WO2011114516A1 - Dispositif d'identification de feuille de papier et procédé d'identification de feuille de papier - Google Patents

Dispositif d'identification de feuille de papier et procédé d'identification de feuille de papier Download PDF

Info

Publication number
WO2011114516A1
WO2011114516A1 PCT/JP2010/054829 JP2010054829W WO2011114516A1 WO 2011114516 A1 WO2011114516 A1 WO 2011114516A1 JP 2010054829 W JP2010054829 W JP 2010054829W WO 2011114516 A1 WO2011114516 A1 WO 2011114516A1
Authority
WO
WIPO (PCT)
Prior art keywords
image data
paper sheet
discrimination
threshold
threshold value
Prior art date
Application number
PCT/JP2010/054829
Other languages
English (en)
Japanese (ja)
Inventor
正範 坪田
賢二 山本
浩貴 坪田
Original Assignee
グローリー株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by グローリー株式会社 filed Critical グローリー株式会社
Priority to PCT/JP2010/054829 priority Critical patent/WO2011114516A1/fr
Publication of WO2011114516A1 publication Critical patent/WO2011114516A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
    • G07D7/20—Testing patterns thereon
    • G07D7/2075—Setting acceptance levels or parameters

Definitions

  • the present invention relates to a paper sheet discriminating apparatus and a paper sheet discriminating method for discriminating whether a paper sheet is correct or not, and in particular, a paper sheet discriminating apparatus capable of easily and appropriately setting a parameter for discriminating damage. And a paper sheet discrimination method.
  • a paper sheet discriminating apparatus that discriminates whether paper sheets such as banknotes and gift certificates are correct or not is known.
  • a non-performing ticket level indicating the degree of a non-performing ticket is provided in multiple stages, and the number of non-performing slips is determined by determining the pertinent slip level corresponding to the paper sheet to be determined. Is disclosed.
  • Patent Document 2 discloses a paper sheet discriminating apparatus that displays a schematic image representing a discrimination item corresponding to a parameter on a parameter change screen. For example, in the paper sheet discriminating apparatus disclosed in Patent Document 2, when a parameter for “corner break” is set, an image indicating a corner break state is displayed.
  • Patent Document 1 presents a guideline for resetting parameters only after discrimination processing for a large number of paper sheets is completed, the time required for parameter adjustment is prolonged and complicated. There was a problem that forced adjustment work was forced on the operator. For this reason, there is a problem that it is difficult to appropriately adjust the parameters.
  • the paper sheet identification device of Patent Document 2 merely notifies the operator of which determination item the parameter to be adjusted corresponds to, and what determination result is obtained after parameter adjustment. Not a notification.
  • the present invention has been made to solve the above-described problems of the prior art, and provides a paper sheet discriminating apparatus and a paper sheet discriminating method capable of easily and appropriately setting a parameter for discriminating damage.
  • the purpose is to provide.
  • the present invention is a paper sheet discriminating apparatus for discriminating whether a paper sheet is normal or not, and includes a storage means for storing image data and a discrimination item. Based on the image data extracted by using the threshold value, an example of the result of determining whether the threshold value after the setting operation received by the receiving unit and the threshold value after the setting operation received by the receiving unit is used. And an example means for performing the above.
  • the example means stores the image data that is an example of correct determination and / or the image data that is an example of loss determination based on the threshold value after the setting operation. It is characterized by extracting from the means.
  • the present invention is characterized in that, in the above-mentioned invention, the storage means stores imaging data obtained by imaging a paper sheet as the image data.
  • the present invention is the above invention, wherein the storage means stores the image data in which a comparison value to be compared with the threshold value is associated with each of the determination items, and the example means has the threshold value equal to or higher than the threshold value.
  • the image data associated with the comparison value and / or the image data associated with the comparison value less than the threshold value are extracted for each of the determination items, and the image data together with the extracted image data is positively determined. It is characterized by displaying the distinction of whether it is an example of the above or an example of loss determination.
  • the present invention further includes a determination unit that determines whether the paper sheet is normal or not by using the threshold value.
  • the determination unit receives the image data as an input, and the determination is performed on the image data.
  • the comparison value calculated for each item is stored in the storage unit in association with the image data.
  • the example means when there is no image data having the comparison value to be exemplified for the specific discrimination item, the example means has the comparison value different for the discrimination item.
  • the image data to be exemplified is generated from the image data.
  • the present invention is characterized in that, in the above invention, the example means exemplifies composite data obtained by combining the image data extracted for each of the different discrimination items.
  • the present invention is also a paper sheet discrimination method for discriminating whether a paper sheet is normal or not, and a storage process for storing image data in a storage unit and a reception operation for accepting a setting operation for a threshold prepared for each discrimination item. And an example step of performing an example of the result of damage determination when the threshold value after the setting operation received by the receiving step is used based on the image data extracted using the threshold value. It is characterized by.
