[0072] When using light of three wavelengths, in the multiplication process, the control unit 20a may further calculate, as the first multiplication data, data obtained by multiplying the first data of λ1 by the first data of λ3 (hereinafter referred to as the first data of λ1×λ3) and data obtained by multiplying the first data of λ2 by the first data of λ3 (hereinafter referred to as the first data of λ2×λ3). As the second multiplication data, the control unit 20a may further calculate data obtained by multiplying the second data of λ1 by the second data of λ3 (hereinafter referred to as the second data of λ1×λ3) and data obtained by multiplying the second data of λ2 by the second data of λ3 (hereinafter referred to as the second data of λ2×λ3). In the correction process, as the fourth data, the control unit 20a may further generate data obtained by correcting the first data of λ1×λ3 with the second data of λ1×λ3 (hereinafter referred to as the fourth data of λ1×λ3) and data obtained by correcting the first data of λ2×λ3 with the second data of λ2×λ3 (hereinafter referred to as the fourth data of λ2×λ3).

[0073] When using light of two wavelengths, the first multiplication data may be data obtained by multiplying each output value (pixel value) of the first data related to the light of the first wavelength by each output value (pixel value) of the second data related to the light of the second wavelength (however, the output values related to the same point in the XY plane are multiplied). Similarly, when using light of three wavelengths, the output values (pixel values) may be multiplied (however, the output values related to the same point in the XY plane).

[0074] When using light of two wavelengths, the second multiplication data may be data obtained by multiplying the representative value of the second data related to the light of the first wavelength by the representative value of the second data related to the light of the second wavelength (however, the same type of representative values (for example, average values) are multiplied). Similarly, when using light of three wavelengths, the representative values may be multiplied (however, the same type of representative values).

[0075] When using light of two wavelengths, in the identification process, the control unit 20a may identify the banknote BN based on the third data of λ1 and the third data of λ2 (two-dimensional feature amounts), or may identify the banknote BN based on the third data of λ1, the third data of λ2, and the fourth data of λ1×λ2 (three-dimensional feature amounts).

[0076] When using light of three wavelengths, in the identification process, the control unit 20a may identify the banknote BN based on the third data of λ1, the third data of λ2, and the third data of λ3 (three-dimensional feature amounts), or may identify the banknote BN based on the third data of λ1, the third data of λ2, the third data of λ3, the fourth data of λ1×λ2, the fourth data of λ1×λ3, and the fourth data of λ2×λ3 (six-dimensional feature amounts).

[0077] When using light of a plurality of wavelengths as described above, during the period when the light source 11a irradiates light of a plurality of wavelengths, the light receiving unit 13a may receive the light of a plurality of wavelengths reflected by the banknote BN. At this time, the light receiving unit 13a can function as a sensor having sensitivity at least in the wavelength band of the light irradiated from the light source 11a. The light receiving unit 13a may output, for each wavelength, an electrical signal corresponding to the amount of received light as output data. More specifically, the light receiving unit 13a may include a light receiving element, the light receiving element may receive light and convert it into an electrical signal corresponding to the incident light amount, and the light receiving unit 13a may output the electrical signal for each wavelength.

[0078] Also, when using light of a plurality of wavelengths, the light of each wavelength irradiated by the light source 11a may be light in a wavelength band including the peak wavelength and wavelengths in its vicinity, and the lights of a plurality of wavelengths irradiated by the light source 11a may have different peak wavelengths from each other. Further, the light source 11a may include a plurality of light emitting elements 17a having different peak wavelengths from each other. For example, the light source 11a may irradiate infrared light of a plurality of wavelengths having different peak wavelengths from each other, or may include a plurality of light emitting elements 17a that respectively irradiate infrared light of a plurality of wavelengths having different peak wavelengths from each other. Also, the light receiving unit 13a may receive infrared light of a plurality of wavelengths irradiated from the light source 11a and reflected by the banknote BN. Similarly, the first data and the second data may each be data related to infrared light of a plurality of wavelengths. Furthermore, various data related to light of a plurality of wavelengths processed by the control unit 20a may be data related to infrared light of a plurality of wavelengths.

[0079] For example, the light source 11a may irradiate infrared light of a plurality of wavelengths (first and second infrared lights, or first to third infrared lights) with mutually different peak wavelengths, and the light receiving unit 13a may receive infrared light of a plurality of wavelengths (first and second infrared lights, or first to third infrared lights) that is irradiated from the light source 11a and reflected by the banknote BN. The first data and the second data may each include data related to infrared light of a plurality of wavelengths (first and second infrared lights, or first to third infrared lights). Various data related to light of a plurality of wavelengths processed by the control unit 20a may be data related to infrared light of a plurality of wavelengths (for example, first and second infrared lights, or first to third infrared lights).

[0080] The first and second infrared lights may be any combination of two of infrared light having a peak wavelength in the wavelength band of 770 to 830 nm, infrared light having a peak wavelength in the wavelength band of 840 to 900 nm, and infrared light having a peak wavelength in the wavelength band of 910 to 970 nm. Note that the wavelengths of the first and second infrared lights may be either larger.

[0081] Similarly, the first to third infrared lights may be a combination of infrared light having a peak wavelength in the wavelength band of 770 to 830 nm, infrared light having a peak wavelength in the wavelength band of 840 to 900 nm, and infrared light having a peak wavelength in the wavelength band of 910 to 970 nm. Note that the magnitude relationship of the wavelengths in the first to third infrared lights is not particularly limited.

