JP6033608B2 - Bill fatigue discrimination device, bill processing device, and bill fatigue discrimination method - Google Patents

Description

  The present invention relates to a technique for detecting a fatigued banknote.

2. Description of the Related Art Various types of banknote processing apparatuses that can take in, store, and pay out banknotes of multiple denominations in various applications such as vending machines, game media lending machines at game halls, ticket vending machines, and money changers have been known. Yes. In this kind of banknote handling apparatus, various techniques for detecting a tired banknote have been proposed. For example, Patent Document 1 collects a passing sound generated when a bill passes through a conveyance path, and separates an electrical signal of the collected passing sound into a low-frequency component and a high-frequency component. A technique for determining the correctness of a banknote based on the number of pulses of a high-frequency component when there is a letter is disclosed.

  However, the technique of the cited document 1 requires frequency analysis, noise component extraction processing, and the like, and corresponding circuit parts are required to perform these processes, which increases the size and cost of the apparatus. Invite you.

Then, the technique of patent document 2 is proposed as a banknote fatigue discrimination apparatus which can discriminate | determine the fatigue state of a banknote, avoiding or suppressing the enlargement of an apparatus and the increase in cost.

In the banknote fatigue discrimination device described in Patent Document 2, the difference between data values of each sampling data and predetermined sampling data sampled before and after the sampling data is calculated as first and second amplitude differences, respectively. The fatigue state of the banknote is determined based on a distribution obtained by plotting a set of data composed of the first and second amplitude differences calculated for one sampling data in a predetermined two-dimensional coordinate system. Thus, the fatigue state of the banknote is determined.

In the bill fatigue discrimination device described in Patent Document 2, as in the technology described in Patent Document 1, the first process is not a process that causes an increase in the size and cost of the apparatus such as frequency analysis and noise component extraction processing. And calculating the second amplitude difference and determining the fatigue state of the banknote based on the distribution in a predetermined two-dimensional coordinate system of a set of data composed of these amplitude differences. The fatigue state of the banknote can be determined by processing.

JP-A-11-53602 JP 2010-286912 A

The bill fatigue discriminating device of the Patent Document 2, a bill on the basis of the distribution of the first and two-dimensional coordinate system with a predetermined set of data consisting of an amplitude difference calculation and these second amplitude difference However, in this discrimination method, there is a problem that it is difficult to improve the discrimination accuracy of the fatigue state of the banknote . In addition, the bill fatigue discrimination device is generally used in a place where the operating environment such as temperature and humidity is different, but there is a risk that the bill discrimination rate is greatly reduced due to a change in the operating environment. .

The present invention has been made in view of such circumstances, and it is possible to improve the determination accuracy of the fatigue state of the banknote and to improve the banknote fatigue that is improved against the influence of changes in the operating environment. It aims at providing a discriminating device, a bill processing device, and a bill fatigue discriminating method.

A bill fatigue discrimination device according to the present invention includes a sampling unit that samples a signal corresponding to a sound generated during conveyance of a bill as sampling data a plurality of times, a predetermined sampling that is sampled after each sampling data and the sampling data. A first amplitude difference that is a difference in data value with respect to the sampling data; a second amplitude difference that is a difference in data value between each of the sampling data and predetermined sampling data sampled two times after the sampling data; and An amplitude difference calculation unit that calculates a third amplitude difference that is a difference in data value between sampling data and predetermined sampling data sampled three times after the sampling data, and the first difference calculated for each of the sampling data Amplitude difference, second amplitude difference and third amplitude difference Based et constituted a set of data, plotted in three-dimensional orthogonal coordinate system of the three mutually orthogonal axes a 3-dimensional coordinate system predetermined in the distribution of the data plotted in the three-dimensional orthogonal coordinate system the bill fatigue discriminating apparatus and a discrimination unit for discriminating the state of fatigue of the paper money Te, the determination unit, a plurality of bills for demarcation including a bill that fatigue new bill prepared in advance, the The number of data plotted in each divided area obtained by dividing a predetermined three-dimensional orthogonal coordinate system into eight quadrants is detected for each divided area, and for each boundary setting banknote, the three-dimensional orthogonal coordinates The eight-dimensional data composed of the number of data in each of the eight quadrants is obtained, and among the obtained eight-dimensional data, the eight-dimensional data in the new banknote and the fatigued banknote Two pieces of 8-dimensional data having the closest distance to the 8-dimensional data are selected, and 8-dimensional data of an intermediate point located in the middle of the point corresponding to the selected 8-dimensional data is obtained. , A boundary passing through the intermediate point, and the distance between the point corresponding to the closest 8-dimensional data and the intermediate point can be secured between the point corresponding to the other 8-dimensional data and the boundary By setting the boundary as described above, the boundary between the eight-dimensional data in the new banknote and the eight-dimensional data in the fatigued banknote is set, and the predetermined three-dimensional orthogonality is determined for the banknote to be discriminated. The number of data plotted in each divided area obtained by dividing the coordinate system into eight quadrants is detected for each divided area, and for each banknote to be discriminated, the number of data in the eight quadrants of the three-dimensional orthogonal coordinates Or The eight-dimensional data composed of the above-mentioned eight-dimensional data obtained from the banknote to be discriminated is divided by the boundary, and the area containing the eight-dimensional data in the new banknote and the tired banknote It is characterized in that it is detected which of the regions including the eight-dimensional data belongs to and the fatigue state of the banknote is determined based on the detection result .

Moreover, the banknote fatigue determination method of the present invention includes a sampling step in which a sampling unit samples a signal corresponding to a sound generated during conveyance of banknotes as sampling data a plurality of times, and an amplitude difference calculation unit includes the sampling data A first amplitude difference, which is a difference in data value from predetermined sampling data sampled subsequent to the sampling data, a data value of each sampling data and predetermined sampling data sampled two times after the sampling data A calculation step for calculating a second amplitude difference that is a difference between the sampling data and a third amplitude difference that is a data value difference between each sampling data and predetermined sampling data sampled three times after the sampling data; Calculated for each sampling data It said first amplitude difference that, a set of data constituted by the second amplitude difference and the third amplitude difference, three-dimensional orthogonal coordinate system of the three mutually orthogonal axes a 3-dimensional coordinate system to a predetermined plotted on the a bill fatigue determination method and a determination step of determining the state of fatigue of the bill based on the distribution of the data plotted in three-dimensional orthogonal coordinate system, it said determining step, the determination unit The plurality of boundary setting banknotes including new banknotes prepared in advance and fatigued banknotes are plotted in respective divided areas obtained by dividing the predetermined three-dimensional orthogonal coordinate system into eight quadrants. The step of detecting the number of data for each divided area, and the discriminating unit, for each boundary setting banknote, 8D data composed of the number of data in 8 quadrants of the 3D orthogonal coordinates And the discriminating unit has the shortest distance between the obtained 8D data and the 8D data of the new banknote and the 8D data of the fatigued banknote. Selecting two dimensional data, the step of determining the eight-dimensional data of an intermediate point located in the middle of the point corresponding to the selected eight-dimensional data, and the determining unit A boundary that passes through a point, so that the distance between the point corresponding to the closest 8-dimensional data and the intermediate point can be secured between the point corresponding to the other 8-dimensional data and the boundary. By setting a boundary between the eight-dimensional data in the new banknote and the eight-dimensional data in the fatigued banknote, and the discrimination unit attaches to the banknote to be discriminated. Detecting the number of data plotted in each divided area obtained by dividing the predetermined three-dimensional orthogonal coordinate system into eight quadrants for each divided area; and For the target banknote, the step of obtaining eight-dimensional data composed of the number of data in the eight quadrants of the three-dimensional orthogonal coordinates, and the determination unit, the eight-dimensional data obtained from the determination target banknote is the Detecting which region of the new banknote divided by the boundary belongs to the region including the 8-dimensional data and the region including the 8-dimensional data of the fatigued banknote, and the detection result And determining the fatigue state of the banknote based on the above.