  • image data is stored, a setting operation with respect to a threshold value prepared for each determination item is received, and an example of a fitness determination result when the received threshold value after the setting operation is used is illustrated after the setting operation. Since the determination is made based on the image data extracted using the threshold value, it is easy to set the damage determination parameter by exemplifying the damage determination result with the image data corresponding to the threshold value after the setting operation. And there is an effect that it can be appropriately performed.
  • image data that is an example of correct discrimination and / or image data that is an example of loss discrimination are extracted based on the threshold value after the setting operation. Is positively determined, and it is possible to accurately tell to the operator what state of the non-performing slip is determined.
  • the imaging data obtained by imaging the paper sheet is stored as the image data, so that the state of the damaged ticket is determined correctly, and the state of the damaged ticket is determined as lost. This is advantageous in that it can be conveyed to the operator more accurately by exemplifying the actual image.
  • the image data associated with the comparison value equal to or greater than the threshold value and / or the image data associated with the comparison value to be compared with the threshold value are stored for each discrimination item. Extracting image data associated with a comparison value less than the threshold value for each discrimination item, and displaying with the extracted image data whether the image data is an example of correct discrimination or an example of loss discrimination As a result, the determination result obtained by changing the threshold value can be accurately and promptly transmitted to the operator.
  • the image data is received as input in the determination of the normality, and the received image data is calculated for each determination item. Since the comparison value is stored in association with the image data, there is an effect that it is possible to extract an appropriate example image even when there is an individual difference in devices used for damage determination.
  • image data to be exemplified is generated from image data having a different comparison value for the discrimination item. Therefore, by providing an exemplary image in which a plurality of discrimination items are combined, there is an effect that it is possible to more easily and appropriately set the parameter for damage discrimination.
  • the exemplary image is displayed even when there is no actual image data to be displayed. There is an effect that it can be provided.
  • FIG. 1 is a diagram showing an outline of a paper sheet discrimination method according to the present invention.
  • FIG. 2 is a block diagram illustrating the configuration of the paper sheet discriminating apparatus according to the present embodiment.
  • FIG. 3 is a diagram showing an internal configuration of the banknote handling apparatus.
  • FIG. 4 is a diagram illustrating an operation example of the banknote handling apparatus.
  • FIG. 5 is a diagram showing an outline of the learning process.
  • FIG. 6 is a diagram illustrating an example of the reference threshold information and the exemplary image information.
  • FIG. 7 is a diagram illustrating an example of the selection screen.
  • FIG. 8 is a diagram illustrating an example of a fine adjustment screen.
  • FIG. 9 is a diagram illustrating a modification of the fine adjustment screen.
  • FIG. 10 is a diagram illustrating a modification of the threshold setting screen.
  • FIG. 11 is a flowchart illustrating the processing procedure of the learning process.
  • FIG. 12 is a flowchart showing the processing procedure of the threshold adjustment processing.
  • FIG. 1 is a diagram showing an outline of a paper sheet discrimination method according to the present invention.
  • the paper sheet discriminating method according to the present invention creates a database of the actual images of the acquired slips in advance, and corresponds to the changed threshold when setting the threshold for discriminating damage.
  • the main feature is that an actual image to be extracted is illustrated from a database.
  • the correct note group predetermined number of correct notes
  • each non-issued ticket group prepared for each level of non-issued ticket (in the figure, level A and level B).
  • “level” refers to each numerical range obtained by dividing a comparison value to be compared with a threshold value into a plurality of stages for each of a plurality of discrimination items used for discrimination of fitness.
  • the “reference threshold value” refers to a threshold value set as an initial value, and has a plurality of sets in which the reference threshold value corresponding to each discrimination item is combined for all discrimination items. Then, the operator selects which set is used as a default value.
  • which set is used as a default value may be set in advance at the time of shipment of the apparatus.
  • a set used as a default value may be set for each country or region to which the device is shipped.
  • an example image DB (database) is generated by actually imaging the slips included in each banknote group (see (A-2) in the figure).
  • the example image DB stores information in which the comparison value of each discrimination item is associated with the image data.
  • the reference threshold value selected from the reference threshold value DB is displayed as a default value on the threshold value adjustment screen for adjusting the threshold value (see (B) in the figure). Further, in conjunction with the threshold changing operation, the process of extracting the “exemplary image that has cleared the threshold” and the “exemplary image that has not cleared the threshold” from the exemplary image DB is repeated ((C) in the figure). reference).
