WO2016158392A1 - Dispositif de détection de feuille de papier et procédé de détection de feuille de papier - Google Patents

Dispositif de détection de feuille de papier et procédé de détection de feuille de papier Download PDF

Info

Publication number
WO2016158392A1
WO2016158392A1 PCT/JP2016/058188 JP2016058188W WO2016158392A1 WO 2016158392 A1 WO2016158392 A1 WO 2016158392A1 JP 2016058188 W JP2016058188 W JP 2016058188W WO 2016158392 A1 WO2016158392 A1 WO 2016158392A1
Authority
WO
WIPO (PCT)
Prior art keywords
paper sheet
edge point
boundary
tape
edge
Prior art date
Application number
PCT/JP2016/058188
Other languages
English (en)
Japanese (ja)
Inventor
鵜飼　和歳
中島　明
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
Publication of WO2016158392A1 publication Critical patent/WO2016158392A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • 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
    • G07D7/06—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 using wave or particle radiation
    • G07D7/12—Visible light, infrared or ultraviolet radiation
    • 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
    • G07D7/181—Testing mechanical properties or condition, e.g. wear or tear
    • G07D7/189—Detecting attached objects, e.g. tapes or clips

Definitions

  • the present invention relates to a paper sheet discriminating apparatus and a paper sheet discriminating method capable of discriminating whether or not a tape is stuck on a paper sheet.
  • Paper sheets such as banknotes are often folded along a short direction. When the crease breaks along the short direction, the tape may be reinforced.
  • Patent Document 1 there is a paper sheet thickness detection device disclosed in Patent Document 1 as a conventional technique capable of detecting a paper sheet to which a tape is attached in this manner.
  • the paper sheet thickness detection device disclosed in Patent Document 1 is a paper sheet that passes between a reference roller provided on a fixed rotation shaft and a detection roller provided in contact with and opposed to the reference roller. Mechanical thickness detection is performed using a detection block that rotates and displaces according to the thickness of the plate.
  • the mechanical thickness detection can only detect a tape having a thickness of 50 ⁇ m or more.
  • a thin tape such as 30 ⁇ m thickness or 40 ⁇ m thickness cannot be detected.
  • the detection device disclosed in Patent Document 2 optically detects wrinkles and tape sticking of paper sheets, not mechanical thickness detection.
  • the detection device disclosed in Patent Document 2 by irradiating light on the paper sheet obliquely from above, bright reflection at the side edge of the tape located on the light source side than the tape center or from the tape center.
  • the shadow of the side edge of the tape away from the light source is detected to detect whether the tape is affixed to the paper sheet, and it is necessary to devise the position of the light source, which complicates the structure of the device .
  • the present invention provides a paper sheet discriminating apparatus and a paper sheet discriminating method capable of discriminating whether or not a tape is stuck on a paper sheet even when a thin tape is stuck. It is intended to do.
  • a paper sheet discriminating apparatus is a paper sheet discriminating apparatus that discriminates whether a tape is affixed to a paper sheet based on a captured image of the paper sheet.
  • a storage unit for storing a reference edge point that is an edge point in a density gradient direction range along the longitudinal direction of the legitimate paper sheet included in the captured image of the paper sheet, and imaging of the paper sheet to be discriminated
  • An edge point extraction unit that extracts edge points in a density gradient direction range along a longitudinal direction of the paper sheet to be determined from an image, and an edge point extracted by the edge point extraction unit, to the reference edge point
  • a remaining edge point extracting unit that extracts a remaining edge point by removing an edge point estimated that a pixel that is not included in a captured image of the corresponding edge point and the legitimate paper sheet is generated due to a bright area; Based on the remaining edge point And it has provided an analysis unit for analyzing whether the tape is stuck to the paper sheet serving as the determination target configuration (first configuration).
  • the edge points generated due to the design of the paper sheet can be removed from the edge points that may have been generated due to the side edge of the tape.
  • the extraction of the remaining edge point as described above causes the side of the tape to move from the edge point that may have occurred due to the side edge of the tape. Edge points estimated not to be generated due to edges can be removed. Therefore, the detection accuracy of tape sticking can be increased.
  • the reference edge point is a first reference edge point that is an edge point of a first density gradient direction range included in the captured image of the legitimate paper sheet, A second reference edge point that is an edge point of the second density gradient direction range that is opposite to the first density gradient direction range, and the edge point extraction unit is configured to detect a captured image of the paper sheet to be determined. Edge points of the first density gradient direction range and edge points of the second density gradient direction range are extracted, and the remaining edge points are edge points of the first density gradient direction range extracted by the edge point extraction unit. From the first remaining edge, the edge point corresponding to the first reference edge point and the edge point estimated that the pixel not included in the captured image of the legitimate paper sheet is generated due to a bright area are removed.
  • an edge point corresponding to the second reference edge point and a pixel not included in the captured image of the legitimate paper sheet are bright areas It is preferable that the configuration includes a second remaining edge point obtained by removing an edge point estimated to have occurred due to the above (second configuration).
  • the analysis unit determines whether a tape is attached to the paper sheet to be discriminated based on the density of the remaining edge points in a predetermined size region. It is preferable that the configuration be analyzed (third configuration).
  • the predetermined size region it is possible to detect tapes with different attaching directions by changing the shape of the predetermined size region. For example, it is possible to detect a tape attached vertically (short direction of the paper sheet) by making the predetermined size area vertically long, and by tilting the predetermined size area diagonally, The affixed tape can be detected.
  • the remaining edge point extraction unit applies the captured image of the paper sheet to be determined to the captured image of the legitimate paper sheet.
  • edge points located around the thin line area are also the edge A configuration (fourth configuration) that is removed from the edge points extracted by the point extraction unit is preferable.
  • an edge point that appears due to the influence of a thin bright line generated by a strong crease can be removed from an edge point that may have occurred due to the side edge of the tape. Therefore, the detection accuracy of tape sticking can be further increased.
  • the longitudinal direction of the paper sheet to be discriminated is directed from one end to the other end. And a second boundary that changes from a first region to a second region that is darker than the first region and a third region that changes from the third region to a fourth region that is brighter than the third region.