According to the banknote fatigue determination device and the banknote fatigue determination method described above, the difference in data value between each sampling data and predetermined sampling data sampled after one, two, and three after the sampling data, respectively. A set of data composed of the first, second and third amplitude differences calculated as the first, second and third amplitude differences and calculated for one sampling data is determined in a predetermined three-dimensional manner. By discriminating the fatigue state of the banknote based on the distribution obtained by plotting in a three-axis orthogonal coordinate system of three axes orthogonal to each other as a coordinate system , it is possible to improve the discrimination accuracy of the fatigue state of the banknote. And improved against the influence of changes in the operating environment.

Specifically, according to the banknote fatigue determination device and the banknote fatigue determination method, the fatigue state of the banknote is determined as follows. First, by using a plurality of boundary setting bill including a bill that fatigue new bill prepared in advance to set the boundary between the bill tired new bill. Specifically, for a plurality of boundary setting banknotes including new banknotes and fatigued banknotes , data plotted in respective divided areas obtained by dividing a predetermined three-dimensional orthogonal coordinate system into eight quadrants. The number is detected for each divided region, and for each boundary setting banknote , eight-dimensional data composed of the number of data in eight quadrants of three-dimensional orthogonal coordinates is obtained. Next, of the obtained 8D data, two 8D data having the closest distance between the 8D data of the new banknote and the 8D data of the fatigued banknote are selected. Then, determine the 8-dimensional data of the intermediate point is located between the points corresponding to the 8-dimensional data the selected. After that, a boundary passing through the intermediate point between the point corresponding to the closest 8D data and a point corresponding to the other 8D data is the distance between the intermediate point and the boundary. By setting the boundary so as to be secured, the boundary between the eight-dimensional data in the new banknote and the eight-dimensional data in the fatigued banknote is set.

Thereafter, the fatigue state of the banknote to be discriminated is discriminated using the set boundary. Specifically, for the banknotes to be discriminated, the number of data plotted in each divided area obtained by dividing the predetermined three-dimensional orthogonal coordinate system into eight areas is detected for each divided area, For the banknote to be discriminated, eight-dimensional data composed of the number of data in the eight quadrants of the three-dimensional orthogonal coordinates is obtained. After that, the region belonging to the region including the 8D data in the new banknote obtained by dividing the 8D data obtained from the banknote to be discriminated by the boundary and the region including the 8D data in the fatigued banknote belongs to any region. It is detected whether or not there is a fatigue state of the banknote based on the detection result. Thereby, the fatigue state of a banknote can be correctly discriminate | determined by simple process.

Bill handling apparatus of the present invention, the inlet for introducing the bill, and the bill fatigue discriminating apparatus for discriminating the fatigue state of the bills inserted from the inlet, on the basis of the determination result by the bill fatigue discriminating device, the banknote in the banknote processing apparatus including a housing part for sorting to accommodated by fatigue state, the bill fatigue discriminating apparatus, characterized in that the above-mentioned bill fatigue discriminating apparatus.

According to the present invention, it is possible in the case of mounting the function of determining the state of fatigue of the paper money to the paper money processing apparatus, to prevent the paper money processing apparatus or an increase in cost or size by mounting of the functional.

  ADVANTAGE OF THE INVENTION According to this invention, the discrimination | determination precision of the discrimination | determination precision of the fatigue state of a banknote can be improved, and it is improved with respect to the influence by the change of an operating environment.

It is a figure which shows the internal structure of one Embodiment of the banknote processing apparatus which concerns on this invention. It is a figure which shows the internal structure of one Embodiment of a banknote processing apparatus. It is a figure which shows the external appearance of a banknote processing apparatus. It is a figure which shows the external appearance of a banknote processing apparatus. It is a block diagram which shows the electrical structure of a banknote processing apparatus. It is explanatory drawing of the sampling operation | movement by a sampling part. It is explanatory drawing of the process by a plot part. It is explanatory drawing of the process by a plot part. It is a figure which shows an example of distribution of the plot point in the three-dimensional orthogonal coordinate system about all the sampling data. (A) shows the signal waveform of the output signal (sound signal) of the microphone that collected the sound emitted during the transportation of the old bill, and (b) collected the sound emitted during the transportation of the new bill. It is a figure which shows the signal waveform of the output signal (sound signal) of a microphone. It is a figure which shows the example of an aspect of distribution. It is an example of the table memorize | stored in the determination part. It is a flowchart which shows the flow of the banknote at the time of money_receiving | payment by a banknote processing apparatus. It is a flowchart which shows the flow of the preprocessing for boundary setting. It is a flowchart which shows the flow of the fatigue state identification process of a banknote. It is a figure which shows the experimental result when conducting the experiment which identifies the fatigue state of a banknote using the banknote processing apparatus which concerns on embodiment of this invention, (a)-(d) was thrown by the different throwing pattern, respectively. It is a figure which shows the discrimination result of the banknote based on the teacher data obtained with the banknote for a sample, (e) is a figure which shows the result which integrated the correct number of sheets in the experimental result of said (a)-(d). It is a figure which shows the experimental result when conducting the experiment which identifies the fatigue state of a banknote using the conventional banknote processing apparatus which is a comparative example of this invention, (a)-(d) is input by a different insertion pattern, respectively. It is a figure which shows the discrimination | determination result of the banknote based on the teacher data obtained by the done banknote for a sample, (e) is a figure which shows the result which integrated the correct number of sheets in the experimental result of said (a)-(d). is there. Is a diagram illustrating the correct answer rate in the comparative example shown in FIG. 15 correct answer rate and 16 according to the embodiment shown. 17 is a graph showing a correct answer rate according to the present embodiment shown in FIG. 15 and a correct answer rate according to a comparative example shown in FIG. 16. It is a figure which shows the experimental result when performing the experiment which identifies the fatigue condition of a banknote using the banknote processing apparatus which concerns on embodiment of this invention in the operation environment different from the experiment shown by FIG. It is a figure which shows the experimental result when it conducts when the experiment which identifies the fatigue state of a banknote using the conventional banknote processing apparatus which is a comparative example of this invention is performed in an operating environment different from the experiment shown by FIG. . It is a figure which shows the correct answer rate by this embodiment shown by FIG. 19, and the correct answer rate by the comparative example shown by FIG. FIG. 21 is a graph showing the accuracy rate according to the present embodiment shown in FIG. 19 and the accuracy rate according to the comparative example shown in FIG. 20.

  Hereinafter, the embodiment of the bill processing device concerning the present invention is described. 1 and 2 show the internal structure of an embodiment of the banknote handling apparatus according to the present invention, and FIGS. 3 and 4 show the external appearance of the banknote handling apparatus.

  As shown in FIGS. 1-4, the banknote processing apparatus 1 has the casing 1a formed in the box shape of the predetermined magnitude | size which can accommodate each unit 2,3,4A-4C mentioned later. The casing 1 a includes a box-shaped casing body 11 having an open front side (the right side in FIG. 1) and a door 12 that closes the front surface of the casing body 11. In the upper part of the door 12 on the front surface of the casing 1a, an opening 14 for inserting bills and an opening 15 for dispensing are disposed.