  • the fact that the threshold has been cleared together with the “example image that has cleared the threshold” indicates that the example image has not cleared the threshold.
  • the fact that the threshold value has not been cleared is displayed.
  • a paper sheet discriminating apparatus to which the paper sheet discriminating method described with reference to FIG. 1 is applied will be described.
  • a paper sheet discriminating apparatus having a function for discriminating damage is described.
  • the present invention is applied to an apparatus having only a threshold setting function (for example, a threshold setting apparatus). Also good.
  • FIG. 2 is a block diagram showing the configuration of the paper sheet discriminating apparatus 10 according to the present embodiment.
  • the paper sheet discriminating apparatus 10 includes an identification unit 11, a display unit 12, an input unit 13, a control unit 14, and a storage unit 15.
  • the control unit 14 further includes a learning unit 14a, an example unit 14b, a threshold adjustment unit 14c, an identification data acquisition unit 14d, and a fitness determination unit 14e.
  • the storage unit 15 stores reference threshold information 15a, exemplary image information 15b, and adjustment threshold information 15c.
  • the identification unit 11 is a device that performs processing for discriminating the type of paper sheet and the correctness of the paper sheet using an image sensor and a magnetic sensor.
  • the identification unit 11 associates the comparison value acquired for each discrimination item with the image data obtained by imaging the paper sheet, and then the control unit 14 learning units 14a. Further, when the paper sheet discriminating apparatus 10 operates in the discrimination mode, the identification unit 11 notifies the identification data acquisition unit 14d of the control unit 14 of the comparison value acquired for each discrimination item.
  • the display unit 12 is a display device such as a liquid crystal display, and displays a threshold setting screen or the like generated by the example unit 14b of the control unit 14.
  • the input unit 13 is an input device such as a numeric keypad, and notifies the threshold adjustment unit 14c of the control unit 14 of the operation content by the operator.
  • a device having both functions for example, a touch panel display may be used.
  • FIG. 3 is a diagram illustrating an internal configuration of the banknote handling apparatus 100
  • FIG. 4 is a diagram illustrating an operation example of the banknote handling apparatus 100.
  • the banknote handling apparatus 100 includes a depositing unit 101, a first dispensing unit 102a, a second dispensing unit 102b, a temporary holding unit 102c, a transport unit 103, an identification unit 104, An operation display unit 105 and a controller 106 are provided.
  • the banknote handling apparatus 100 includes a scrutiny cassette 107, a stacker 108a, a stacker 108b, a stacker 108c, a stacker 108d, a stacker 108e, and a collection cassette 109.
  • the identification unit 104 corresponds to the identification unit 11 in FIG. 2
  • the operation display unit 105 corresponds to the display unit 12 and the input unit 13
  • the controller 106 corresponds to the control unit 14 and the storage unit 15.
  • the controller 106 includes a communication interface with other apparatuses and a printer that performs receipt printing.
  • the depositing unit 101 is a device that accepts bills inserted by a user or an operator, and the bills deposited into the depositing unit 101 are sent out to the transport unit 103.
  • the first withdrawal unit 102 a and the second withdrawal unit 102 b are devices that withdraw banknotes received from the transport unit 103.
  • the temporary storage unit 102c is a device that temporarily holds banknotes deposited from the depositing unit 101 and banknotes fed out from the stackers (108a to 108e).
  • the transport unit 103 is a device that transports the banknote deposited from the deposit unit 101 to the temporary storage unit 102c and each stacker (108a to 108e) via the identification unit 104. Further, the transport unit 103 transports banknotes fed from the stackers (108a to 108e) to the first withdrawal unit 102a and the second withdrawal unit 102b.
  • the stacker 108a, the stacker 108b, the stacker 108c, the stacker 108d, and the stacker 108e are storage units prepared for respective denominations, for example, when the banknotes received from the transport unit 103 are accumulated and a feeding instruction is received. Feeds the designated number of banknotes to the transport unit 103.
  • the scrutiny cassette 107 is a cassette used when re-identifying banknotes accumulated in the stackers (108a to 108e). For example, when a failure such as banknote jam occurs in the stacker 108d and is recovered, all banknotes are fed out from the stacker 108d and stored in the scrutinizing cassette 107 through re-identification by the identification unit 104.
  • the re-identified banknotes stored in the scrutiny cassette 107 are returned to the stacker 108d via the transport unit 103.
  • the collection cassette 109 is a detachable storage unit used when collecting banknotes from the banknote processing apparatus 100.
  • FIG. 4A shows an operation example at the time of depositing
  • FIG. 4B shows an operation example at the time of withdrawal.
  • FIG. 4A when a banknote is deposited into the depositing unit 101 by a user or an operator (see (A-1) in FIG. 4), the transport unit 103 identifies the deposited banknote as the identifying unit 104.
  • the identification unit 104 executes bill recognition processing (see (A-2) in the figure).
  • banknotes identified as correct bills by the identifying unit 104 are temporarily stored in the temporary holding unit 102c ((A-3a) in the figure).
  • banknotes identified by the identifying unit 104 as other than genuine (for example, counterfeit or damaged) are returned to the second dispensing unit 102b (see (A-3b) in the figure).