[0082] As shown in FIG. 4, the light source 11a may irradiate the banknote BN with linear light in the main scanning direction (Y direction), the light receiving unit 13a may receive the linear light in the main scanning direction (Y direction) coming from the banknote BN, and the control unit 20a may use, as the second data, the region ROI including the object S to be identified AOutput data corresponding to the position in the main scanning direction (Y direction) of (see FIG. 2) may be used. When the position in the main scanning direction changes, the length of the light guide 15a (for example, a light guide made of an acrylic resin) of the light source 11a through which light passes also fluctuates, so the output data also fluctuates in the main scanning direction, and particularly the fluctuation becomes more prominent at the center in the main scanning direction (the central portion of the light guide 15a). However, according to the above configuration, as the second data for correction, the region ROI including the object S to be identified A uses output data corresponding to the position in the main scanning direction of, so it is possible to reduce the variation in the output data caused by the position in the main scanning direction. Also, variation in the characteristics of the light receiving element may occur depending on the position in the main scanning direction, but according to the above configuration, such variation in the characteristics of the light receiving element can also be reduced. Therefore, it is possible to further improve the identification accuracy of the banknote BN.

[0083] In this case, the region ROI including the object S to be identified A and the region ROI that does not include the object S to be identified B may be set at the same location (same range) of the banknote BN in the main scanning direction (Y direction), and both the first data and the second data may be data in the same channel range included in the reflection image data of the entire banknote BN. For example, the first data and the second data may be data from the n-th channel to the m-th channel (where n and m are natural numbers satisfying n < m) among the reflection image data of the entire banknote BN.

[0084] Note that the ranges in the sub-scanning direction (X direction) of the first data and the second data, that is, the number of lines, can be set appropriately respectively, and they may be the same or different from each other.

[0085] In the identification process, the control unit 20a may apply an identification function to each pixel and determine whether each pixel has special ink. That is, various data described above used in the identification process may be input into the identification function as feature quantities (for example, two-dimensional, three-dimensional, or six-dimensional feature quantities), and based on the output of the identification function, it may be determined whether the identification object S is provided on the banknote BN. Thereby, the identification process by the control unit 20a can be speeded up.

[0086] Here, the identification function can be generated by supervised machine learning. Specifically, for example, discriminant analysis, support vector machine, neural network, etc. can be used. As the training data, for example, image data including the ink portion of a banknote printed with special ink and its background portion (peripheral portion) can be used. Here, the special ink portion and the background portion, that is, the non-special ink portion, can be used as class labels. For example, in the case of negative ink, image data related to infrared light having a peak wavelength in the wavelength band of 910 to 970 nm is binarized (separated into the ink portion and the background portion), and the result can be directly used as the class label for each pixel. In the case of positive ink, image data related to infrared light having a peak wavelength in the wavelength band of 770 to 830 nm is binarized (separated into the ink portion and the background portion), and the result can be directly used as the class label for each pixel. In any case, Otsu's binarization may be performed as the binarization process.

[0087] More specifically, for example, when using light of three wavelengths, the control unit 20a may determine whether the identification object S is provided on the banknote BN based on the following formulas (1) to (6) in the identification process. Here, formula (3’) may be used instead of formula (3).

[0088]

Equation

[0089] In formulas (1) and (2), L is a threshold value. In formula (1), if λ is greater than or equal to L, it is determined that the identification object S is provided on the banknote BN; if λ is less than L, it is determined that the identification object S is not provided on the banknote BN.

[0090] In formula (2), λ is an evaluation value, and the sum of P A in the region ROI j including the identification object S is calculated.

[0091] In each formula, P j is the result of the identification function f(x), and the sum of the pixels determined to have special ink (formula (3)), or the sum of the classification scores that are the output of the identification function f(x) (formula (3')) can be used. In formulas (3) and (3'), c is the threshold value of the classification score.

[0092] The identification function f(x) is represented by formula (4), and a three-dimensional feature amount is input as shown in formula (6). In formula (5), ω (w 0 ~w 3 ) is the coefficient vector (weight) obtained as a result of machine learning, and φ(x j ) represented by formula (6) is the feature amount vector of the target pixel j (j is the number indicating the target pixel). In formula (6), x 1j , x 2j and x 3j are the pixel values related to the first, second, and third lights (which may be the first, second, and third infrared lights) in the target pixel j respectively, and μ 1 , μ 2 and μ 3 are the representative values of the output data related to the first, second, and third lights (which may be the first, second, and third infrared lights) in the region ROI B not including the identification object S respectively. Here, the identification function f(x) is represented by a linear discriminant formula.

[0093] Note that in formula (6), x 1j / μ 1 , x 2j / μ 2 and x 3j / μ3 respectively correspond to the third data of λ1, the third data of λ2, and the third data of λ3 described above.

[0094] Also, when using light of three wavelengths, the control unit 20a may determine whether or not the identification object S is provided on the banknote BN based on the following formulas (11) to (16) in the identification process. Here, formula (13’) may be used instead of formula (13).

[0095]

Equation

[0096] In formulas (11) and (12), L is a threshold value. In formula (11), if λ is greater than or equal to L, it is determined that the identification object S is provided on the banknote BN, and if λ is less than L, it is determined that the identification object S is not provided on the banknote BN.

[0097] In formula (12), λ is an evaluation value, and the sum of P A in the region ROI j including the identification object S is calculated.

[0098] In each formula, P j is the result of the identification function f(x), and the sum of the pixels determined to have special ink (formula (13)), or the sum of the classification scores that are the output of the identification function f(x) (formula (13’)) can be used. In formulas (13) and (13’), c is a threshold value of the classification score.