  Inside the casing 1a, a deposit / withdrawal unit 2 located at the uppermost part, a base unit 3 located at the lowermost part, and one or a plurality of stages (in the illustrated example) located between these units 2,3. Three-stage intermediate units 4A to 4C are provided. Each intermediate unit 4A to 4C and base unit 3 stores bills by denomination. For example, the upper unit 4A of the intermediate unit has a thousand yen bill, the middle unit 4B has a five thousand yen bill, and the lower unit. Ten thousand yen bills are stored in 4C, respectively, and bills with high fatigue (old bills described later) are stored in the base unit 3.

  Further, if necessary, an auxiliary unit 5 for increasing the bill storage space is arranged above any one or a plurality of intermediate unit, and in the example shown, the auxiliary unit 5 is arranged on the intermediate unit 4A. Yes.

  The deposit / withdrawal unit 2, the base unit 3, and the intermediate units 4A to 4C can be separated from each other and can be attached to and detached from the casing 1a. A supported portion 17 provided on one side of each of the units 2, 3, 4A to 4C is coupled to a slide guide 16 provided on one side of the casing 1a so as to be slidable in the front-rear direction. Thus, the units 2, 3, 4A to 4C are supported in a cantilever state in a state in which the units 2, 3, 4A to 4C can be individually pulled out forward with respect to the casing 1a.

  As shown in FIG. 4, a control board 100 and a power supply 105 including a main CPU board 101, a sub CPU board 102, and the like are provided on the side of the casing 1 a, and the control board 100 and the power supply 105 are connected to the control board 100 and the power supply 105. On the other hand, each unit 2, 3, 4A-4C is electrically connected via a detachable connector.

  The deposit / withdrawal unit 2 includes a bill introduction mechanism 21 for introducing a bill from the insertion port 20a into a frame 20 having an insertion port 20a and a payout port 20b, and a banknote derivation mechanism 23 for guiding the bill to the payout port 20b. And the transport mechanism 29 are accommodated in the upper part of the casing 1a in a state in which the insertion port 20a and the outlet 20b protrude from the openings 14 and 15 of the casing 1a.

  The bill introduction mechanism 21 has an identification device 22 for identifying the authenticity and denomination of the bill in the vicinity of the insertion slot 20a, and the banknote taken from the insertion port 20a via the identification device 22 is downward in the rear part of the unit 2. It has a bill introduction path 210 that guides it to face. Further, the bill introduction mechanism 21 is separated from the feed rollers 211 and 212 disposed on the upstream side and the downstream side of the bill introduction path 210, the guide roller 213 disposed in the middle of the bill introduction path 210, and the bill introduction path 210. The feed roller 214 is disposed at a different position. The rollers 211, 212, 213, and 214 are driven by a motor 215 via a transmission mechanism 216 such as a belt.

  The banknote derivation mechanism 23 includes a mechanism that pays out banknotes to the payout opening 20b in accordance with a payout command, and a mechanism that rejects illegal banknotes and the like, and a payout reject disposed at a height corresponding to the payout opening 20b. Feeding belt device 24, a temporary storage unit 25 composed of a space above the belt device 24, a guide device 26 for guiding banknotes to the temporary storage unit 25, and a temporary storage unit 25 on the belt device 24. And a reject chamber 28 formed in a space below the belt device 24. The front surface of the reject chamber 28 can be opened by a door 280, and a lock 281 is provided on the door 280.

  The base unit 3 includes a banknote storage unit 31, a transport mechanism 32 that transports banknotes behind the banknote storage unit 31, a transport motor 33 that is a drive source of the transport mechanism 32, a transport mechanism 32, and banknote storage. A take-out / feeding mechanism 34 that takes in and out banknotes from / to the unit 31, a banknote stacking mechanism 35 that stacks banknotes in the banknote storage unit 31, and a drive mechanism 36 that drives the banknote stacking mechanism 35 are provided. ing.

  The banknote storage unit 31 includes both side plates, a bottom plate, a front door 310 (see FIG. 2), and the like, and is formed to have a space in which banknotes can be stored in an accumulated state. The door 310 is provided with a lock 311. A bill support table 312 is provided in the bill storage unit 31 at a predetermined height position.

  Each of the intermediate units 4A to 4C has the same structure, and each includes a banknote storage unit 41 and a transport mechanism 42 that transports banknotes in the range from the upper end to the lower end of the unit behind the banknote storage unit 41. In addition, it has a take-out / feeding mechanism 44 for taking in and feeding out banknotes between the transport mechanism 42 and the banknote storage unit 41, and a banknote stacking mechanism 45 for stacking banknotes in the banknote storage unit 41.

  The banknote storage part 41 is composed of both side plates, a bottom plate, a door 410 with a lock 411 on the front side (see FIG. 2), and the like, like the banknote storage part 31 of the base unit 3.

  In addition, the auxiliary unit 5 is provided with a storage space increasing portion 51 that communicates with the banknote storage portion 41 of the unit 4A located below the auxiliary unit 5, and a transport mechanism 52 is provided behind the storage space increasing portion 51. Although not shown in detail, the transport mechanism 52 includes a pair of upper and lower rollers as well as the transport mechanism 42 of the intermediate unit 4A to 4C, and includes a gear provided on each roller shaft and one of the upper and lower rollers. A transmission belt is provided between pulleys provided on the roller shaft, and an intermediate transmission gear that meshes with a gear provided on the upper one roller shaft. The rollers interlock with each other, and the driving force can be transmitted from the lower unit to the upper unit while the driving force can be transmitted to the upper unit.

  Next, the electrical configuration of the banknote handling apparatus 1 shown in FIGS. 1 to 4 will be described. FIG. 5 is a block diagram showing an electrical configuration of the banknote handling apparatus 1. The same members as those shown in FIGS. 1 to 4 are denoted by the same reference numerals, and description thereof is omitted.

  As shown in FIG. 5, the banknote handling apparatus 1 includes a microphone 501, a banknote insertion sensor 502, a banknote passage sensor 503, and a control unit 600 in addition to the deposit / withdrawal unit 2, the base unit 3, and the intermediate unit 4 </ b> A to 4 </ b> C. .

  The microphone 501 converts sound into an electrical signal (analog signal), and collects sound generated during the conveyance of banknotes. The microphone 501 is installed in or near the transport path for transporting bills whose authenticity and denomination have been identified by the identification device 22, and in this embodiment, as shown in FIG. For example, the microphone 501 is installed in the vicinity of the roller 213 disposed along the bill introduction path 210.

  As shown in FIG. 1, the bill insertion sensor 502 is installed in the vicinity of the bill insertion slot 20 a and detects insertion of a bill into the opening 14. The bill insertion sensor 502 includes, for example, a pair of reflection type light projecting and receiving devices, and when the bill to be conveyed enters the detection position, the light output from the projector is reflected by the bill and received by the light receiving device. Is done. The bill insertion sensor 502 outputs a light reception signal (ON signal) to the control unit 600 while the light receiver receives reflected light from the bill. The rise timing and fall timing of the ON signal output from the bill insertion sensor 502 are used to determine the start and stop timing of the operation of the motor or the like provided in the bill introduction mechanism 21.