  • the determination unit determines an interval between the first boundary and the second boundary located on the other end side with respect to the first boundary. Only in the region between the first boundary and the second boundary located on the other end side than the first boundary only when it is not less than the minimum width and not more than the maximum width of the target tape. Based on the pixel value of the pixel located, it is determined whether a tape is applied to a region between the first boundary and the second boundary located on the other end side of the first boundary. A configuration (sixth configuration) is preferable.
  • the determination unit is between the first boundary part and the second boundary part located on the other end side with respect to the first boundary part. Based on the dispersion of the pixel values of the pixels located in the region, a tape is applied to the region between the first boundary and the second boundary located on the other end side from the first boundary. It is preferable that the configuration (seventh configuration) be determined.
  • the area where the tape is affixed has little uneven density, so the dispersion of pixel values is small. Therefore, according to such a structure, the detection accuracy of tape sticking can be made high.
  • the determination unit is configured to determine the first boundary portion and the fourth region based on the pixel value of the first region and the pixel value of the fourth region. It is preferable that it is the structure (8th structure) which determines whether the tape is affixed to the area
  • a paper sheet discriminating method is a paper sheet discriminating method for discriminating whether a tape is stuck on a paper sheet based on a captured image of the paper sheet.
  • An edge point extracting step for extracting edge points in a density gradient direction range along the longitudinal direction of the paper sheet to be discriminated from a captured image of the paper sheet to be discriminated, and an edge extracted by the edge point extracting step From the point, an edge point corresponding to a reference edge point that is an edge point in a density gradient direction range along the longitudinal direction of the legitimate paper sheet included in the captured image of the legitimate paper sheet and the legitimate paper sheet
  • a remaining edge point extracting step of extracting a remaining edge point by removing an edge point estimated that a pixel not included in the captured image is generated due to a bright region, and the determination target based on the remaining edge point Become paper sheets A configuration that includes an analysis step of analyzing whether the tape is stuck.
  • the edge points generated due to the design of the paper sheet can be removed from the edge points that may have been generated due to the side edge of the tape.
  • the extraction of the remaining edge point as described above causes the side of the tape to move from the edge point that may have occurred due to the side edge of the tape. Edge points estimated not to be generated due to edges can be removed. Therefore, the detection accuracy of tape sticking can be increased.
  • the present invention even when a thin tape is stuck, it can be determined whether or not the tape is stuck on the paper sheet.
  • determination method based on this invention The block diagram which shows the structure of the paper sheet discrimination
  • the figure which shows an example of the smoothing filter The figure which shows an example of a Laplacian filter
  • the figure which shows an example of a horizontal direction Prewitt filter Diagram showing an example of a vertical Prewitt filter A flowchart showing the first estimation process Pixel value histogram for captured images of banknotes to be identified A flowchart showing the second estimation process
  • determination object The figure which shows an example of the filter for density detection
  • 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 first, the paper sheet that is the discrimination target is irradiated with light, and the paper sheet that is the discrimination target based on the transmitted or reflected light from the paper sheet that is the discrimination target The captured image is generated (see (1) in FIG. 1).
  • edge points in the density gradient direction range along the longitudinal direction of the paper sheet to be discriminated are extracted from the captured image of the paper sheet to be discriminated (see (2) in FIG. 1).
  • the edge refers to a portion where the contrast of the image is remarkably changed.
  • the direction from the bright edge to the dark edge is the density gradient direction.
  • An edge point is a pixel corresponding to an edge in an image.
  • the longitudinal direction of the paper sheet to be discriminated with a width of ⁇ 12.5 degrees with respect to the direction from the left end to the right end of the paper sheet to be discriminated.
  • a width of ⁇ 12.5 degrees with respect to the edge point of the density gradient direction range (indicated as the A direction range in FIG. 1B) and the direction from the right edge to the left edge of the sheet to be identified
  • the edge point of the density gradient direction range (denoted as the B direction range in (2) of FIG. 1) along the longitudinal direction of the paper sheet to be discriminated is extracted.
  • a legitimate paper sheet means a paper sheet that is free from contamination such as dirt, wrinkles, and folds and is not attached with a tape.
  • Density gradient direction range along the longitudinal direction of the paper sheet to be discriminated used when extracting a specific edge point
  • a legitimate paper sheet image to be used when obtaining a reference edge point The “concentration gradient direction range along the longitudinal direction of the legitimate paper sheets included” may not completely match, but it is desirable that they completely match.
  • the edge points generated due to the design of the paper sheet can be removed from the edge points that may have been generated due to the side edge of the tape. Also, in the area where the tape is applied, the pixel becomes dark due to the influence of the tape, that is, the pixel value becomes small in this embodiment. It is possible to remove an edge point that is estimated not to have been generated due to the side edge of the tape from the edge point that may have occurred.
  • the paper sheet discrimination method in the paper sheet discrimination method according to the present invention, tape sticking is optically detected. Therefore, even when a thin tape is stuck, it can be determined whether or not the tape is stuck on the paper sheet. Further, since the bright reflection and shadow at the side edge of the tape generated by irradiating light on the paper sheet from obliquely above is not used, it is not necessary to devise the position of the light source. Furthermore, in the paper sheet discriminating method according to the present invention, due to the extraction of the remaining edge point as described above, the edge point that may have occurred due to the side edge of the tape is caused by the design of the paper sheet. The generated edge point can be removed.
  • the extraction of the remaining edge point as described above causes the tape side from the edge point that may have occurred due to the side edge of the tape. Edge points estimated not to be generated due to the edge can be removed. Therefore, the detection accuracy of tape sticking can be increased.
  • the paper sheet discriminating method according to the present invention is not limited to bills. It can also be applied to other arbitrary paper sheets such as checks, bills and gift certificates.
  • FIG. 2 is a block diagram showing the configuration of the banknote discriminating apparatus 10 according to the first embodiment of the present invention.
  • FIG. 2 only constituent elements necessary for explaining the features of the banknote discriminating apparatus 10 are shown, and descriptions of general constituent elements are omitted.
  • the bill discriminating apparatus 10 includes an image line sensor unit 1, a control unit 2, and a storage unit 3.
  • the control unit 2 includes an image data acquisition unit 2a, a denomination identification unit 2b, an edge point extraction unit 2c, a remaining edge point extraction unit 2d, and an analysis unit 2e.