[0099] The identification function f(x) is represented by formula (14), and a six-dimensional feature amount is input as shown in formula (16). In formula (15), ω (w 0 ~w 6 ) is a coefficient vector (weight) obtained as a result of machine learning, and φ(x j ) represented by formula (16) is a feature amount vector of the target pixel j (j is a number indicating the target pixel). In formula (16), x 1j , x 2j and x 3jare the pixel values related to the first, second, and third lights (which may be the first, second, and third infrared lights) in the target pixel, respectively, and μ j are the representative values of the output data related to the first, second, and third lights (which may be the first, second, and third infrared lights) in the region ROI 1 without the identification target object S. Here, the identification function f(x) is expressed by an equation obtained by expanding a linear discriminant formula into a non-linear model. 2 and μ 3 are the representative values of the output data related to the first, second, and third lights (which may be the first, second, and third infrared lights) in the region ROI B without the identification target object S. Here, the identification function f(x) is expressed by an equation obtained by expanding a linear discriminant formula into a non-linear model.

[0100] Note that in Equation (16), x 1j / μ 1 , x 2j / μ 2 , x 3j / μ 3 , x 1j x 2j / μ 1 μ 2 , x 1j x 3j / μ 1 μ 3 and x 2j x 3j / μ 2 μ 3 correspond to the third data of λ1, the third data of λ2, the third data of λ3, the fourth data of λ1×λ2, the fourth data of λ1×λ3, and the fourth data of λ2×λ3 described above, respectively.

[0101] The control unit 20a may perform multiplication processing simultaneously with correction processing within the same calculation process, as described in the above Equations (6) and (16), for example.

[0102] The control unit 20a may identify the authenticity of the banknote BN in the identification process. For example, when it is determined that the identification target object S is provided on the banknote BN, the banknote BN may be determined as a genuine note, and when it is determined that the identification target object S is not provided on the banknote BN, the banknote BN may be determined as a counterfeit note.

[0103] Next, with reference to FIG. 7, the operation of the paper sheet discrimination apparatus 1a according to the present embodiment will be described. FIG. 7 is a flowchart for explaining an example of the operation of the paper sheet discrimination apparatus according to the present embodiment.

[0104] As shown in FIG. 7, first, the control unit 20a acquires output data from the light receiving unit 13a that has received (for example, reflected) light irradiated from the light source 11a and arriving from the banknote BN (step S11).

[0105] Next, the control unit 20a obtains first data that is output data of the light receiving unit 13a corresponding to the region ROI A including the object to be discriminated S, and second data that is output data of the light receiving unit 13a corresponding to the region ROI B not including the object to be discriminated S (step S12).

[0106] Next, the control unit 20a performs a correction process for generating third data obtained by correcting the first data with the second data (step S13). In step S13, the control unit 20a may perform a multiplication process together with the correction process.

[0107] Thereafter, the control unit 20a performs a discrimination process for discriminating the banknote BN based on the third data (step S14), and the operation of the paper sheet discrimination apparatus 1a ends.

[0108] (Embodiment 2) With reference to FIG. 8, the configuration of the paper sheet discrimination apparatus according to the present embodiment will be described. FIG. 8 is a schematic diagram for explaining an example of the configuration of the paper sheet discrimination apparatus according to the present embodiment, and is a view of the banknote conveyance path seen from the side. As shown in FIG. 8, the paper sheet discrimination apparatus 1b according to the present embodiment includes a light source 11b that irradiates a banknote BN with light of a plurality of wavelengths, a light receiving unit 13b that receives light of a plurality of wavelengths arriving from the banknote BN, and a control unit 20b that acquires output data related to the light of a plurality of wavelengths of the light receiving unit 13b, and can be mounted and used, for example, in a paper sheet processing apparatus that processes banknotes. The banknote BN to be discriminated may be conveyed in the X direction within the XY plane.

[0109] FIG. 9 is a schematic plan view showing an example of a banknote to be identified in the present embodiment. As shown in FIG. 9, an object S to be identified (for example, printed) is provided on at least one main surface of a banknote BN to be identified in the present embodiment. On the main surface of the banknote BN, a rectangular region ROI including the object S to be identified is set. A is set.

[0110] The banknote BN to be identified may include, as the object S to be identified, at least one of an ink (negative ink) whose reflectance decreases as the wavelength increases in the infrared region and an ink (positive ink) whose reflectance increases as the wavelength increases in the infrared region, as shown in FIG. 3. According to the paper sheet identification device 1b, it is possible to accurately identify a banknote BN including such an ink.

[0111] The light source 11b irradiates the banknote BN with light of a plurality of wavelengths. The type (wavelength) of the light irradiated from the light source 11b is not particularly limited, and examples include visible light such as white light, red light, green light, and blue light, and infrared light.

[0112] Note that the "light of a plurality of wavelengths" is light having mutually different wavelength bands and includes at least light of a first wavelength and light of a second wavelength. For example, it may be light of two wavelengths, that is, light of a first wavelength and light of a second wavelength, or light of three wavelengths, that is, light of a first wavelength, light of a second wavelength, and light of a third wavelength. The light of a plurality of wavelengths may be, for example, light having mutually different colors in the case of visible light, and in the case of infrared light and ultraviolet light, light in which only a part of the wavelength bands overlaps or light in which the wavelength bands do not overlap.

[0113] The light-receiving unit 13b receives light of a plurality of wavelengths arriving from the banknote BN. That is, it can function as an optical sensor. The light-receiving unit 13b may receive light of a plurality of wavelengths that is irradiated from the light source 11b and reflected by the banknote BN. That is, while the light source 11b irradiates light of a plurality of wavelengths, the light-receiving unit 13b may receive the light of a plurality of wavelengths that is reflected by the banknote BN. At this time, the light-receiving unit 13b can function as a sensor having sensitivity at least in the wavelength band of the light irradiated from the light source 11b. The light-receiving unit 13b may output, for each wavelength, an electrical signal corresponding to the amount of received light as output data. More specifically, the light-receiving unit 13b may include a light-receiving element, the light-receiving element may receive light and convert it into an electrical signal corresponding to the incident light amount, and the light-receiving unit 13b may output the electrical signal for each wavelength.