  As shown in FIG. 1, the bill passage sensor 503 is installed at a position in the vicinity of the roller 213 arranged along the bill introduction path 210 and in the vicinity of the microphone 501 (a position on the downstream side of the microphone 501). It detects the passage of banknotes at a preset detection position. The bill passage sensor 503 has a configuration similar to that of the bill insertion sensor 502, and outputs a light reception signal (ON signal) to the control unit 600 while the light receiver receives reflected light from the bill. . The rise timing and fall timing of the ON signal output from the bill passage sensor 503 are used to determine the start and stop timings of the sound collection operation of the microphone 501.

  The control unit 600 includes an unillustrated CPU (Central Processing Unit), a ROM (Read Only Memory) that stores a program that defines the operation of the CPU, and a function and work area for temporarily storing data. The banknote processing apparatus 1 is entirely controlled by a microcomputer configured with a RAM (Random Access Memory) having a function as The control unit 600 includes circuit components on the main CPU board 101 and the sub CPU board 102 installed on the control board unit 100.

By the way, the banknote processing apparatus 1 which concerns on this embodiment is a banknote with a small tension | tensile_strength and the grade of waist | lumps with the fatigue | accuracy (degree of a banknote and a wrinkle) being small for the banknote by which the authenticity and the money type were identified by the identification apparatus 22. (Hereinafter, this bill is referred to as a new bill), or whether it is a bill (hereinafter referred to as an old bill) having a large degree of fatigue and a low degree of fatigue, and the bill processing apparatus 1 Function as a bill fatigue discriminating device for extracting old bills from bills inserted into the bill, and a function as a storage unit for storing the old bills in the device 1 so that the old bills are not used again Have

  In order to realize the function of the banknote fatigue determination apparatus, the control unit 600 includes a sound collection control unit 601, a sampling unit 602, an amplitude difference calculation unit 603, a plotting unit 604, and a plot number counting unit 605 for each region. And a determination unit 606.

  The sound collection control unit 601 controls the sound collection operation of the microphone 501, and the rising timing of the output signal of the banknote passage sensor 503 from OFF to ON (the leading edge of the banknote passes through the detection position of the banknote passage sensor 503). Based on the timing), the sound collection operation by the microphone 501 is started, and the output signal of the bill passage sensor 503 falls from ON to OFF (the detection position of the bill passage sensor 503 is determined by the trailing edge of the bill). The sound collection operation by the microphone 501 is stopped based on the timing of the passage of the sound.

  FIG. 10A shows the signal waveform of the output signal (sound signal) of the microphone 501 that collects the sound emitted during the transportation of the old bill, and FIG. 10B is emitted during the transportation of the new bill. It is a figure which shows the signal waveform of the output signal (sound signal) of the microphone 501 which collected the sound. As can be seen from FIGS. 10A and 10B, the amplitude of the signal waveform is larger in the case of the new bill than in the old bill. On the other hand, in the case of an old bill, the signal waveform changes smoothly (amplitude increase / decrease mode is small) compared to a new bill.

  As shown in FIG. 6, the sampling unit 602 samples the analog signal S output from the microphone 501 at a constant sampling period T (for example, T = 1/5000 seconds). Hereinafter, the sampled data is referred to as sampling data. When the length in the banknote transport direction is, for example, 16 cm, the banknote transport speed is 8 cm / sec, and sampling is performed at a sampling period of 1/5000 (sec), 10000 (pieces) of sampling data is obtained per banknote. It will be.

  The amplitude difference calculation unit 603 calculates a difference in data value between the sampling data acquired by the sampling unit 602 and the sampling data after one, two, three, and so on. For example, when focusing on the sampling data indicated by the arrow Q1 in FIG. 6, the amplitude difference calculation unit 603 calculates the data value of the sampling data and the data value of the sampling data indicated by the next arrow Q2 following the data value. The difference is calculated as the first amplitude difference. Further, the amplitude difference calculation unit 603 calculates a difference between the data value of the sampling data indicated by the arrow Q1 and the data value of the sampling data indicated by the arrow Q3 two times after the data value as the second amplitude difference. Further, the amplitude difference calculation unit 603 calculates the difference between the data value of the sampling data indicated by the arrow Q1 and the data value of the sampling data indicated by the arrow Q4 three times after the data value as the third amplitude difference. The amplitude difference calculation unit 603 performs such processing for all the sampling data acquired by the sampling unit 602.

  Expressing this in a general form, as shown in FIG. 7, the amplitude difference calculation unit 603, with respect to the i-th sampling data D (i), the sampling data D (i) and the next sampling. The difference “D (i + 1) −D (i)” between the data and D (i + 1) is the first amplitude difference, and the difference “D (between the sampling data D (i) and the second sampling data D (i + 2)” i + 2) −D (i) ”is the second amplitude difference, and the difference“ D (i + 3) −D (i) ”between the sampling data D (i) and the sampling data D (i + 3) after the third is the third difference. Calculated as the amplitude difference.

The plotting unit 604 preliminarily sets points where the first amplitude difference, the second amplitude difference, and the third amplitude difference calculated by the amplitude difference calculation unit 603 for each sampling data are set as an X coordinate, a Y coordinate, and a Z coordinate, respectively. Plotting is performed on a three-dimensional orthogonal coordinate system of three axes orthogonal to each other (specifically, the X axis, the Y axis, and the Z axis shown in FIGS. 8 to 9), which is a defined three-dimensional coordinate system. That is, as shown in FIG. 7, the plot unit 604 calculates the first amplitude difference “D (i + 1) −D (i) for the i-th sampling data D (i) calculated by the amplitude difference calculation unit 603. ”Is the X coordinate Xi, the second amplitude difference“ D (i + 2) −D (i) ”for the i th sampling data D (i) calculated by the amplitude difference calculation unit 603 is the Y coordinate Yi, i th The third amplitude difference “D (i + 3) −D (i)” for the sampling data D (i) is Z coordinate Zi, and points Pi (Xi, Yi, Zi) are determined in advance as shown in FIG. Plot in a three-dimensional orthogonal coordinate system. An example of the distribution of plot points for all sampling data is shown in FIG.

As shown in FIG. 9, Pi points plotted in a three-dimensional orthogonal coordinate system, to one of a range of formed by dividing the 3-dimensional orthogonal coordinate system into eight quadrants divided regions (1) to (8) included. Here, the divided regions (1) to (8) are regions respectively corresponding to the first quadrant to the eighth quadrant, and are regions indicated by circled numbers 1 to 8 in FIG.

  The determination unit 606 determines the fatigue state of the banknote based on the distribution of the plotted data in each of the divided regions (1) to (8) calculated by the area-specific plot number counting unit 605.

In the present embodiment, the technology of a support vector machine (hereinafter referred to as SVM) is used to determine the fatigue state of a bill by dividing the above three-dimensional orthogonal coordinate system into a new bill region and an old bill region. It is done.

  SVM is a learning algorithm for pattern recognition of two classes (for example, two types of new and old bills). The SVM is basically a linear classifier, but can be extended to a non-linear classifier. In order to obtain a boundary line (or boundary plane) that divides each class based on teacher data (or learning data) of two known classes (for example, new and old bills) prepared in advance, Of the teacher data belonging to the class, the teacher data closest to the boundary line determines the boundary line having the maximum distance (that is, margin) from the boundary line. As a result, future unknown discrimination target data can be correctly identified as much as possible based on the boundary line obtained from the known teacher data (that is, the generalization ability is high).