  • the storage unit 3 stores a denomination identification template 3a, various filters 3b, a reference edge point 3c, and analysis standard information 3d.
  • the image line sensor unit 1 is a sensor unit that receives transmitted light or reflected light from banknotes conveyed by a conveyance mechanism (not shown), and is configured by arranging a plurality of light receiving sensors in a straight line.
  • the light applied to the banknote is preferably light having an infrared wavelength that hardly reacts to dirt, but may be visible light such as white, red, green, and blue.
  • the image line sensor unit 1 also performs a process of outputting the light reception result to the image data acquisition unit 2 b of the control unit 2.
  • the control unit 2 is a processing unit that generates image data of banknotes based on the output from the image line sensor unit 1 and analyzes the generated image data to determine whether a tape is stuck on the banknotes.
  • the image data acquisition unit 2a is a processing unit that performs processing to develop output data from the image line sensor unit 1 in a memory, synthesize it for each banknote, and generate image data for the entire banknote.
  • the image data acquisition unit 2a also performs a process of outputting the generated image data to the denomination identifying unit 2b and the edge point extracting unit 2c.
  • the denomination identifying unit 2b compares the feature pattern of the image data generated by the image data acquiring unit 2a with the denomination identifying template 3a that is a feature pattern for each denomination of the bill, and determines the denomination of the bill. To do.
  • the edge point extraction unit 2c uses various filters 3b to smooth the image data output by the image data acquisition unit 2b, and extracts edge points in the density gradient direction range along the longitudinal direction of the banknote from the smoothed image data. It is a processing part which performs the process to perform. The edge point extraction unit 2c also performs a process of outputting an edge point image indicating the extracted edge point to the remaining edge point extraction unit 2d.
  • the edge point extraction unit 2c has a concentration gradient direction range (hereinafter referred to as an A direction range) having a width of ⁇ 12.5 degrees with respect to the direction from the left end to the right end of the banknote along the longitudinal direction of the banknote.
  • Edge point and a concentration gradient direction range (hereinafter also referred to as a B direction range) along the longitudinal direction of the bill with a width of ⁇ 12.5 degrees with respect to the direction from the right end to the left end of the bill. Extract edge points.
  • the reason why the width is ⁇ 12.5 degrees is that the tape is applied obliquely. However, +12.5 degrees is an example and may be any value between 0 degrees and +45 degrees.
  • each concentration gradient direction range may not be line symmetric with respect to the longitudinal direction of the banknote, and both concentration gradient direction ranges may not be line symmetrical with respect to the short direction of the banknote.
  • either the right tape side end or the left tape side end cannot be reliably detected, but only one of the former edge point and the latter edge point may be extracted.
  • the center of the filter and the target pixel are overlapped, the filter coefficient is multiplied by the pixel value of the pixel at each overlap position, and the sum of the respective multiplication values is used as the pixel value of the target pixel. .
  • smoothing for example, a smoothing filter in which all the coefficients of 3 ⁇ 3 pixels shown in FIG. 3 are 1 can be used. By smoothing, random noise superimposed on the image can be removed. Even when smoothing is not performed, it is possible to detect edge points and density gradient directions.
  • edge points for example, a 3 ⁇ 3 pixel 8-direction Laplacian filter shown in FIG. 4 can be used.
  • a zero-cross point detected by filter processing using a Laplacian filter is an edge portion of the original image.
  • a 3 ⁇ 3 pixel horizontal Prewitt filter shown in FIG. 5 and a 3 ⁇ 3 pixel vertical Prewitt filter shown in FIG. 6 can be used.
  • Density gradient by the ratio of positive and negative combination and absolute value between pixel value of target pixel obtained by filter processing using horizontal Prewitt filter and pixel value of target pixel obtained by filter processing using vertical Prewitt filter The direction can be detected.
  • the remaining edge point extracting unit 2d is included in the edge point corresponding to the denomination reference edge point identified by the denomination identifying unit 2b from the edge point extracted by the edge point extracting unit 2c and the captured image of the valid banknote. An edge point estimated to be generated due to a region having a large pixel value that is not present is removed.
  • the remaining edge point extraction unit 2d has a thin line area with a large pixel value along the short direction of the banknote to be discriminated that is not included in the captured image of the legitimate banknote in the image data of the banknote that is discriminatively symmetric.
  • the edge points located around the thin line area are also removed from the edge points extracted by the edge point extraction unit 2c.
  • the order of removing the above three types of edge points is not particularly limited. Further, one type may be removed in order, or a plurality of types of edge points may be removed at the same time.
  • the remaining edge point extracting unit 2d is an edge point image indicating edge points in the A direction range extracted by the edge point extracting unit 2c, an image indicating reference edge points in the A direction range described later, and described later. Using the result of each estimation process, an edge point image indicating the remaining edge points in the A direction range is generated.
  • the remaining edge point extraction unit 2d includes an edge point image indicating edge points in the B direction range extracted by the edge point extraction unit 2c, an image indicating reference edge points in the B direction range described later, and estimations described later. An edge point image indicating the remaining edge points in the B direction range is generated using the processing result.
  • the remaining edge point extracting unit 2d also performs processing of outputting an edge point image indicating the remaining edge points in the A direction range and an edge point image indicating the remaining edge points in the B direction range to the analyzing unit 2e.
  • the reference edge point is an edge point appearing in legitimate banknote image data, and is used as a mask pattern of the edge point to be removed in order to extract the edge point of the tape.
  • edge points in the A direction range are detected.
  • the expansion process which expands an effective edge point to a surrounding pixel is mainly performed for the purpose of absorption of the position shift of the banknote used as a discrimination
  • the neighboring pixels may be, for example, adjacent eight neighboring pixels, or may be one neighboring pixel adjacent in the direction from the left end to the right end of the bill.
  • the effective edge point in the A direction range obtained in this way is set as the reference edge point in the A direction range.
  • the storage unit 3 stores the reference edge point in the A direction range in the form of an image showing the reference edge point in the A direction range.
  • an edge point in the B direction range is detected, and if there is an edge point at the same position with the number of determination thresholds (for example, 5) or more, B The effective edge point of the direction range.
  • the expansion process which expands an effective edge point to a surrounding pixel is mainly performed for the purpose of absorption of the position shift of the banknote used as a discrimination