[0114] FIG. 10 is a schematic diagram for explaining an example of the configuration of the paper sheet discrimination device according to the present embodiment, and is a view seen from an oblique direction. As shown in FIG. 10, the light source 11b and the light-receiving unit 13b may constitute an optical line sensor 14b extending in the Y direction. In this case, the Y direction corresponds to the main scanning direction of the optical line sensor 14b, and the X direction corresponds to the sub-scanning direction of the optical line sensor 14b. The light source 11b may irradiate light linearly extending in the Y direction. The light-receiving unit 13b may include a plurality of light-receiving elements (light-receiving pixels) arranged in a row in the Y direction, and may constitute a linear image sensor.

[0115] Further, the lengths of the light source 11b and the light receiving unit 13b in the Y direction (main scanning direction) may be longer than the length of the banknote BN in the Y direction. Then, the light source 11b may linearly irradiate light over the entire Y direction of the banknote BN, and the light receiving unit 13b may receive the light reflected over the entire Y direction of the banknote BN. That is, the light receiving unit 13b may output an electrical signal corresponding to the incident light amount on a plurality of channels corresponding to a plurality of light receiving elements (positions in the Y direction). The channels are numbers assigned to the light receiving elements in order in the Y direction. At this time, the light receiving unit 13b outputs, as output data, line data which is data related to the light simultaneously received on each channel. While the banknote BN is being conveyed in the X direction (sub-scanning direction), by repeating the irradiation of light by this light source 11b and the reception of light by the light receiving unit 13b, data related to the reflected light of the entire banknote BN may be acquired.

[0116] FIG. 11 is a schematic diagram for explaining an example of the configuration of the sheet-like object discrimination device according to the present embodiment, and is a view of the banknote conveyance path as seen from above. As shown in FIG. 11, the light source 11b may include a light guide 15b and light emitting elements 17b respectively facing two end faces 15ba of the light guide 15b, and may irradiate the banknote BN with light through the light guide 15b.

[0117] The light guide 15b is a transparent rod-shaped optical member, which guides the light from the light emitting element 17b and irradiates the banknote BN, which is the irradiation target, with linear light, and linearizes the light emitted from the light emitting element 17b.

[0118] The light guide 15b may be made of an acrylic resin.

[0119] The light emitting element 17b is an element that emits light toward the opposing end face 15ba. For example, an LED can be used. Note that a plurality of light emitting elements 17b may be provided with respect to the corresponding end face. Further, the light emitting element 17b may be arranged to face only one of the two end faces 15ba.

[0120] The light source 11b may irradiate the banknote BN with infrared light including light having a wavelength of 850 nm or more and 950 nm or less. Thereby, it is possible to highly accurately identify the banknote BN including the ink (for example, special ink) whose reflectance varies in the infrared region around 900 nm as the object S to be identified.

[0121] Each light-receiving pixel of the light-receiving unit 13b may include a light-receiving element having sensitivity over the entire region of a plurality of different wavelength bands, or may include a plurality of types of light-receiving elements that selectively receive light in different wavelength bands. In the former case, the light source 11b may irradiate the banknote BN with light of a plurality of wavelengths in sequence, and the light-receiving unit 13b may receive the light of the corresponding wavelength in accordance with the irradiation timing of the light of each wavelength. In the latter case, the light source 11b may irradiate the banknote BN with light of a plurality of wavelengths simultaneously, and the light-receiving unit 13b may receive the light of the plurality of wavelengths with the plurality of types of light-receiving elements respectively.

[0122] The control unit 20b performs a process of acquiring output data related to light of a plurality of wavelengths of the light-receiving unit 13b. That is, data for each wavelength corresponding to the amount of light received by the light-receiving unit 13b is acquired. Note that the "output data related to light of a plurality of wavelengths" is data respectively output when the light-receiving unit 13b receives light of each wavelength, and includes the output data related to the light of the first wavelength to the output data related to the light of the Nth (N is an integer of 2 or more) wavelength. The output data of the light-receiving unit 13b acquired by the control unit 20b may be digitized. The control unit 20b may acquire image data of the entire banknote BN as the output data of the light-receiving unit 13b.

[0123] The image data of the entire banknote BN is data (two-dimensional data) obtained by imaging the entire banknote BN, and as shown in FIG. 6, may be composed of a plurality of pixels Pix arranged in a matrix in the Y direction (main scanning direction) and the X direction (sub-scanning direction). The address of each pixel Pix may be specified by the channel of the light-receiving unit 13b corresponding to the position in the Y direction and the line corresponding to the position in the X direction. The line is a number sequentially assigned to the line data sequentially output by the light-receiving unit 13b.

[0124] The output data of the light receiving unit 13b acquired by the control unit 20b may include data related to the light reflected by the banknote BN. Thereby, it is possible to highly accurately identify a banknote BN including an ink (for example, a special ink) having characteristics in reflectance as an identification object S.

[0125] Further, the control unit 20b may acquire, as the output data of the light receiving unit 13b, image data related to the reflected light of the entire banknote BN, that is, reflected image data of the entire banknote BN.

[0126] Note that the resolution of the output data acquired by the control unit 20b may be the same as or different from the resolution of the output data of the light receiving unit 13b, and may be low, for example, in the Y direction (main scanning direction) and the X direction (sub-scanning direction).