  • the genuine bills once stored in the temporary holding unit 102c are respectively stored in the corresponding stackers (any one of 108a to 108e) when the operation display unit 105 accepts the confirmation operation ((A -4)). Then, the stock amount (in this case, addition) of the stacker (any one of 108a to 108e) storing the correct ticket is updated (see (A-5) in the figure).
  • the temporary holding unit 102c may not be used.
  • the banknotes identified as correct bills by the identifying unit 104 are respectively stored in the corresponding stackers (any one of 108a to 108e) without going through the temporary holding unit 102c.
  • the banknotes identified by the identifying unit 104 as other than the regular bill for example, a fake ticket or a non-performing bill
  • the stock amount of the stacker any one of 108a to 108e in which the correct ticket is stored is updated.
  • FIG. 4B when the operation display unit 105 accepts a withdrawal operation (see (B-1) in FIG. 4), a predetermined number of banknotes are paid out from the corresponding stackers (108a to 108e). (See (B-2) in the figure). The fed banknotes are withdrawn to the first withdrawal unit 102a via the transport unit 103 (see (B-3) in the figure).
  • the bills fed out of the stackers (108a to 108e) may be re-identified by the identification unit 104.
  • the banknote in which the abnormality is found in the identification unit 104 is temporarily stored in the temporary storage unit 102c, and returned to the feeding stacker (108a to 108e) at a predetermined timing.
  • the control unit 14 is a control unit that performs overall control of the paper sheet discriminating apparatus 10.
  • the learning unit 14a receives and stores the comparison value acquired for each discrimination item and the image data obtained by imaging the paper sheet from the discrimination unit 11. It is a processing unit that performs processing for generating the reference threshold information 15a and the exemplary image information 15b of the unit 15.
  • the learning unit 14a uses the correct ticket group (predetermined number of correct tickets), and learning using each of the damaged ticket groups (level A and level B in the figure) prepared for each level of the damaged ticket.
  • the reference threshold value information 15a including the reference threshold value.
  • three types of strong, medium, and weak are generated as the reference threshold.
  • the learning unit 14a generates, for each banknote, exemplary image information 15b in which each image data obtained by capturing each banknote is associated with each comparison value acquired by the identification unit 11 for each discrimination item.
  • the learning unit 14a synthesizes the image data corresponding to the comparison values other than the missing comparison value to thereby obtain the missing comparison value.
  • generates the image data corresponding to is performed.
  • the learning unit 14a combines the image data with the comparison values “5” and “7” to generate image data with the comparison value “6”.
  • the image data corresponding to the missing comparison value is not generated in advance by the learning unit 14a, but may be generated, for example, after receiving a threshold change operation when displaying the image data. In this case, if there is no image data to be exemplified, the image data to be exemplified may be generated by combining a plurality of image data corresponding to other comparison values.
  • FIG. 5 is a diagram showing an outline of the learning process.
  • (A) in the figure shows a basic example of the learning process
  • (B) in the figure shows an example of threshold estimation in the case where there is no set of a predetermined banknote level.
  • the horizontal axis of each graph shown in the figure represents the comparison value for each discrimination item
  • the vertical axis represents the distribution frequency (for example, the number of paper sheets).
  • the learning unit 14a generates a correct distribution based on the identification result identified by the identifying unit 11 with respect to a predetermined number of correct tickets (see the broken line in FIG. 5).
  • the correct note distribution is, for example, a normal distribution.
  • the learning unit 14a generates each banknote distribution based on the identification result identified by the identification unit 11 for each banknote group consisting of a predetermined number for each banknote level.
  • the figure shows a case where a non-ticket group at a non-slip level A, a non-slip group at a non-slip level B and a non-slip group at a non-slip level C are used. It is assumed that the level of the loss ticket is the worst in level C and the closest to the correct ticket in level A.
  • the learning unit 14a generates a loss distribution for each of a plurality of loss ticket levels. Then, the learning unit 14a determines a threshold A for the slipped ticket level A, a threshold B for the slipped ticket level B, and a threshold C for the slipped ticket level C. In the figure, a case is shown in which each threshold value is determined near the apex of each banknote distribution. Then, the determined threshold A, threshold B, and threshold C are used as the above-described reference threshold.
  • the threshold value A corresponding to the loss ticket level A is used as the reference threshold value
  • about 30% of all banknotes are determined as the loss tickets in the above-described determination mode
  • the threshold value B is used as the reference threshold value.
  • about 10% is determined to be a non-performing ticket.
  • the threshold value C is used as the reference threshold value, about 3% is determined to be a bad ticket.
  • threshold value among the threshold value A, threshold value B, and threshold value C is selected as the reference threshold value, the tendency of the damage discrimination in the paper sheet discriminating apparatus 10 can be changed.