  • the neighboring pixels may be, for example, adjacent eight neighboring pixels, or may be one neighboring pixel adjacent in the direction from the left end to the right end of the bill.
  • the effective edge point in the B direction range obtained in this way is set as the reference edge point in the B direction range.
  • the storage unit 3 stores the reference edge point in the B direction range in the form of an image indicating the reference edge point in the B direction range.
  • the reference edge point in the A direction range and the reference edge point in the B direction range described above differ depending on the denomination, they are stored for each denomination.
  • the reference edge point described above is created before the product shipment of the banknote discriminating apparatus 10, and the banknote discrimination apparatus 10 is shipped in a state where the reference edge point 3c is stored in the storage unit 3 in advance.
  • the creation of the reference edge point may be performed using an apparatus other than the banknote discriminating apparatus 10 or may be performed using the banknote discriminating apparatus 10 itself.
  • an interface for enabling rewriting of the contents stored in the storage unit 3 may be provided in the bill discriminating apparatus 10 so that the reference edge point 3c can be easily added or corrected.
  • the first estimation process is executed by the remaining edge point extraction unit 2d.
  • the edge point extracted by the edge point extraction unit 2c is the maximum as the target edge point processed by the first estimation process.
  • the edge points corresponding to the denomination reference edge points identified by the denomination identifying unit 2b are removed from the edge points extracted by the edge point extracting unit 2c. In this case, the remaining edge point becomes the target edge point processed by the first estimation process.
  • the remaining edge point extraction unit 2d obtains the most frequently appearing pixel value of the captured image of the banknote to be determined (step S1).
  • FIG. 8 is a diagram illustrating an example of a pixel value histogram relating to a captured image of a bill to be determined.
  • the density of the captured image of the banknote to be determined is 256 gradations
  • the pixel with a pixel value of 0 is the darkest pixel
  • the pixel with a pixel value of 256 is the brightest pixel
  • the pixel value is 188.
  • the “most frequently occurring pixel value” is used as a pixel value representing the background of the captured image of the banknote to be determined in step S2 and subsequent steps.
  • the processing after step S2 is executed for each target edge point.
  • the remaining edge point extraction unit 2d has the pixel values of the three pixels lined up successively in the direction from the right end to the left end of the banknote adjacent to the left side (the left end side of the banknote) of the target edge point.
  • the pixel value of three pixels that are smaller than the value obtained by subtracting 5 from the “most frequently appearing pixel value”, or that are adjacent to the right side of the target edge point (the right end side of the banknote) and that are successively arranged in the direction from the left end to the right end of the banknote. It is determined whether or not the first condition that each is smaller than a value obtained by subtracting 5 from the “most frequently used pixel value” (step S2).
  • the pixel value becomes smaller due to the influence of the tape. For this reason, when the first condition is satisfied, it can be estimated that the target edge point is generated due to the side edge of the tape. Therefore, when it is determined that the first condition is satisfied (YES in step S2), the remaining edge point extracting unit 2d is caused by a region having a large pixel value in which the target edge point is not included in the captured image of the valid banknote. It is estimated that the edge point is not generated (step S3).
  • the remaining edge point extraction unit 2d is adjacent to the left side of the target edge point (the left end side of the banknote) from the right end to the left end of the banknote.
  • the pixel value becomes smaller due to the influence of the tape. Therefore, when the second condition is satisfied, it can be estimated that the periphery of the target edge point is a relatively bright background and the target edge point is generated due to the side edge of the tape. Therefore, when it is determined that the second condition is satisfied (YES in step S4), the remaining edge point extraction unit 2d is caused by a region having a large pixel value in which the target edge point is not included in the captured image of the valid banknote. It is estimated that the edge point is not generated (step S3).
  • step S4 when neither the first condition nor the second condition is satisfied, it is unlikely that the target edge point has occurred due to the side edge of the tape. Therefore, when it is not determined that the second condition is satisfied (NO in step S4), the remaining edge point extraction unit 2d has a large pixel value where the target edge point is not included in the captured image of the valid banknote. It is estimated that the edge point is generated due to (step S5).
  • determination conditions used in steps S2 and S4 are merely examples, and the threshold values used in the determination conditions are not particularly limited.
  • the second estimation process to be estimated will be described using the flowchart of FIG.
  • the second estimation process is executed by the remaining edge point extraction unit 2d.
  • the remaining edge point extraction unit 2d obtains the most frequently appearing pixel value of the captured image of the banknote to be discriminated (step S11).
  • the process of step S11 is the same as the process of step S1 in the flowchart of FIG.
  • the remaining edge point extraction unit 2d determines the average value of the pixel values in the vertical direction (short direction of the banknote) for each captured pixel image in the horizontal direction (longitudinal direction of the banknote). (Step S12).
  • An example of the calculation result obtained by the process of step S12 is represented as a graph in FIG.
  • Condition (I) is a condition in which at least one of the average values of the three vertical pixel values is larger than the most frequent pixel value in the three horizontal width pixels to be determined.
  • Condition (II) is a condition that the average value of the vertical pixel values at the left end of the three horizontal pixels to be determined is 5 or more larger than the average value of the vertical pixel values adjacent to the left side.
  • Condition (III) is a condition that the average value of the vertical pixel values at the right end of the three horizontal pixels to be determined is 5 or more larger than the average value of the vertical pixel values adjacent to the right. .
  • the remaining edge point extraction unit 2d has a width of 3 pixels that is the determination target in step S13.
  • the bright vertical thin line means a thin linear region having a large pixel value along the short direction of the banknote to be determined that is not included in the captured image of the legitimate banknote. This bright vertical line is generated by a strong crease.
  • the remaining edge point extraction unit 2d is the horizontal direction that is the determination target in step S13. It is estimated that the width of 3 pixels is not a bright vertical thin line (step S15).
  • step S13 onward is repeated while sliding the horizontal width of 3 pixels, which is the determination target in step S13, in the horizontal direction one pixel at a time.
  • the edge points included in the bright vertical thin line and one pixel on both sides thereof are extracted by the edge point extracting unit 2c. Removed from.
  • an edge point appearing by a thin line-shaped region having a large pixel value along the short direction of the banknote to be discriminated that is not included in the captured image of the valid banknote is erroneously determined as an edge point by the side edge of the tape. It is possible to prevent detection.