Specifically, the determination of the fatigue state of the banknote using the SVM technique in the present embodiment is performed according to the following procedure. First, before performing the new / old discrimination on the banknotes to be discriminated between new and old, a plurality of sample banknotes (banknotes included in the boundary setting banknote of the present invention) are separately provided for the new bill and the old bill. Prepare and sample the voice of these sample banknotes as they pass through the banknotes and collect data. The control unit 600 divides the three-dimensional orthogonal coordinate system into eight divided quadrants (1) to (8) (see FIG. 9), and determines the number of plot points of data in each divided region. The number of plot points is calculated and stored in the determination unit 606 as teacher data. Specifically, as shown in FIG. 11, the determination unit 606 stores the number of plot points for each of the divided regions (1) to (8). For example, the number of plot points of a new bill, that is, a plurality of sample bills that are new bills, is stored for each of the divided regions (1) to (8) (see E1 to E8 in FIG. 11). The number of plot points of a plurality of sample bills that are old bills as fatigued bills is stored for each of the divided regions (1) to (8) (see F1 to F8 in FIG. 11). In this way, the determination unit 606 obtains eight-dimensional data composed of the number of data in eight quadrants of three-dimensional orthogonal coordinates for each of a plurality of sample banknotes including new and old bills.

  Next, the determining unit 606 determines the 8D data that is closest in distance between the 8D data of the new bill sample banknotes and the 8D data of the old bill sample banknotes. Select two. Here, as an example, the two selected eight-dimensional data are A (a1,... A8) and B (b1,... B8).

Next, the determination unit 606 obtains intermediate 8D data C located in the middle of the points corresponding to the two selected 8D data A and B. Here, the 8-dimensional data C is
C ((a1 + b1) / 2, ..., (a8 + b8) / 2) (Formula 1)
Represented as:

  And the boundary surface passing through the intermediate point obtained from the 8-dimensional data C of (Equation 1), and the distance between the point corresponding to the closest 8-dimensional data A and B and the intermediate point The boundary surface is set so that it can be secured between the point corresponding to the 8-dimensional data and the boundary surface. This boundary surface serves as a reference for discriminating between new and old bills.

Next, the determination unit 606 determines the fatigue state of the banknote to be determined using the boundary surface set as described above. Specifically, the determination unit 606 detects, for each divided region, the number of data plotted in each divided region of eight quadrants obtained by dividing the three-dimensional orthogonal coordinate system into eight regions for the banknote to be determined. Then, for each banknote to be discriminated, eight-dimensional data composed of the number of data in eight quadrants of three-dimensional orthogonal coordinates is obtained.

  Thereafter, the determination unit 606 includes an area including the 8D data in the new banknote obtained by dividing the 8D data obtained from the banknote to be determined by the boundary surface and an area including the 8D data in the fatigued banknote. It is detected which region of the banknote belongs to, and the fatigue state of the banknote is determined based on the detection result. Thereby, the fatigue state of a banknote can be correctly discriminate | determined by simple process.

For example, the distance to the boundary surface is obtained for a point corresponding to new 8-dimensional data D (d1,..., D8) obtained from a certain banknote to be discriminated. The distance to the boundary surface is obtained, for example, as an orthogonal projection value Result,
Result = w1 · d1 + w2 · d3 ... + w8 · d8 + b (Formula 2)
It is expressed as Here, w (w1, w2,..., W8) is a weight vector, and b is a parameter called a bias term.

  Note that the boundary surface is determined by using the Lagrangian function to determine each parameter of the weight vector w and the bias term b.

  Next, the orthogonal projection value Result is compared with a predetermined reliability limit T, and the fatigue state is determined. For example, when Result> T, it is determined as a new bill, and when Result <−T, it is determined as an old bill. If -T <Result <T, it is processed as undetermined.

  Next, operation | movement of the banknote processing apparatus 1 is demonstrated below. FIG. 12 is a flowchart showing the flow of banknotes when depositing money by the banknote handling apparatus 1.

  As shown in FIG. 12, when a detection signal (ON signal) indicating that a bill has been inserted from the bill insertion slot 20a is output from the bill insertion sensor 502 provided near the bill insertion slot 20a (step #). 1), the control unit 600 drives a motor (not shown) of the bill introduction mechanism 21 to cause the bill introduction mechanism 21 to take a bill into the apparatus 1 (step # 2). At this time, the bill is introduced at a relatively low speed by driving the motor.

  Next, the control unit 600 determines the denomination while the banknote is being conveyed (step # 3), and determines the authenticity of the banknote if the denomination can be determined (YES in step # 4). (Step # 5). When it is determined that the banknote is a true note (YES in step # 6), the control unit 600 identifies a fatigue state described later for the banknote (step # 7), and then determines the identified banknote. Depending on the denomination and fatigue state, the bill is taken into the unit that should take in the bill (step # 8).

  If the denomination cannot be identified (NO in step # 4), and if the control unit 600 determines that the banknote is a bill (NO in step # 6), the banknote is discharged. Transport toward 20b (step # 9).

  Next, the fatigue state determination process in step # 7 in FIG. 12 will be described in more detail.

  Here, before the fatigue state determination process is performed on the banknote to be determined, the boundary setting pre-process is performed in advance. The boundary setting pre-process is used to determine whether 8-dimensional data calculated from the sampling data is included in the new bill area or the old bill area as a reference for performing the determination process. This is pre-processing for setting the boundary to be performed, and is performed according to the flowchart shown in FIG.

  First, as shown in FIG. 13, when a plurality of (for example, ten) sample banknotes are inserted from the banknote insertion slot 20a for each of the new and old bills, the banknote passage sensor 503 detects the leading edge of the banknote (step). The sound collection control unit 601 causes the microphone 501 to start the sound collection operation, and the sampling unit 602 outputs an analog output signal output from the microphone 501 to a certain sampling period T (for example, T = The operation of sampling the sample banknote is started at (1/5000 seconds) (step # 12).

  When the trailing edge of the bill is detected by the bill passage sensor 503 (YES in step # 13), the sound collection control unit 601 stops the sound collection operation by the microphone 501, and the sampling unit 602 stops the sampling operation. The amplitude difference calculation unit 603 calculates the above-described first amplitude difference, second amplitude difference, and third amplitude difference for each sampling data acquired by the sampling unit 602 (step # 14).

Next, the plotting unit 604 plots points having the first to third amplitude differences calculated for each sampling data as the X coordinate, Y coordinate, and Z coordinate, respectively, in a preset three-dimensional orthogonal coordinate system ( Step # 15).

The area-specific plot number counting unit 605 detects (counts) the number of plot points in each of the divided areas (1) to (8) obtained by dividing the three-dimensional orthogonal coordinate system into a plurality of eight quadrants. (Step # 16).

  Thereafter, the determination unit 606 obtains 8-dimensional data for a plurality of sample bills for each of the new bill and the old bill based on the number of the detected plot points. Then, the determination unit 606 sets the boundary for dividing the new bill area and the old bill area by performing the above SVM processing using the eight-dimensional data (step # 17).

  As described above, the boundary between the new bill area and the old bill area can be set in advance.

  Thereafter, by using the boundary obtained by the above-described boundary setting preprocessing (see FIG. 13), the fatigue state identification process of the bill to be discriminated is performed as in the flowchart shown in FIG.

  As shown in FIG. 14, first, when a bill to be discriminated is inserted from the bill insertion slot 20a, the tip of the bill is detected by the bill passage sensor 503 in the same manner as described above (YES in step # 21). The sound collection control unit 601 causes the microphone 501 to start sound collection, and the sampling unit 602 outputs an analog output signal output from the microphone 501 at a constant sampling period T (for example, T = 1/5000 seconds). The sampling operation is started (step # 22).