  • the learning part 14a performs the process which estimates the threshold value corresponding to the missing banknote level based on the banknote distribution corresponding to another banknote level.
  • the learning unit 14a corresponds to the threshold A corresponding to the loss ticket level A and the loss ticket level B when there is no loss ticket group of the loss ticket level B.
  • the threshold value B corresponding to the loss distribution at the loss ticket level B is estimated (see (B-1) in the figure).
  • the learning unit 14a An average value with C is defined as a threshold value B.
  • the threshold corresponding to the non-ticket level B is set to the non-ticket level A and C. The case of estimation by interpolation using the distribution of is shown.
  • the present invention is not limited to this, and the threshold value corresponding to the missing banknote level may be estimated by extrapolation. For example, when there is a population set corresponding to the loss ticket levels A and B and there is no population set corresponding to the loss ticket level C, the loss tickets are obtained by extrapolation using the distribution of the loss ticket levels A and B.
  • the threshold value corresponding to level C may be estimated.
  • FIG. 6 is a diagram illustrating an example of the reference threshold information 15a and the exemplary image information 15b. Note that (A) in the figure shows an example of the reference threshold information 15a, and (B) in the figure shows an example of the illustrative image information 15b. Moreover, in the same figure, the example in case the paper sheets used as discrimination
  • the reference threshold value information 15a includes a “denomination” item, a “defect ticket level” item, and a “reference threshold” item.
  • the “reference threshold value” item is classified for each discrimination item in the damage discrimination.
  • the reference threshold information 15a stores a reference threshold for each of a plurality of banknote levels for one denomination.
  • the same figure has illustrated the case where the reference threshold value corresponding to each of the banknote level A, banknote level B, and banknote level C is stored about one denomination.
  • the reference threshold values are “50” for the “tape ticket” item, “60” for the “tear” item, and “70” for the “dirt (part)” item.
  • ”And“ dirt (whole) ”items are“ 100 ”
  • “ graffiti ”items are“ 150 ”
  • “ blur ”items are“ 200 ”.
  • Each reference threshold is set by the learning unit 14a.
  • the reference threshold value information 15a is information in which reference threshold values corresponding to a plurality of discrimination items are stored for each denomination and each non-performing ticket level. If the default level B is set for the denomination ⁇ , “60”, “70”, “80”, “110”, “160”, and “210” are used as the respective reference threshold values. Will be.
  • the exemplary image information 15b includes an “image ID” item and a “comparison value” item.
  • a combination of numbers and symbols that uniquely identify image data can be used for the “image ID” item, but a serial number (an identification code printed on the banknote) read from the banknote is used. It is good as well.
  • the “comparison value” item is classified for each discrimination item in the fitness discrimination. Note that the contents of the classification are the same as those in FIG. 6A, and a description thereof is omitted here.
  • the comparison values corresponding to the image data whose “image ID” item is “11111” are “10”, “20”, “30”, “40”, “50”, and “60”. Further, the comparison values corresponding to the image data whose “image ID” item is “22222” are “20”, “30”, “40”, “50”, “60”, and “70”. Each comparison value is set by the learning unit 14a.
  • FIG. 6B shows a case where the image data itself is not included in the exemplary image information 15b, the image data itself may be included in the exemplary image information 15b.
  • the example unit 14b When receiving the threshold adjustment instruction via the input unit 13, the example unit 14b extracts a predetermined number of image data that clears the threshold and image data that does not clear the threshold from the example image information 15b using the adjusted threshold. It is a processing part which performs processing to perform.
  • the example unit 14b also performs a process of displaying a screen including the extracted image data on the display unit 12.
  • the example unit 14b uses the reference threshold value of the reference threshold value information 15a as the initial value of the threshold value on the threshold adjustment screen.
  • An example of the screen generated by the example unit 14b will be described later with reference to FIGS.
  • the threshold adjustment unit 14c is a processing unit that performs processing for storing the adjusted threshold value in the storage unit 15 as the adjustment threshold information 15c when an instruction to change the threshold value is received from the input unit 13.
  • the configuration of the adjustment threshold information 15c is the same as the reference threshold information 15a shown in FIG. Each time the adjustment threshold information 15c is updated, re-extraction processing of the exemplary image information 15b and update processing of the threshold adjustment screen are performed by the exemplary unit 14b.
  • the identification data acquisition unit 14d receives the comparison value acquired for each discrimination item from the discrimination unit 11 and the received comparison value to the fitness discrimination unit 14e. It is a processing unit that performs a passing process.
  • the damage determination unit 14e is a processing unit that determines the damage of the paper sheet by comparing the comparison value received from the identification data acquisition unit 14d with the finally determined adjustment threshold information 15c. is there.
  • the storage unit 15 is a storage device such as a hard disk drive or a non-volatile memory, and stores reference threshold information 15a, exemplary image information 15b, and adjustment threshold information 15c.