  • each determination condition used in step S13 is merely an example, and the threshold value used in the determination condition is not particularly limited.
  • the above-described second estimation process can be performed independently regardless of the detection of tape sticking.
  • it has a function of detecting a strong broken line (strong broken line).
  • the analysis unit 2e synthesizes the edge point image indicating the remaining edge point in the A direction range and the edge point image indicating the remaining edge point in the B direction range sent from the remaining edge point extracting unit 2d, and the synthesized image Then, a density detection filter is applied to detect the density of remaining edge points in a predetermined size region as a pixel value.
  • the analysis unit 2e detects the side edge of the tape when the density of remaining edge points in a predetermined size area detected as a pixel value exceeds a threshold value stored in the storage unit 3 as analysis reference information 3d. In this embodiment, both the right tape side edge and the left tape side edge are detected. For this reason, even if one of the right tape side edge and the left tape side edge is in a position where it overlaps with the thread portion of the banknote, the other tape side edge can be detected, and tape sticking can be detected. it can.
  • the predetermined size region is formed in a vertically long shape, for example, the density detection filter shown in FIG. 11 can be used, and when the predetermined size region is formed in an inclined shape, for example, the density detection filter shown in FIG. Can be used.
  • the predetermined size area vertically long, it is possible to detect tapes that are stuck vertically (short direction of the paper), and by making the predetermined size area inclined diagonally, the tape is attached obliquely. The detected tape can be detected.
  • the side edge of the tape is detected independently without combining the edge point image indicating the remaining edge point in the A direction range and the edge point image indicating the remaining edge point in the B direction range. You may make it do.
  • detection of the right side edge of the right tape and detection of the left side edge of the left tape can be performed separately. For example, even if one of the right side tape side end and the left side tape side end overlaps the bill thread portion, the other tape side end can be detected, and the other tape side end Since it can be grasped whether it is a right tape side edge or a left tape side edge, a tape sticking can be detected and a tape sticking position can be estimated.
  • the banknote discriminating apparatus 10 extracts an edge point and discriminates whether or not a tape is stuck on the banknote. However, it is also assumed that the edge generated by the side edge of the affixed tape is not clear. For this reason, it is desirable to be able to detect that the tape is stuck on the banknote without extracting the edge point.
  • the bill discriminating apparatus 20 has a function capable of detecting that the tape is stuck on the bill without extracting the edge point, according to the first embodiment of the present invention.
  • the configuration is added to the apparatus 10.
  • FIG. 13 is a block diagram showing a configuration of the bill discriminating apparatus 20.
  • the same parts as those in FIG. 2 are denoted by the same reference numerals, and detailed description thereof is omitted.
  • the control unit 2 of the bill discriminating apparatus 20 includes a boundary detection unit 2f and a determination unit in addition to the image data acquisition unit 2a, denomination identification unit 2b, edge point extraction unit 2c, remaining edge point extraction unit 2d, and analysis unit 2e. 2g.
  • the storage unit 3 stores detection standard information 3e and determination standard information 3f in addition to the denomination identification template 3a, various filters 3b, reference edge points 3c, and analysis standard information 3d.
  • the boundary detection unit 2f uses the image data generated by the image data acquisition unit 2a and is darker than the first region from the first region in the direction from one end to the other end in the longitudinal direction of the bill to be determined. A first boundary portion that is a boundary that changes to the second region and a second boundary portion that is a boundary that changes from the third region to the fourth region that is brighter than the third region are detected.
  • one end in the longitudinal direction of the banknote to be discriminated is set as the left end of the banknote, and the other end in the longitudinal direction of the banknote to be discriminated is set as the right end of the banknote. Can be obtained.
  • the boundary detection unit 2f sets a point of interest 4 corresponding to a height of 2 pixels in the horizontal direction in the captured image of the banknote to be discriminated, and sets a left side region 5 of 4 ⁇ 2 pixels adjacent to the left side of the point of interest 4.
  • the right region 6 of 4 ⁇ 2 pixels adjacent to the right side of the point of interest is set (step S21). Therefore, the positional relationship among the point of interest 4, the left region 5, and the right region 6 is as shown in FIG.
  • the number of constituent pixels of each of the point of interest 4, the left region 5, and the right region 6 is not particularly limited. However, the edge point generated by the bill design is prevented from entering each of the point of interest 4, the left region 5, and the right region 6. There is a need.
  • a banknote having no symbol in the vicinity of the upper end is set as a determination target, and the target point 4 is set so that the target point 4 slides in the horizontal direction in the vicinity of the upper end without the symbol.
  • the vertical position of the point of interest 4 is changed according to the horizontal direction of the banknote using the denomination identification template 3a or the like so that the point of interest 4, the left region 5 and the right region 6 do not cover the design of the banknote.
  • the boundary detection unit 2f determines whether or not the point of interest 4 corresponds to “a first boundary that is a boundary where the first region changes to a second region darker than the first region” (step S22). ). In the determination in step S22, if the left region 5 is a bright region and the right region 6 is a dark region, the point of interest 4 corresponds to the first boundary.
  • the storage unit 3 may store the predetermined value and the determination formula used in the determination in step S22 as the detection reference information 3e.
  • the point of interest 4 corresponds to the first boundary.
  • the central pixel value of the left region 5 is larger than the central pixel value of the right region 6 by a predetermined value or more, it can be determined that the point of interest 4 corresponds to the first boundary.
  • the average pixel value of the left area 5 is larger than the average pixel value of the right area 6 by a predetermined value or Even when the central pixel value of the region 5 is larger than the central pixel value of the right region 6 by a predetermined value or more, if the variance of the pixel values of the right region 6 is not less than the predetermined value, the point of interest 4 becomes the first boundary. You may determine that it does not apply.
  • the boundary detection unit 2f When it is determined that the point of interest 4 corresponds to “a first boundary portion that is a boundary where the first region changes to a second region that is darker than the first region” (YES in step S22), the boundary detection unit 2f The point of interest 4 is set as the first boundary (step S23).