[0127] The control unit 20b may control each part of the paper sheet discrimination device 1b, and may be configured by, for example, a program for realizing various processes including a paper sheet discrimination program, a CPU that executes the program, and various hardware (for example, FPGA) controlled by the CPU.

[0128] The control unit 20b performs a process (hereinafter sometimes referred to as a multiplication process) of calculating multiplication data that is data obtained by multiplying data related to light of a first wavelength and a second wavelength among the output data related to light of a plurality of wavelengths acquired (hereinafter sometimes referred to as output data), and performs a process (hereinafter sometimes referred to as an identification process) of identifying the banknote BN based on the output data related to light of a plurality of wavelengths and the multiplication data. Thereby, the separation performance of the authenticity of the identification object S (particularly special ink) can be improved. Therefore, it is possible to improve the identification accuracy of the banknote BN.

[0129] In general inks, such as infrared absorbing ink and infrared non-absorbing ink, there is almost no difference in reflectance in the infrared region, and in the space of the output data related to infrared light, each output is a vector (1, 1, 1) passing through the origin TThey are distributed in the [direction]. On the other hand, the special ink is not. Therefore, the product of the output data related to light of multiple wavelengths is more easily affected by the ink that is more general than the special ink, contributing to an improvement in the separation degree between the special ink and the general ink.

[0130] The output data related to light of multiple wavelengths acquired by the control unit 20b from the light receiving unit 13b may be data corresponding to the region ROI A including the object S to be identified. That is, the output data related to light of multiple wavelengths may all be part of the reflection image data of the entire banknote BN, that is, the reflection image data of a part of the banknote BN. The region ROI A may be preset according to the denomination of the banknote BN, and the control unit 20b may, based on the position information of the region ROI A set for each denomination, extract from the output data of the light receiving unit 13b (for example, the reflection image data of the entire banknote BN) the data corresponding to the region ROI A including the object S to be identified.

[0131] When using light of two wavelengths, the control unit 20b may calculate, in the multiplication process, as multiplication data, the data obtained by multiplying the output data related to light of the first wavelength (hereinafter, the output data of λ1) by the output data related to light of the second wavelength (hereinafter, the output data of λ2) (hereinafter, the output data of λ1×λ2). In the identification process, the control unit 20b may identify the banknote BN based on the output data of λ1, the output data of λ2, and the output data of λ1×λ2 (three-dimensional feature amounts).

[0132] When using light of three wavelengths, in the multiplication process, the control unit 20b may further calculate, as multiplication data, data obtained by multiplying the output data of λ1 by the output data related to the light of the third wavelength (hereinafter referred to as the output data of λ3) (hereinafter referred to as the output data of λ1×λ3), and data obtained by multiplying the output data of λ2 by the output data of λ3 (hereinafter referred to as the output data of λ2×λ3). In the identification process, the control unit 20b may identify the banknote BN based on the output data of λ1, the output data of λ2, the output data of λ3, the output data of λ1×λ2, the output data of λ1×λ3, and the output data of λ2×λ3 (six-dimensional feature amounts).

[0133] When using light of two wavelengths, the multiplication data may be data obtained by multiplying each output value (pixel value) of the output data related to the light of the first wavelength by each output value (pixel value) of the output data related to the light of the second wavelength (however, those obtained by multiplying the output values related to the same point within the XY plane). Similarly, when using light of three wavelengths, the output values (pixel values) may be multiplied (however, the output values related to the same point within the XY plane).

[0134] In this embodiment, the light of each wavelength irradiated by the light source 11b may be light in a wavelength band including the peak wavelength and wavelengths in its vicinity, and the lights of a plurality of wavelengths irradiated by the light source 11b may have different peak wavelengths from each other. Further, the light source 11b may include a plurality of light-emitting elements 17b having different peak wavelengths from each other. For example, the light source 11b may irradiate infrared light of a plurality of wavelengths having different peak wavelengths from each other, or may include a plurality of light-emitting elements 17b that respectively irradiate infrared light of a plurality of wavelengths having different peak wavelengths from each other. Further, the light-receiving unit 13b may receive infrared light of a plurality of wavelengths irradiated from the light source 11b and reflected by the banknote BN. Similarly, the output data related to the light of a plurality of wavelengths acquired by the control unit 20b from the light-receiving unit 13b may each be data related to infrared light of a plurality of wavelengths. Furthermore, various data related to the light of a plurality of wavelengths processed by the control unit 20b may be data related to infrared light of a plurality of wavelengths.

[0135] For example, the light source 11b may irradiate infrared light of a plurality of wavelengths (first and second infrared lights, or first to third infrared lights) with mutually different peak wavelengths, and the light receiving unit 13b may receive infrared light of a plurality of wavelengths (first and second infrared lights, or first to third infrared lights) that is irradiated from the light source 11b and reflected by the banknote BN. The control unit 20b may acquire data related to infrared light of a plurality of wavelengths (first and second infrared lights, or first to third infrared lights) from the light receiving unit 13b. Various data related to light of a plurality of wavelengths processed by the control unit 20b may be data related to infrared light of a plurality of wavelengths (for example, first and second infrared lights, or first to third infrared lights).

[0136] The first and second infrared lights may be any combination of two of infrared light having a peak wavelength in the wavelength band of 770 to 830 nm, infrared light having a peak wavelength in the wavelength band of 840 to 900 nm, and infrared light having a peak wavelength in the wavelength band of 910 to 970 nm. Note that the wavelengths of the first and second infrared lights may be either larger.