  • the contents of the reference threshold information 15a, the exemplary image information 15b, and the adjustment threshold information 15c have already been described with reference to FIG.
  • FIG. 7 is a diagram illustrating an example of the selection screen. Note that (A) in the figure shows a denomination selection screen 71 and (B) in the figure shows an item selection screen 72, respectively.
  • the denomination selection screen 71 has a denomination selection button 71a prepared for each denomination. For example, when the denomination selection button 71a corresponding to “denomination ⁇ ” is selected, the item selection screen 72 shown in FIG. 7B is displayed.
  • the item selection screen 72 includes a determination item selection button 72a corresponding to a determination item for fitness determination, and a threshold area 72b in which a reference threshold value in the determination item is displayed as an initial value. There are as many sets as there are discriminating items.
  • the item selection screen 72 also displays a denomination (“denomination ⁇ ” in the figure) to be finely adjusted.
  • FIG. 8 is a diagram illustrating an example of the fine adjustment screen 81. Note that (A) in the figure shows an example of the fine adjustment screen 81 displayed first, and (B) in the figure shows an example of the fine adjustment screen 81 after acceptance of the threshold change operation. Yes.
  • the fine adjustment screen 81 includes an information area 82 in which denominations and discrimination items that are targets for fine adjustment of the threshold are displayed, an up button 83a that receives an operation for increasing the threshold, A down button 83b for accepting an operation for reducing the threshold value, a threshold value display area 84 for displaying the latest threshold value, an example image area 85 for displaying an example image, and a confirm button 86 for pressing the threshold value have.
  • two of the four example images in which “ ⁇ ” is displayed have an example image having a comparison value equal to or less than the threshold value “50”, that is, the threshold value. It is the image for illustration which cleared.
  • Two of the “x” displayed are example images having comparison values larger than the threshold value “50”, that is, example images that have not cleared the threshold value.
  • the comparison values of the image for illustration are, for example, “35”, “45”, “55”, “65” in order from the top of the figure.
  • the comparison value “45” among the example images included in the example image information 15b, a plurality of example images having comparison values close to the comparison value “45” are selected. What is necessary is just to synthesize
  • the conditions for extracting the example image having what kind of comparison value can be determined as appropriate.
  • the new image threshold value “55” is used to indicate the example image area 85. Is updated.
  • three of the four example images displayed with “ ⁇ ” have an example image having a comparison value equal to or less than the threshold value “50”, that is, the threshold value. It is the image for illustration which cleared. Further, one of the “x” displayed is an example image having a comparison value larger than the threshold value “50”, that is, an example image that has not cleared the threshold value.
  • FIG. 8B illustrates the case where three example images that have cleared the threshold and one example image that has not cleared the threshold are displayed.
  • the display number of images may be the same as the display number of example images that have not cleared the threshold.
  • FIG. 8 shows the case where both the example image with the threshold cleared and the example image with the threshold cleared are displayed. However, only the example image with the threshold cleared, or the example with the threshold not cleared. Only the image for use may be displayed. In addition, after displaying a predetermined number of example images, it is possible to display whether each example image has cleared the threshold value “ ⁇ ” or whether the threshold value has not been cleared “x”.
  • the example image to be exemplified in the image area 85b is not included in the example image information 15b, the example image to be exemplified by combining a plurality of example images included in the example image information 15b. Is displayed on the image area 85b.
  • FIG. 9 is a diagram illustrating a modification of the fine adjustment screen.
  • 9A shows a fine adjustment area 91 corresponding to each discrimination item
  • FIG. 9B shows a fine adjustment screen 95 including a plurality of fine adjustment areas 91. Yes.
  • the fine adjustment area 91 corresponding to each determination item includes an up button 92a for accepting an operation for increasing the threshold value, a down button 92b for accepting an operation for reducing the threshold value, and the latest threshold value. Is displayed and an example image area 94 in which an example image is displayed.
  • the example image area 94 includes a notification area 94a in which “ ⁇ ” or “x” is displayed, and an image area 94b in which an example image extracted from the example image information 15b is displayed. A plurality of sets are displayed.
  • FIG. 9A shows a case where the exemplary image area 94 further includes a slider bar 94c.
  • the example image information 15b does not include the example image to be displayed in the image area 94b, the example image to be exemplified by combining a plurality of example images included in the example image information 15b. Is displayed on the image area 94b.
  • the fine adjustment screen 95 includes a denomination area 96 indicating denominations, and a fine adjustment area 91 (see FIG. 9A) corresponding to each discrimination item. , And a composition area 97 and a confirm button 98 that is pressed to confirm the threshold value.