  • step S24 when it is determined that the point of interest 4 does not correspond to the “first boundary portion that is a boundary changing from the first region to the second region darker than the first region” (NO in step S22), the point of interest 4 is It is determined whether or not a “second boundary portion that is a boundary changing from the third region to the fourth region brighter than the third region” is satisfied (step S24). In the determination of step S24, if the left area 5 is a dark area and the right area 6 is a bright area, the point of interest 4 corresponds to the second boundary.
  • the storage unit 3 may store the predetermined value and the determination formula used in the determination in step S24 as the detection reference information 3e.
  • the average pixel value of the right area 6 is larger than the average pixel value of the left area 5 by a predetermined value or more, it can be determined that the point of interest 4 corresponds to the second boundary.
  • the central pixel value of the right region 6 is larger than the central pixel value of the left region 5 by a predetermined value or more, it can be determined that the point of interest 4 corresponds to the second boundary.
  • the average pixel value in the right area 6 is larger than the average pixel value in the left area 5 by a predetermined value or on the right side.
  • the attention point 4 becomes the second boundary. You may determine that it does not apply.
  • the boundary detection unit 2f The point of interest 4 is set as the second boundary (step S25).
  • the boundary detection process described above is repeated while the point of interest 4 is slid horizontally by one pixel.
  • the boundary detection unit 2f outputs information on the first boundary and the second boundary determined in steps S23 and S25 to the determination unit 2g.
  • the determination unit 2g uses the first boundary part and the second boundary part detected by the boundary part detection part 2f, and is between the first boundary part and the second boundary part located on the right side of the first boundary part. Based on the pixel value of the pixel located in the area, it is determined whether or not the tape is applied to the area between the first boundary and the second boundary located on the right side of the first boundary.
  • Determination processing executed by the determination unit 2g will be described with reference to the flowchart of FIG.
  • the determination unit 2g selects a combination of the first boundary and the second boundary that can be a combination of the left tape side end and the right tape side end from all combinations of the first boundary portion and the second boundary portion. Extract (step S31).
  • a combination of the first boundary and the second boundary located on the right side of the first boundary is extracted, and further the second boundary located on the right side of the first boundary and the first boundary. Extraction is limited to combinations in which the interval between the parts is not less than the minimum width of the tape to be determined and not more than the maximum width.
  • the combination of the first boundary portion and the second boundary portion is narrowed down in consideration of the width of the tape to be determined, so that the determination time can be shortened and erroneous detection can be prevented.
  • the determination unit 2g pays attention to a certain combination from the combinations extracted in step S31, and determines whether or not the focused first and second boundary portions correspond to the tape application portion ( Step S32).
  • the storage unit 3 may store the predetermined value and the determination formula used in the determination in step S32 as the determination reference information 3f.
  • a tape is applied between the first boundary and the second boundary. Can be determined to fall under the category.
  • the tape between the focused first boundary and the second boundary is tape. It can be determined that it corresponds to the pasting part.
  • the variance of the pixel values in the region between the first boundary and the second boundary is less than a predetermined value, the area between the first boundary and the second boundary is the tape application portion. It can be determined that this is the case.
  • the background pixel values of the banknotes to be discriminated are not uniform. Then, since the pixel value distribution when the tape is affixed to a place where the background density is not uniform is as shown in FIG. 17, if the detection conditions of the first boundary and the second boundary are strict, the first boundary or There is a possibility that the second boundary may not be detected. On the other hand, if the detection conditions at the first boundary and the second boundary are relaxed, the first boundary and the pixel value distribution when the background density is not uniform as shown in FIG. The second boundary will be detected.
  • the average pixel value of the left region 5 shown in FIG. 15 corresponding to the focused first boundary and the right side shown in FIG. 15 corresponding to the focused second boundary is obtained, and a value obtained by subtracting “the average pixel value of the pixels located in the region between the first boundary portion and the second boundary portion of interest” from the sum is obtained.
  • the obtained value is less than the predetermined value
  • the average pixel value of the pixels located in the region between the first boundary portion and the second boundary portion of interest is less than the predetermined value or the first of interest. Even if the central pixel value of the pixel located in the area between the boundary and the second boundary is less than the predetermined value, the area between the first boundary and the second boundary that is focused on corresponds to the tape application part You may decide not to.
  • the determination unit 2g determines the distance between the focused first boundary and the second boundary. Let it be a tape application part (step S33).
  • step S32 when it is determined that the area between the focused first boundary and the second boundary does not correspond to the tape application part (NO in step S32), the flow is ended as it is.
  • step S32 is repeated, and the determination in step S32 is performed for all combinations extracted in step S31.
  • the boundary detection processing and determination processing described above can determine whether the tape is applied without extracting the edge point, so even if the edge generated by the side edge of the applied tape is not clear It is possible to detect that the tape is stuck on the leaves.
  • the determination is performed in consideration of the pixel value distribution in any of the above-described steps S22, S24, and S32. Accordingly, it is possible to prevent erroneous detection of contamination such as ink bleeding as tape sticking.
  • the bill discriminating device 20 has a function capable of detecting that the tape is stuck on the bill by extracting the edge point, and a function capable of detecting that the tape is stuck on the bill without extracting the edge point.
  • the function that can detect that the tape is stuck on the banknote without extracting the edge point explained in detail in the present embodiment is that the edge point is extracted and the tape is stuck on the banknote. It is also possible to carry out the function independently regardless of the function that can detect that it has been detected.
  • the function which can detect that the tape is affixed on a banknote, and a mechanical thickness detection are performed, and it detects that the tape is affixed You may implement in combination with the function which can be performed.
  • the front edge of the paper sheet is larger than the original thickness due to the impact when entering the thickness sensor Since the thickness is detected, there is a problem that it is not possible to determine whether or not the tape is stuck on the front end portion of the paper sheet even if it is not a thin tape.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Toxicology (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Inspection Of Paper Currency And Valuable Securities (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