[0137] Similarly, the first to third infrared lights may be a combination of infrared light having a peak wavelength in the wavelength band of 770 to 830 nm, infrared light having a peak wavelength in the wavelength band of 840 to 900 nm, and infrared light having a peak wavelength in the wavelength band of 910 to 970 nm. Note that the magnitude relationship of the wavelengths in the first to third infrared lights is not particularly limited.

[0138] In the identification process, the control unit 20b may apply an identification function to each pixel and determine whether each pixel has special ink. That is, various data described above used in the identification process may be input as feature amounts (for example, three-dimensional or six-dimensional feature amounts) to the identification function, and based on the output of the identification function, it may be determined whether the identification object S is provided on the banknote BN. Thereby, the identification process by the control unit 20b can be speeded up.

[0139] Here, the discrimination function can be generated by supervised machine learning. Specifically, for example, discriminant analysis, support vector machines, neural networks, etc. can be used. As the training data, for example, image data including the ink portion of a banknote printed with special ink and the background portion (peripheral portion) thereof can be used. Here, feature amounts (for example, 3D or 6D feature amounts) related to the above various data can be used as inputs, and the special ink portion and the background portion, that is, the non-special ink portion, can be used as class labels. For example, in the case of negative ink, image data related to infrared light having a peak wavelength in the wavelength band of 910 to 970 nm is binarized (separated into the ink portion and the background portion), and the result can be directly used as the class label for each pixel. In the case of positive ink, image data related to infrared light having a peak wavelength in the wavelength band of 770 to 830 nm is binarized (separated into the ink portion and the background portion), and the result can be directly used as the class label for each pixel. In any case, Otsu's binarization may be performed as the binarization process.

[0140] More specifically, for example, when using three-wavelength light, the control unit 20b may determine whether or not the identification object S is provided on the banknote BN in the identification process based on the following formulas (21) to (26). Here, formula (23') may be used instead of formula (23).

[0141] [Number]

[0142] In formulas (21) and (22), L is a threshold value. In formula (21), if λ is greater than or equal to L, it is determined that the identification object S is provided on the banknote BN, and if λ is less than L, it is determined that the identification object S is not provided on the banknote BN.

[0143] In formula (22), λ is an evaluation value, and the sum of P A inside the region ROI j including the identification object S is calculated.

[0144] In each case, P j is the result of the discrimination function f(x), and the sum of the pixels determined to have the special ink (Equation (23)), or the sum of the classification scores that are the output of the discrimination function f(x) (Equation (23')) can be used. In Equations (23) and (23'), c is the threshold of the classification score.

[0145] The discrimination function f(x) is represented by Equation (24), and a six-dimensional feature amount is input as shown in Equation (26). In Equation (25), ω (w 0 ~w 6 ) is the coefficient vector obtained as a result of machine learning, and φ(x j ) represented by Equation (26) is the feature amount vector of the target pixel j (j is the number indicating the target pixel). In Equation (26), x 1j , x 2j and x 3j are the pixel values related to the first, second, and third lights (which may be the first, second, and third infrared lights) in the target pixel j , respectively. Here, the discrimination function f(x) is represented by an equation obtained by expanding a linear discriminant formula into a non-linear model.

[0146] Note that in Equation (26), x 1j , x 2j , x 3j , x 1j x 2j , x 1j x 3j and x 2j x 3j correspond to the output data of λ1, the output data of λ2, the output data of λ3, the output data of λ1×λ2, the output data of λ1×λ3, and the output data of λ2×λ3 described above, respectively.

[0147] The control unit 20b may discriminate the authenticity of the banknote BN in the discrimination process. For example, when it is determined that the discrimination object S is provided on the banknote BN, the banknote BN may be determined to be a genuine note, and when it is determined that the discrimination object S is not provided on the banknote BN, the banknote BN may be determined to be a counterfeit note.

[0148] Next, with reference to FIG. 12, the operation of the paper sheet discrimination device 1b according to the present embodiment will be described. FIG. 12 is a flowchart for explaining an example of the operation of the paper sheet discrimination device according to the present embodiment.

[0149] As shown in FIG. 12, first, the control unit 20b acquires output data from the light receiving unit 13b that has received light of a plurality of wavelengths irradiated from the light source 11b and arriving from the banknote BN (e.g., reflected light) (step S21).

[0150] Next, the control unit 20b performs multiplication to calculate multiplication data, which is data obtained by multiplying the data related to the light of the first wavelength and the second wavelength among the output data related to the light of the plurality of wavelengths that has been acquired (step S22).

[0151] When the data related to the light of the first wavelength and the second wavelength is data corresponding to the region ROI including the object to be discriminated S, before step S22, for the output data related to the light of each wavelength, from the data corresponding to the entire banknote BN (e.g., the reflected image data of the entire banknote BN), the data corresponding to the region ROI including the object to be discriminated S A (e.g., the reflected image data of the region ROI including the object to be discriminated S) may be extracted. A A A A

[0152] Thereafter, the control unit 20b performs discrimination processing to discriminate the banknote BN based on the output data related to the light of the plurality of wavelengths acquired from the light receiving unit 13b (which may be data corresponding to the region ROI including the object to be discriminated S) and the calculated multiplication data (step S23), and the operation of the paper sheet discrimination device 1b ends. A A

[0153] (Embodiment 3) Using FIG. 13, the configuration of a paper sheet processing apparatus in which the paper sheet discrimination apparatus according to the present embodiment can be mounted will be described. FIG. 13 is a perspective schematic view showing an external appearance of an example of a paper sheet processing apparatus in which the paper sheet discrimination apparatus according to the present embodiment can be mounted. The paper sheet processing apparatus in which the paper sheet discrimination apparatus according to the present embodiment is mounted may have, for example, the configuration shown in FIG. 13. The paper sheet processing apparatus 300 shown in FIG. 13 includes a banknote discrimination apparatus according to the present embodiment that performs discrimination processing of banknotes (not shown in FIG. 13), a hopper 301 on which a plurality of banknotes to be processed are placed in a stacked state, two reject units 302 from which rejected banknotes are discharged, an operation unit 303 for inputting an instruction from an operator, four stacking units 306a to 306d for classifying and stacking banknotes whose denomination, authenticity, and integrity have been discriminated within a housing 310, and a display unit 305 for displaying information such as the discrimination and counting results of banknotes and the stacking status of each of the stacking units 306a to 306d.