  When the trailing edge of the bill is detected by the bill passage sensor 503 (YES in step # 23), the sound collection control unit 601 stops the sound collection operation by the microphone 501, and the sampling unit 602 stops the sampling operation. The amplitude difference calculation unit 603 calculates the above-described first amplitude difference, second amplitude difference, and third amplitude difference for each sampling data acquired by the sampling unit 602 (step # 24).

Next, the plotting unit 604 plots points having the first to third amplitude differences calculated for each sampling data as the X coordinate, Y coordinate, and Z coordinate, respectively, in a preset three-dimensional orthogonal coordinate system ( Step # 25).

The area-specific plot number counting unit 605 detects (counts) the number of plot points in each of the divided areas (1) to (8) obtained by dividing the three-dimensional orthogonal coordinate system into a plurality of eight quadrants. (Step # 26).

And the determination part 606 calculates | requires the 8-dimensional data comprised from each data number of 8 quadrants of a 3-dimensional orthogonal coordinate about each banknote of discrimination | determination object based on the number of said detected plot points. Next, the determination unit 606 includes an area including the 8D data in the new bill and the area including the 8D data in the old bill in which the 8D data obtained from the banknote to be determined is divided by the boundary. It is detected which of these areas belongs, and the fatigue state of the banknote is determined based on the detection result (step # 27). If the discrimination target banknote is not in the new bill area (NO in step # 27), the banknote is determined to be an old bill and set as a recovery target banknote (step # 28). The banknote set as the collection target banknote is stored in the base unit 3. If the old bills stored in the base unit 3 are distributed again in the market, there is a risk that the bill processing device 1 or a device such as a vending machine or a money changer may cause a bill jam and cause a failure. The bills are separated from other banknotes so that they are not distributed to the banknotes (not used again).

  On the other hand, when the eight-dimensional data of the discrimination target banknote is in the new bill area (YES in step # 27), the determination unit 606 determines that the banknote is a new bill and sets it as a non-recoverable banknote. (Step # 29). The banknotes set as non-collection banknotes are stored in the intermediate units 4A to 4C and the like.

(Banknote fatigue discrimination experiment)
Next, a bill fatigue discrimination experiment using the bill fatigue discrimination method of the present embodiment will be described in comparison with a comparative example.

  Here, for the experiment, a new bill and an old bill are prepared as shown in FIGS. As old bills, fatigue bills with different degrees of fatigue are prepared. The fatigue degree of the fatigue banknote is different in four stages of fatigue degrees A to D. The new bill is a bill that is not fatigued at all. Fatigue degree A is a slightly fatigued state, and Fatigue degree B to Fatigue degree D indicate states in which the fatigue degree is large in order, and fatigue degree D is the largest.

  Moreover, in experiment, the pattern which inserts the banknote at the time of sampling a banknote into the banknote insertion port 20a of the banknote processing apparatus 1 is performed changing 4 patterns about front and back. That is, as shown in FIGS. 15 to 16, bills are inserted in four insertion patterns of DF (front side), DR (front side), UF (rear side), and UR (rear side).

  First, an experiment using the determination method according to the present embodiment will be described.

  In the determination method according to the present embodiment, sampling data sampled on May 24, 2011 in Tokyo is used as teacher data, and as a test data, a condition of air temperature 26 ° C. and humidity 36% on March 29, 2012 in Okinawa. The sampling data below is used.

First, as a banknote for a sample in Tokyo, 40 fatigue banknotes and new bills with fatigue degrees A to D are inserted in one of the above four insertion patterns (DF, DR, UF, UR). And sampling to create teacher data. Next, using the created teacher data, a set of data composed of the first, second amplitude difference and third amplitude difference calculated for the teacher data is determined in advance as in the above embodiment. Plotting on the 3D Cartesian coordinate system for judgment, detecting the number of samples for each of the eight quadrant divisions (1) to (8) in the 3D Cartesian coordinate system, and creating a boundary for discriminating old and new banknotes To do. Then, using the test data sampled from the banknotes to be discriminated in Okinawa, the detection points obtained from the test data are plotted in the three-dimensional orthogonal coordinate system for judgment, and the divided areas (1) to (8) of the eight quadrants are plotted. ), The number of samples is detected, and using the detected number of samples and the above-mentioned boundary, the new / old discrimination of the banknote to be discriminated is performed. The determination results are shown in FIGS. 15 (a) to 15 (d).

  In the table of FIG. 15A, as the teacher data, for the insertion pattern DF, 40 samples of each fatigue level A to D and new bills are input and sampled and sampled. Using this teacher data, a boundary for discriminating between old and new banknotes based on the banknotes of the input pattern DF is created in advance by the SVM technique. Then, 40 banknotes for each fatigue level A to D and new bills as banknotes to be discriminated are inserted into 10 pieces for each of the four input patterns (DF, DR, UF, UR), With respect to test data sampled from banknotes, the old and new banknotes are discriminated by the above-mentioned boundary.

  The experimental results shown in FIG. 15A show that all 40 new bills are correctly discriminated as new bills, and the discrimination rate is 100%. Similarly, FIG. 15 (a) shows that 28 out of 40 bills with a fatigue level A (the oldest bill with the lightest fatigue level) are correctly identified as old bills, and the discrimination rate is 70%. , 37 out of 40 banknotes with fatigue level B (slightly fatigued old bill) are correctly identified as old bills, indicating that the discrimination rate is 93%, and fatigue level C (with a slightly heavy fatigue level) All 40 bills of old bills) are correctly identified as old bills, the discrimination rate is 100%, and 39 out of 40 bills of fatigue degree D (old bill with the heaviest fatigue level) Is correctly identified as an old bill, and the discrimination rate is 98%. Therefore, as shown in FIG. 15 (a), the discrimination rate of the entire banknote is 92% for each of the fatigue levels A to D and the new bill when using the boundary created based on the insertion pattern DF. .

  Similar to FIG. 15A above, FIG. 15B shows the discrimination result of old and new banknotes when using the boundary created with reference to the insertion pattern DR. As shown in FIG. 15 (b), the discrimination rate of the entire banknote is 93% for each of the fatigue levels A to D and the new bill when using the boundary created with the insertion pattern DR as a reference.

  Similar to FIG. 15A, FIG. 15C shows the discrimination result of old and new banknotes when using a boundary created with reference to the insertion pattern UF. As shown in FIG. 15C, the discrimination rate of the entire banknote is 79% for each of the fatigue levels A to D and the new bill when using the boundary created based on the insertion pattern UF.

  Similar to FIG. 15A, FIG. 15D shows the discrimination result of old and new banknotes when using the boundary created with reference to the insertion pattern UR. As shown in FIG. 15D, the discrimination rate of the entire banknote is 96% for each of the fatigue levels A to D and the new bill when using the boundary created based on the insertion pattern UR.

  FIG. 15 (e) shows a result obtained by integrating the number of correct answers in the experimental results of FIGS. 15 (a) to 15 (d). As shown in FIG. 15E, in the determination method of the present embodiment, as described above, the test data sampled in March in Okinawa is determined using the teacher data sampled in May in Tokyo. It can be seen that the discrimination rate is 90% as a total average.