  • the synthesis area 97 is an area for displaying a synthesized image obtained by synthesizing the example image extracted with the latest threshold value for each discrimination item. For example, a case where an example image having comparison values of +10, +5, ⁇ 5, and ⁇ 10 with respect to the latest threshold is extracted for each determination item will be described. In this case, the exemplary images having the comparison value of +10 and the exemplary images having the comparison value of +5 are synthesized with respect to all the discrimination items.
  • FIG. 9 shows the fine adjustment screen 95 in which the fine adjustment areas 91 respectively corresponding to the discrimination items are arranged in the vertical and horizontal directions
  • the configuration of the screen is not limited to this. Therefore, hereinafter, a modified example of the threshold setting screen will be described.
  • FIG. 10 is a diagram showing a modification of the threshold setting screen.
  • symbol as FIG. 9 is attached
  • the threshold setting screen 200 includes a threshold display area 93 in which the latest threshold is displayed and an image area 94 b in which an exemplary image extracted from the exemplary image information 15 b is displayed for each discrimination item. Is displayed.
  • the threshold setting screen 200 is provided with a slider bar used for changing the threshold.
  • the threshold is increased, and when the slider 99 is moved in the direction 99b, the threshold is decreased.
  • the image area 94b an exemplary image corresponding to the changed threshold value is displayed. 9 may be provided on the threshold setting screen 200.
  • the example image information 15b does not include the example image to be displayed in the image area 94b, the example image to be exemplified by combining a plurality of example images included in the example image information 15b. Is displayed on the image area 94b.
  • FIG. 11 is a flowchart illustrating the processing procedure of the learning process.
  • the learning unit 14a obtains the distribution of correct bills (see FIG. 5) from the identification unit 11 (step S101), and also distributes the distribution of each lossy ticket level (see FIG. 5) from the identification unit 11. Obtain (step S102).
  • the learning unit 14a calculates a reference threshold for each loss ticket level (step S103), and determines whether there is a loss ticket level without a mother set, that is, whether there is an insufficient loss ticket level. (Step S104).
  • step S104 when there is a deficient ticket level (step S104, Yes), the reference threshold value of the corresponding level is estimated from the other banknote level (step S105). If the determination condition in step S104 is not satisfied (step S104, No), the process proceeds to step S106 without performing the process procedure in step S105.
  • the learning unit 14a registers the reference threshold calculated in step S103 and the reference threshold estimated in step S105 in the reference threshold information 15a (step S106), and ends the process.
  • FIG. 12 is a flowchart showing the processing procedure of the threshold adjustment processing.
  • the example unit 14b searches the example image information 15b using the reference threshold value (step S202).
  • the example unit 14b displays the extracted example image on the display unit 12 (step S203).
  • the threshold adjustment unit 14c determines whether or not a confirmation operation for the threshold has been accepted (step S204). If a confirmation operation has been accepted (Yes in step S204), the latest threshold is adjusted to the adjustment threshold information 15c. (Step S208), and the process ends.
  • step S204 when the confirmation operation has not been received (step S204, No), it is determined whether or not a threshold change operation has been received (step S205).
  • step S205 Yes
  • the example unit 14b searches the example image information 15b using the changed threshold value (step S206).
  • step S207 After the extracted exemplary image is displayed on the display unit 12 (step S207), the processes after step S204 are repeated. Even when the determination condition of step S205 is not satisfied (step S205, No), the processing after step S204 is repeated.
  • a desired example image is generated by combining a plurality of example images included in the example image information 15b. Good.
  • the storage unit stores image data obtained by capturing paper sheets, the input unit accepts a setting operation for a threshold value prepared for each discrimination item, and the example unit accepts it.
  • the example of the result of damage determination when the threshold value after the setting operation is used is determined based on the image data extracted using the threshold value after the setting operation. Therefore, it is possible to easily and appropriately set the parameter for determining the damage.
  • the reference threshold value and the example image are learned via the identification unit included in the paper sheet identification device.
  • the reference threshold value and the example image generated by another device are identified as the paper sheet. It is good also as making it memorize
  • the example mentioned above demonstrated the case where the actual image of a defective ticket was switched and illustrated in connection with the change operation of a threshold value
  • the image for example, illustration
  • the grade of a damaged ticket is switched and illustrated. It is good as well.
  • a plurality of illustrations corresponding to the threshold value may be stored in advance, and when the threshold value is changed, an illustration corresponding to the changed threshold value may be exemplified.
  • the paper sheet discriminating apparatus and the paper sheet discriminating method according to the present invention are useful when it is desired to easily and appropriately set the parameters for discriminating damage, and in particular, the proficiency level of the operator is Even if it is low, it is suitable for the case where it is desired to easily and appropriately set the parameter for damage determination.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Inspection Of Paper Currency And Valuable Securities (AREA)