[0154] Next, using FIG. 14, the configuration of the paper sheet discrimination apparatus according to the present embodiment will be described. FIG. 14 is a block diagram for explaining an example of the configuration of the paper sheet discrimination apparatus according to the present embodiment. As shown in FIG. 14, the paper sheet discrimination apparatus 100 according to the present embodiment includes an optical line sensor 110, a control unit 120, a storage unit 130, and a transport unit 140.

[0155] The optical line sensor 110 detects various optical characteristics of the banknotes being transported, and may include a light source 111 and a light receiving unit 113 along the banknote transport path. The light source 111 irradiates the banknote with light of a plurality of wavelengths, and the light receiving unit 113 receives the light of a plurality of wavelengths that is irradiated from the light source 111 and reflected by the banknote, and outputs data related to the light of a plurality of wavelengths for each wavelength.

[0156] The control unit 120 is composed of a program (including a paper currency identification program) for realizing various processes stored in the storage unit 130, a CPU that executes the program, and various hardware (such as an FPGA) controlled by the CPU. The control unit 120 controls each part of the paper currency identification device 100 according to the program stored in the storage unit 130. Further, the control unit 120 has a function of performing processes such as acquisition processing of output data from the light receiving unit 113, correction processing of the acquired output data, multiplication processing of the acquired output data, and identification processing using various data that have been corrected and / or multiplied, according to the program stored in the storage unit 130. Since these processes by the control unit 120 are the same as the processes by the control unit 10a or 10b described in Embodiment 1 or 2, detailed description thereof is omitted.

[0157] As an identification process, the control unit 120 performs a process of identifying at least the denomination and authenticity of banknotes. According to the identification process using various data that have been corrected and / or multiplied described in Embodiment 1 or 2, the authenticity of banknotes can be identified. The control unit 120 may have a function of determining the integrity of banknotes. In that case, the control unit 120 has a function of determining whether to process banknotes as either genuine notes that can be reused in the market or damaged notes that are not suitable for market circulation, by detecting dirt, folds, tears, etc. of the banknotes.

[0158] The storage unit 130 is composed of a non-volatile and / or volatile storage device such as a semiconductor memory or a hard disk, and stores various programs and various data for controlling the paper currency identification device 100.

[0159] The conveyance unit 140 rotationally drives a plurality of rollers, belts, etc., and conveys banknotes one by one along a conveyance path provided in the paper currency identification device 100.

[0160] Next, the configuration of the optical line sensor 110 will be described with reference to FIG. 15. FIG. 15 is a schematic cross-sectional view for explaining an example of the configuration of the optical line sensor included in the paper sheet discrimination apparatus according to the present embodiment. As shown in FIG. 15, the optical line sensor 110 is composed of a contact image sensor facing the conveyance path 311 of the paper sheet processing apparatus, and constitutes a part of the conveyance path 311. The banknote BN is conveyed in the X direction within the conveyance path 311 (XY plane). The Y direction corresponds to the main scanning direction of the optical line sensor 110, and the X direction corresponds to the sub-scanning direction of the optical line sensor 110.

[0161] As shown in FIG. 15, the optical line sensor 110 includes two light sources 111 for reflection, a condenser lens 112, a light receiving unit 113, and a substrate 114. The light source 111 for reflection includes, for example, a light guide extending in the main scanning direction and a plurality of types of light emitting elements facing at least one end surface of the light guide and irradiating light of a plurality of wavelengths, and sequentially irradiates the main surface (hereinafter, referred to as surface A) on the light receiving unit 113 side of the banknote BN with light of a plurality of wavelengths. The condenser lens 112 is composed of, for example, a rod lens array in which a plurality of rod lenses are arranged in the main scanning direction, and condenses the light emitted from the light source 111 for reflection and reflected by the surface A of the banknote BN. The light receiving unit 113 includes, for example, a linear image sensor in which a plurality of light receiving elements (light receiving pixels) are arranged in the main scanning direction, and each light receiving element has sensitivity in the wavelength band of light of a plurality of wavelengths irradiated by the light source 111. For each light receiving element, for example, a silicon (Si) photodiode having sensitivity from at least the visible region to the infrared region with a wavelength of 1100 nm can be used. Each light receiving element is mounted on the substrate 114, receives the light condensed by the condenser lens 112, converts it into an electrical signal corresponding to the incident light amount, and outputs it to the substrate 114. Each light receiving element receives the light of the corresponding wavelength in accordance with the irradiation timing of the light of each wavelength by the light source 111. The substrate 114 includes, for example, a drive circuit for driving the light receiving elements and a signal processing circuit for processing and outputting signals from the light receiving elements. The substrate 114 amplifies the output signals of the light receiving unit 113 (each light receiving element), performs A / D conversion into digital data, and then outputs it.

[0162] The light source 111 irradiates light of a plurality of wavelengths, at least infrared light of a plurality of wavelengths, for example, first to third infrared lights having different peak wavelengths. The light source 111 may also irradiate visible light. As the visible light, for example, red light (R), green light (G), blue light (B), white light (W) including these three colors of light, etc. can be used.