  On the other hand, as a comparative example of the present invention, as described in Patent Document 2 above, the difference between the data values of each sampling data and predetermined sampling data sampled before and after the sampling data is first and second, respectively. Bills based on a distribution obtained by plotting a set of data composed of the first and second amplitude differences calculated for one sampling data in a predetermined two-dimensional coordinate system as an amplitude difference. To determine the fatigue state. Here, also in this comparative example, under the same operating environment as the above-described determination method according to the present embodiment (the test data sampled in March in Okinawa is determined using the teacher data sampled in May in Tokyo). Make a determination with. In the discrimination method of this comparative example, the experimental result as shown in FIG. 16 is obtained.

  In the example shown in FIG. 16 (a), as in FIG. 15 (a), 40 pieces of each of the fatigue levels A to D and new bills are input and sampled as the teacher data for the input pattern DF. Sampled data is used. Using this teacher data, a boundary for discriminating between old and new banknotes based on the banknote of the input pattern DF is created in advance by the SVM technique. Then, 40 banknotes for each fatigue level A to D and new bills as banknotes to be discriminated are inserted into 10 pieces for each of the four input patterns (DF, DR, UF, UR), With respect to test data sampled from banknotes, the old and new banknotes are discriminated by the above-mentioned boundary.

  The experimental result of the comparative example shown in FIG. 16A shows that all 40 new bills are correctly discriminated as new bills, and the discrimination rate is 100%. Similarly, FIG. 16A shows that 26 out of 40 banknotes with fatigue level A are correctly identified as old bills, and the discrimination rate is 65%. It is shown that 35 of them are correctly identified as old bills, and the discrimination rate is 88%. All 40 bills with fatigue degree C are correctly discriminated as old bills, and the discrimination rate is 100%. It is shown that 39 of 40 banknotes with fatigue degree D are correctly identified as old bills, and the discrimination rate is 98%. Accordingly, as shown in FIG. 16 (a), the discrimination rate of the entire banknote for each fatigue level A to D and the new bill when using the boundary created based on the insertion pattern DF in the comparative example is 90 %.

  Similar to FIG. 16A above, FIG. 16B shows the discrimination result of old and new banknotes when using a boundary created based on the insertion pattern DR in the comparative example. As shown in FIG. 16 (b), the discrimination rate of the entire banknote is 96% for each of the fatigue levels A to D and the new bill when using the boundary created based on the insertion pattern DR in the comparative example. is there.

  Similar to FIG. 16A, FIG. 16C shows the discrimination result of old and new banknotes when using a boundary created with reference to the insertion pattern UF in the comparative example. As shown in FIG. 16 (c), the discrimination rate of the entire banknote is 74% for each of the fatigue levels A to D and the new bill when using the boundary created based on the insertion pattern UF in the comparative example. is there.

  Similar to FIG. 16A, FIG. 16D shows the discrimination result of old and new banknotes when using a boundary created based on the insertion pattern UR in the comparative example. As shown in FIG. 16 (d), the discrimination rate of the entire banknote for each of the fatigue levels A to D and the new bill when using the boundary created based on the insertion pattern UR in the comparative example is 85%. is there.

  FIG. 16E shows a result obtained by summing up the number of correct answers in the experimental results of the comparative examples of FIGS. 16A to 16D. As shown in FIG. 16 (e), in the determination method of the comparative example, the test data sampled in March in Okinawa using the teacher data sampled in May in Tokyo as described above is used. Below, it can be seen that the overall average is 86%.

  As described above, when the discrimination rates of the discrimination method of the present embodiment and the discrimination method of the comparative example are compared under the same operating environment, as shown in FIGS. It can be seen that for any banknote, the discrimination method of the present embodiment has a higher individual discrimination rate than the discrimination method of the comparative example, and the overall accuracy rate is also improved. As a result, it can be seen that the determination method of the present embodiment improves the determination accuracy of fatigue banknotes compared to the determination method of the comparative example.

  Further, regarding the change in the discrimination rate when the operating environment such as humidity and temperature changes, the discrimination method of the present embodiment and the discrimination method of the comparative example will be further considered.

  First, in the experiments shown in FIGS. 15 to 16 described above, sampling data sampled on May 24, 2011 in Tokyo is used as teacher data, and as test data, an air temperature of 26 ° C. on March 29, 2012 in Okinawa, Sampling data under the condition of humidity 36% is used, but in the following experiments, sampling data sampled under conditions of a temperature of 24 ° C and humidity of 62% in Okinawa as a different operating environment, As test data, sampling data is used in Tokyo under conditions of an air temperature of 21.4 ° C. and a humidity of 46%.

  A table of FIG. 19 shows a result of an experiment performed by the discrimination method of the present embodiment using the teacher data and the test data changed as described above. As shown in FIG. 19, the discrimination rate of banknotes with fatigue level B is 60%, and the discrimination rate of banknotes with fatigue level B in the experimental results of FIG. 15 (e) is lower than 87%. It can be seen that the discrimination rates of the other new bills and the notes with fatigue levels A, C, and D have not changed much. In particular, the determination rate of the banknote with the lightest fatigue level A is 70% (see FIG. 19), and the discrimination rate of the banknote with the fatigue level A in the experimental result of FIG. It is. From the above points, it can be seen that the determination method of the present embodiment is not easily affected by changes in the operating environment such as temperature and humidity.

  On the other hand, the table of FIG. 20 shows the results of an experiment performed by the above-described comparative method using the teacher data and test data whose operating environment has been changed as described above. As shown in FIG. 20, the discrimination rate for banknotes with a fatigue level A is 30%, and the discrimination rate for banknotes with a fatigue level A in the experimental results of FIG. 16 (e) is significantly lower than 58%. Further, the discrimination rate of the banknote with the fatigue level B is also 50%, and it can be seen that the discrimination rate of the banknote with the fatigue level B in the experimental result of FIG. .

  As can be seen from the comparison of the tables of FIGS. 17 and 21 and the graphs of FIGS. 18 and 22, the determination method of this embodiment is affected by changes in the operating environment such as temperature and humidity. On the other hand, it can be seen that the comparative example discrimination method is easily affected by changes in the operating environment such as temperature and humidity. In particular, in the discrimination method of the comparative example, the discrimination rate of the banknotes with a relatively low degree of fatigue A and B greatly varies depending on the change of the operating environment, whereas in the discrimination method of the present embodiment, the change of the operating environment It can be seen that the effect on is small.

As described above, in the determination method of the present embodiment, a set of data composed of the first and second amplitude differences and the third amplitude difference calculated for one sampling data is set in a predetermined three-dimensional orthogonal coordinate system. By discriminating the fatigue state of banknotes based on the distribution obtained by plotting, it is possible to improve the discrimination accuracy about the fatigue state of banknotes, and it is improved against the effects of changes in the operating environment. You can see that

(Feature)
(1)
In the banknote fatigue determination device and the determination method according to the present embodiment, the difference in data value between each sampling data and predetermined sampling data sampled after one, two, three, and after the sampling data, respectively, is determined. A set of data composed of the first, second and third amplitude differences calculated as one, second and third amplitude differences, and calculated for one sampling data, is predetermined three-dimensional orthogonal By discriminating the fatigue state of the banknote based on the distribution obtained by plotting in the coordinate system, it is possible to suppress a decrease in reproducibility of the discrimination accuracy for the fatigue state of the banknote.