L'invention concerne un dispositif de détection de feuille de papier pourvu d'une unité d'enregistrement, d'une unité d'extraction de points de bord, d'une unité d'extraction de points de bord résiduels et d'une unité d'analyse. L'unité d'enregistrement enregistre des points de bord de référence, qui sont des points de bord dans une plage de direction de gradient de densité le long de la direction longitudinale d'une feuille de papier valide compris dans une image prise de la feuille de papier valide. L'unité d'extraction de points de bord extrait des points de bord dans une plage de direction de gradient de densité le long de la direction longitudinale de la feuille de papier soumise à détection, à partir d'une image prise de la feuille de papier soumise à détection. L'unité d'extraction de points de bord résiduels élimine, parmi les points de bord extraits par l'unité d'extraction de points de bord, des points de bord qui correspondent aux points de bord de référence et des points de bord supposés apparaître lorsque des pixels qui ne sont pas compris dans l'image prise de la feuille de papier valide sont générés par une région brillante, et extrait des points de bord résiduels. L'unité d'analyse analyse, sur la base des points de bord résiduels, si une bande est fixée ou non à la feuille de papier soumise à détection.
PCT/JP2016/058188 2015-03-31 2016-03-15 Dispositif de détection de feuille de papier et procédé de détection de feuille de papier WO2016158392A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2015071082A JP6534278B2 (ja) 2015-03-31 2015-03-31 紙葉類判別装置及び紙葉類判別方法
JP2015-071082 2015-03-31

Publications (1)

Publication Number Publication Date
WO2016158392A1 true WO2016158392A1 (fr) 2016-10-06

Family

ID=57006699

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2016/058188 WO2016158392A1 (fr) 2015-03-31 2016-03-15 Dispositif de détection de feuille de papier et procédé de détection de feuille de papier

Country Status (2)

Country Link
JP (1) JP6534278B2 (fr)
WO (1) WO2016158392A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114565632A (zh) * 2022-03-03 2022-05-31 上海擎泰仿真科技有限公司 一种确定ct数据物质交界区域边界及物质厚度的方法
CN114627080A (zh) * 2022-03-16 2022-06-14 江苏巨杰机电有限公司 基于计算机视觉的车辆冲压配件缺陷检测方法

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106898085B (zh) * 2017-02-23 2019-06-11 深圳怡化电脑股份有限公司 识别纸币面向的方法及装置
CN107886615B (zh) * 2017-12-15 2020-03-27 深圳怡化电脑股份有限公司 边缘检测方法及验钞设备
WO2025134392A1 (fr) * 2023-12-22 2025-06-26 富士通フロンテック株式会社 Dispositif de manutention de billets, procédé de détection de corps étranger et programme de détection de corps étranger

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11173997A (ja) * 1997-12-12 1999-07-02 Glory Ltd 紙葉類の異物判別装置
JP2000259885A (ja) * 1999-03-10 2000-09-22 Hamamatsu Photonics Kk 紙葉類鑑別装置
US20090310126A1 (en) * 2006-08-18 2009-12-17 De La Rue Internatonal Limited Method and apparatus for raised material detection
JP2010122894A (ja) * 2008-11-19 2010-06-03 Oki Electric Ind Co Ltd 媒体鑑別装置

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011114447A1 (fr) * 2010-03-17 2011-09-22 グローリー株式会社 Dispositif et procédé de discrimination de papier

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11173997A (ja) * 1997-12-12 1999-07-02 Glory Ltd 紙葉類の異物判別装置
JP2000259885A (ja) * 1999-03-10 2000-09-22 Hamamatsu Photonics Kk 紙葉類鑑別装置
US20090310126A1 (en) * 2006-08-18 2009-12-17 De La Rue Internatonal Limited Method and apparatus for raised material detection
JP2010122894A (ja) * 2008-11-19 2010-06-03 Oki Electric Ind Co Ltd 媒体鑑別装置

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114565632A (zh) * 2022-03-03 2022-05-31 上海擎泰仿真科技有限公司 一种确定ct数据物质交界区域边界及物质厚度的方法
CN114627080A (zh) * 2022-03-16 2022-06-14 江苏巨杰机电有限公司 基于计算机视觉的车辆冲压配件缺陷检测方法
CN114627080B (zh) * 2022-03-16 2023-08-25 江苏巨杰机电有限公司 基于计算机视觉的车辆冲压配件缺陷检测方法

Also Published As

Publication number Publication date
JP6534278B2 (ja) 2019-06-26
JP2016192026A (ja) 2016-11-10

Similar Documents

Publication Publication Date Title
WO2016158392A1 (fr) Dispositif de détection de feuille de papier et procédé de détection de feuille de papier
JP5616958B2 (ja) 紙幣検出器デバイスのための方法、および紙幣検出器デバイス
US6741727B1 (en) Apparatus for determining the soil degree of printed matter
US8559748B2 (en) Edge detection
CN101799868B (zh) 纸币机器视觉检测方法
JP5137602B2 (ja) 紙葉類識別装置、及び紙葉類識別方法
EP2660787A1 (fr) Catégorisation de défaut dans une image digitale
JPWO2008026286A1 (ja) 紙葉類識別装置および紙葉類の識別方法
RU2598296C2 (ru) Способ проверки оптического защитного признака ценного документа
KR101781009B1 (ko) 낡은 지폐 식별 방법
CN107134047B (zh) 白水印检测方法及装置
US9042632B2 (en) Method and system for touchless counting of stacked substrates, especially bundled banknotes
WO2019001191A1 (fr) Procédé et dispositif de détection de billet de banque collé
CN106599923B (zh) 一种对印防伪特征的检测方法及装置
US20200084320A1 (en) Print quality diagnosis
CN102915522A (zh) 一种智能手机的名片提取系统及其实现方法
CN106447908B (zh) 一种纸币鉴伪方法及装置
WO2011114447A1 (fr) Dispositif et procédé de discrimination de papier
US9661183B2 (en) Image correction apparatus and method
KR20180020596A (ko) 시뮬레이션을 통한 낡은 지폐 이미지 생성 방법
JP4679953B2 (ja) 紙葉類の損券判定装置、損券判定方法及び損券判定プログラム
JP4319173B2 (ja) 紙葉類処理装置
JP3756250B2 (ja) 紙葉類の真偽判別装置
AU2017332227A1 (en) Method and device for detecting color fading on a value document, in particular a banknote, and value-document processing system
NL2011739C2 (en) Banknote counterfeit classification.

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: 16772275

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: 16772275

Country of ref document: EP

Kind code of ref document: A1