[0163] In this embodiment, since the control unit 120 performs the same processing as the control unit 10a or 10b described in Embodiment 1 or 2, it is possible to improve the discrimination accuracy of banknotes as in Embodiment 1 or 2.

[0164] In the above embodiment, the case where the output data related to the light irradiated from the light source and reflected by the banknote is used for the correction processing and multiplication processing by the control unit has been described. However, the output data related to the light irradiated from the light source and transmitted through the banknote may be used for the correction processing and multiplication processing by the control unit.

[0165] As described above, the embodiments have been described with reference to the drawings. However, the present disclosure is not limited to the above embodiments. Also, the configurations of the respective embodiments may be appropriately combined or changed without departing from the gist of the present disclosure.

Industrial Applicability

[0166] As described above, the present disclosure is a technique useful for improving the discrimination accuracy of paper materials.

Explanation of Signs

[0167] 1a, 1b, 100: Paper material discrimination device 11a, 11b, 111: Light source 13a, 13b, 113: Light receiving unit 14a, 14b, 110: Optical line sensor 15a, 15b: Light guide 15aa, 15ba: End faces of the light guide 17a, 17b: Light emitting element 20a, 20b, 120: Control unit 112: Condensing lens 114: Substrate 130: Memory unit 140: Conveyor unit 300: Banknote processing device 301: Hopper 302: Reject unit 303: Operation unit 305: Display unit 306a~306d: Integration unit 311: Conveyor path BN: Banknote S: Object to be identified ROI A : Region including the object to be identified ROI B : Region not including the object to be identified Pix: Pixel

Claims

1. A paper sheet identification device for identifying a paper sheet on which an object to be identified is provided, comprising: a light source for irradiating the paper sheet with light; a light receiving unit for receiving the light coming from the paper sheet; a control unit for acquiring the output data of the light receiving unit, wherein the control unit acquires first data which is the output data of the light receiving unit corresponding to a region including the object to be identified on the paper sheet, and second data which is the output data of the light receiving unit corresponding to a region on the paper sheet that does not include the object to be identified, generates third data obtained by correcting the first data with the second data, inputs the third data as a feature amount into an identification function, and identifies the paper sheet based on the output of the identification function. A paper sheet identification device characterized by the above.

2. The light source irradiates the paper sheet with light of a plurality of wavelengths, the light receiving unit receives the light of a plurality of wavelengths coming from the paper sheet, the first data and the second data each include data related to the light of the plurality of wavelengths, the control unit generates third data related to the light of a plurality of wavelengths obtained by correcting the first data related to the light of the plurality of wavelengths with the second data related to the light of the same corresponding wavelength respectively, and identifies the paper sheet based on the third data related to the light of the plurality of wavelengths. The paper sheet identification device according to claim 1, characterized by the above.

3. The control unit calculates first multiplication data which is data obtained by multiplying the data related to the light of the first wavelength and the second wavelength among the first data related to the light of the plurality of wavelengths, and second multiplication data which is data obtained by multiplying the data related to the light of the first wavelength and the second wavelength among the second data related to the light of the plurality of wavelengths, generates fourth data obtained by correcting the first multiplication data with the second multiplication data, and identifies the paper sheet based on the third data related to the light of the plurality of wavelengths and the fourth data. The paper sheet identification device according to claim 2, characterized by the above.

4. The control unit uses, as the second data, a representative value of the output data of a region on the paper sheet that does not include the object to be identified. The paper sheet identification device according to any one of claims 1 to 3, characterized by the above.

5. The light source comprises a rod-shaped light guide made of an acrylic resin, and a light emitting element facing at least one of the two end faces of the light guide, and the light source irradiates the paper sheet with light through the light guide. The paper sheet identification device according to any one of claims 1 to 4, characterized by the above.

6. The light source irradiates the paper sheet with linearly shaped light in the main scanning direction. The light-receiving unit receives linearly-shaped light in the main scanning direction that has arrived from the paper sheets, The control unit uses, as the second data, the output data of the light-receiving unit corresponding to the region of the paper sheets where the identification target is not included, which is set in the same range as the position in the main scanning direction of the region including the identification target of the paper sheets. The paper sheet identification device according to any one of claims 1 to 5, characterized in that.

7. The light source irradiates the paper sheets with infrared light, The infrared light includes light having a wavelength of 850 nm or more and 950 nm or less. The paper sheet identification device according to any one of claims 1 to 6, characterized in that.

8. The light-receiving unit receives the light irradiated from the light source and reflected by the paper sheets, The output data includes data related to the light reflected by the paper sheets. The paper sheet identification device according to any one of claims 1 to 7, characterized in that.

9. The paper sheets to be identified include, as an identification target, at least one of an ink whose reflectance decreases as the wavelength increases in the infrared region and an ink whose reflectance increases as the wavelength increases in the infrared region. The paper sheet identification device according to any one of claims 1 to 8, characterized in that.

10. A paper sheet identification method for identifying paper sheets provided with an identification target, comprising: a step of acquiring output data from a light-receiving unit that has received light irradiated from a light source and arrived from the paper sheets; a step of acquiring first data that is the output data of the light-receiving unit corresponding to the region including the identification target of the paper sheets and second data that is the output data of the light-receiving unit corresponding to the region of the paper sheets where the identification target is not included; a step of generating third data obtained by correcting the first data with the second data; a step of inputting the third data as a feature amount into an identification function; a step of identifying the paper sheets based on the output of the identification function; The paper sheet identification method is characterized by comprising the above steps.

Images