(2)
Moreover, in the banknote fatigue determination device and the determination method according to the present embodiment, each divided region obtained by dividing a three-dimensional orthogonal coordinate system into eight quadrants for a plurality of sample banknotes including a new bill and an old bill prepared in advance. 8 dimensional data is obtained from the number of data in, and two 8 dimensional data having the closest distance between the 8 dimensional data in the new bill and the 8 dimensional data in the old bill are selected, and then the selected 2 The 8D data of the intermediate point located in the middle of the points corresponding to the 8D data is obtained. After that, a boundary passing through the intermediate point between the point corresponding to the closest 8D data and a point corresponding to the other 8D data is the distance between the intermediate point and the boundary. By setting the boundary so as to be secured, the boundary between the eight-dimensional data in the new banknote and the eight-dimensional data in the fatigued banknote is set. Thereafter, the fatigue state of the banknote to be discriminated is discriminated using the set boundary. That is, to which area of the area including the 8D data in the new bill and the area including the 8D data in the old bill that the 8D data obtained from the banknote to be distinguished belongs to the boundary belongs to And the fatigue state of the banknote is determined based on the detection result. Thereby, the fatigue state of a banknote can be correctly discriminate | determined by simple process.

(3)
In the banknote processing apparatus according to the present embodiment, when the banknote processing apparatus is equipped with a function for determining the fatigue state of banknotes, the mounting of the function suppresses the banknote processing apparatus from becoming large or causing an increase in cost. be able to.

(Modification)
(A)
In the above-described embodiment, the new bill area and the old bill area are used to identify only whether the bill to be identified is a new bill or an old bill. In the invention, the present invention is not limited to the above form, and three or more stages may be set as the degree of fatigue of the banknote, and the degree of fatigue corresponding to the banknote to be identified may be identified .

DESCRIPTION OF SYMBOLS 1 Banknote processing apparatus 3 Base unit 4A-4C Intermediate | middle part unit 21 Banknote introduction mechanism 210 Banknote introduction path 501 Microphone 502 Banknote insertion sensor 503 Banknote passage sensor 600 Control part 601 Sound collection control part 602 Sampling part 603 Amplitude difference calculation part 604 Plotting part 605 Area-specific plot number counting unit 606 determining unit

Claims (3)

A sampling unit that samples a signal corresponding to sound generated during conveyance of banknotes as sampling data multiple times;
A first amplitude difference that is a difference in data value between each sampling data and the predetermined sampling data sampled after the sampling data; a predetermined sampling sampled after the sampling data and the sampling data Amplitude for calculating a second amplitude difference that is a difference in data value from data and a third amplitude difference that is a difference in data value between each sampling data and predetermined sampling data sampled three times after the sampling data A difference calculator;
A set of data composed of the first amplitude difference, the second amplitude difference, and the third amplitude difference calculated for each of the sampling data is orthogonal to each other in a predetermined three-dimensional coordinate system. A bill fatigue discriminating apparatus comprising a discriminating unit that plots in a three-dimensional orthogonal coordinate system of an axis and discriminates a fatigue state of the bill based on a distribution of data plotted in the three-dimensional orthogonal coordinate system ,
The discrimination unit
Data plotted in each divided region obtained by dividing the predetermined three-dimensional orthogonal coordinate system into eight quadrants for a plurality of border setting bills including new bills prepared in advance and tired bills Is detected for each divided area,
For each boundary setting banknote, obtain 8D data composed of the number of data in 8 quadrants of the 3D Cartesian coordinates,
Of the obtained 8D data, two 8D data having the closest distance between the 8D data in the new banknote and the 8D data in the fatigued banknote are selected,
Obtaining 8D data of an intermediate point located in the middle of the point corresponding to the selected 8D data;
After that, a boundary passing through the intermediate point between the point corresponding to the closest 8D data and a point corresponding to the other 8D data is the distance between the intermediate point and the boundary. By setting the boundary so that it can be secured, the boundary between the 8-dimensional data in the new banknote and the 8-dimensional data in the fatigued banknote is set,
For the banknote to be discriminated, the number of data plotted in each divided area obtained by dividing the predetermined three-dimensional orthogonal coordinate system into eight quadrants is detected for each divided area,
For each banknote to be discriminated, 8D data composed of the number of data in 8 quadrants of the 3D orthogonal coordinates is obtained,
Of the region containing the 8-dimensional data in the fatigued banknote and the region containing the 8-dimensional data in the new banknote obtained by dividing the 8-dimensional data obtained from the banknote to be discriminated Detect which region it belongs to and determine the fatigue state of the banknote based on the detection result
The banknote fatigue discrimination apparatus characterized by the above-mentioned . A slot for inserting the bills;
A bill fatigue discrimination device for discriminating a fatigue state of a bill inserted from the insertion slot;
A banknote processing apparatus comprising: a storage unit that separates and stores the banknotes according to fatigue states based on a determination result by the banknote fatigue determination apparatus;
The banknote fatigue determination apparatus according to claim 1 , wherein the banknote fatigue determination apparatus is the banknote fatigue determination apparatus. A sampling step in which the sampling unit samples a signal corresponding to the sound generated during the conveyance of banknotes as sampling data a plurality of times;
An amplitude difference calculation unit is a first amplitude difference that is a difference in data value between each sampling data and predetermined sampling data sampled after the sampling data, and after each sampling data and the sampling data. A second amplitude difference that is a difference in data value from the sampled predetermined sampling data, and a third difference that is a difference in data value between each sampling data and predetermined sampling data sampled three times after the sampling data. A calculation step for calculating an amplitude difference;
A discriminating unit is a predetermined three-dimensional coordinate system for a set of data composed of the first amplitude difference, the second amplitude difference, and the third amplitude difference calculated for each sampling data. plotted in three-dimensional orthogonal coordinate system of the three mutually orthogonal axes, met bill fatigue determination method and a determination step of determining the state of fatigue of the bill based on the distribution of the data plotted in the three-dimensional orthogonal coordinate system And
The determination step includes
For each of the divided areas formed by dividing the predetermined three-dimensional orthogonal coordinate system into eight quadrants for a plurality of boundary setting banknotes including new banknotes and tired banknotes prepared in advance. Detecting the number of each plotted data for each divided region;
The step of determining, for each boundary setting banknote, eight-dimensional data composed of the number of data in the eight quadrants of the three-dimensional orthogonal coordinates;
Of the obtained 8D data, the determination unit obtains 8D data having the closest distance between the 8D data of the new banknote and the 8D data of the fatigued banknote. One step to select,
The step of determining the 8D data of an intermediate point located in the middle of the point corresponding to the selected 8D data;
The discrimination unit is a boundary passing through the intermediate point, and a point between the point corresponding to the closest 8D data and the intermediate point corresponding to another 8D data and the boundary. Setting a boundary between the eight-dimensional data in the new banknote and the eight-dimensional data in the fatigued banknote by setting a boundary so as to be secured between
A step of detecting, for each divided area, the number of data plotted in each divided area obtained by dividing the predetermined three-dimensional orthogonal coordinate system into eight quadrants for the banknote to be determined; ,
The step of obtaining, for each banknote to be discriminated, eight-dimensional data composed of the number of data in eight quadrants of the three-dimensional orthogonal coordinates;
The discriminating unit obtains the region including the eight-dimensional data in the new bill obtained by dividing the eight-dimensional data obtained from the bill to be discriminated by the boundary and the eight-dimensional data in the fatigued bill. A step of detecting which region of the included regions belongs and determining a fatigue state of the banknote based on the detection result;
Have
A bill fatigue discrimination method characterized by the above .

Images