Abstract

La présente invention concerne un dispositif d'identification de feuille de papier qui est configuré de sorte qu'une unité de stockage stocke des données d'image de feuilles de papier, qu'une unité d'entrée accepte une opération de réglage concernant un seuil préparé pour chaque élément d'identification et qu'une unité d'exemplification exemplifie, sur la base des données d'image extraites à l'aide du seuil après l'opération de réglage, le résultat de l'identification normale ou endommagée, en cas d'utilisation du seuil après l'opération de réglage acceptée. Par ailleurs, le dispositif d'identification de feuille de papier est configuré de sorte que l'unité d'exemplification extraie, sur la base du seuil après l'opération de réglage, des données d'image pour une exemplification de l'identification en tant que normale et/ou des données d'image pour une exemplification de l'identification en tant qu'endommagée.
PCT/JP2010/054829 2010-03-19 2010-03-19 Dispositif d'identification de feuille de papier et procédé d'identification de feuille de papier WO2011114516A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2010/054829 WO2011114516A1 (fr) 2010-03-19 2010-03-19 Dispositif d'identification de feuille de papier et procédé d'identification de feuille de papier

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2010/054829 WO2011114516A1 (fr) 2010-03-19 2010-03-19 Dispositif d'identification de feuille de papier et procédé d'identification de feuille de papier

Publications (1)

Publication Number Publication Date
WO2011114516A1 true WO2011114516A1 (fr) 2011-09-22

Family

ID=44648642

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2010/054829 WO2011114516A1 (fr) 2010-03-19 2010-03-19 Dispositif d'identification de feuille de papier et procédé d'identification de feuille de papier

Country Status (1)

Country Link
WO (1) WO2011114516A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10286422B2 (en) 2014-10-24 2019-05-14 Glory Ltd. Paper sheet processing device, paper sheet processing system, and paper sheet processing method

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08305923A (ja) * 1995-04-28 1996-11-22 Glory Ltd 真偽鑑別装置
JP2009294933A (ja) * 2008-06-05 2009-12-17 Toshiba Corp 紙葉類処理装置及び紙葉類処理システム

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08305923A (ja) * 1995-04-28 1996-11-22 Glory Ltd 真偽鑑別装置
JP2009294933A (ja) * 2008-06-05 2009-12-17 Toshiba Corp 紙葉類処理装置及び紙葉類処理システム

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10286422B2 (en) 2014-10-24 2019-05-14 Glory Ltd. Paper sheet processing device, paper sheet processing system, and paper sheet processing method

Similar Documents

Publication Publication Date Title
US7631743B2 (en) Apparatus and a method for processing paper currency
JP5927811B2 (ja) 紙葉類処理装置
EP2827306B1 (fr) Dispositif de traitement de supports de valeur
US8408398B2 (en) Sheet handling system
WO2014064776A1 (fr) Dispositif de tri de feuilles et système de gestion de feuilles
WO2009099150A1 (fr) Dispositif de traitement de feuilles de papier et procédé de traitement de feuilles de papier
JP2009116646A (ja) 紙幣取扱装置および現金自動取引装置
JP2016206839A (ja) 媒体認識装置及び取引装置
JP5610804B2 (ja) 小切手処理装置および小切手処理方法
JP2013254349A (ja) 紙葉類判別システム及び紙葉類判別方法
WO2011114516A1 (fr) Dispositif d'identification de feuille de papier et procédé d'identification de feuille de papier
US11276263B2 (en) Paper sheet handling apparatus and paper sheet handling method
JP2008250530A (ja) 銀行券鑑査装置及び鑑査方法
JP2006085443A (ja) 紙葉類取り扱い装置、それに用いる紙葉類判別方法及び自動取引装置
JP2014225214A (ja) 紙葉類処理装置、及び紙葉類処理方法
JP2008225806A (ja) 現金処理装置およびその出力方法
JP2009294933A (ja) 紙葉類処理装置及び紙葉類処理システム
JP2013182350A (ja) 紙幣取扱装置
JP2003242549A (ja) 汚損券抽出装置およびそれを用いた現金取扱装置
JP2014197357A (ja) 有価媒体管理装置、有価媒体管理システム及び有価媒体管理方法
JP5198557B2 (ja) 紙幣処理装置
US20110139574A1 (en) Banknote handling system and banknote handling method
JP7178798B2 (ja) 紙葉類処理装置および紙葉類処理システム
JP2017208020A (ja) 有価媒体処理装置、有価媒体処理システム及び有価媒体処理方法
JP2020071639A (ja) 有価媒体処理装置、有価媒体処理システム及び有価媒体処理方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 10847927

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 10847927

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP