WO2016119410A1 - 钞票裂缝检测方法及装置 - Google Patents

钞票裂缝检测方法及装置 Download PDF

Info

Publication number
WO2016119410A1
WO2016119410A1 PCT/CN2015/083862 CN2015083862W WO2016119410A1 WO 2016119410 A1 WO2016119410 A1 WO 2016119410A1 CN 2015083862 W CN2015083862 W CN 2015083862W WO 2016119410 A1 WO2016119410 A1 WO 2016119410A1
Authority
WO
WIPO (PCT)
Prior art keywords
crack
banknote
edge
depth
edge length
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2015/083862
Other languages
English (en)
French (fr)
Inventor
余元超
王荣秋
黄湛峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
GRG Banking Equipment Co Ltd
Original Assignee
GRG Banking Equipment Co Ltd
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 GRG Banking Equipment Co Ltd filed Critical GRG Banking Equipment Co Ltd
Priority to EP15879610.2A priority Critical patent/EP3252710B1/en
Priority to RU2017129563A priority patent/RU2678493C1/ru
Priority to US15/543,551 priority patent/US10319172B2/en
Priority to HK18105762.5A priority patent/HK1246476A1/zh
Publication of WO2016119410A1 publication Critical patent/WO2016119410A1/zh
Anticipated expiration legal-status Critical
Priority to ZA2017/05304A priority patent/ZA201705304B/en
Ceased legal-status Critical Current

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
    • G07D11/00—Devices accepting coins; Devices accepting, dispensing, sorting or counting valuable papers
    • G07D11/20—Controlling or monitoring the operation of devices; Data handling
    • G07D11/22—Means for sensing or detection
    • G07D11/235—Means for sensing or detection for monitoring or indicating operating conditions; for detecting malfunctions
    • G07D11/237—Means for sensing or detection for monitoring or indicating operating conditions; for detecting malfunctions for detecting transport malfunctions, e.g. jams or misfeeds
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/10—Image acquisition
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/88—Image or video recognition using optical means, e.g. reference filters, holographic masks, frequency domain filters or spatial domain filters
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D11/00—Devices accepting coins; Devices accepting, dispensing, sorting or counting valuable papers
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D11/00—Devices accepting coins; Devices accepting, dispensing, sorting or counting valuable papers
    • G07D11/009—Depositing devices
    • 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

Definitions

  • the present invention relates to the field of image processing, and in particular, to a banknote processing method and apparatus.
  • banknote processing technology is no longer limited to basic currency face value recognition and authenticity identification.
  • banknotes of poor quality are easily damaged and should not be circulated in the market.
  • banknotes of poor quality are likely to cause machine failures in self-service equipment, such as heavy banknotes, banknotes, and banknotes.
  • a crack in a banknote is generally one or more cracks in the face of the banknote due to tearing, folding or cutting.
  • the present invention provides a banknote crack detecting device and method, which can accurately detect whether a banknote has cracks and can calculate the crack length of the banknote. And depth, to provide a basis for judging the degree of damage of banknotes, thereby rejecting banknotes with severe cracks, and avoiding problems such as banknotes caused by cracks in banknotes.
  • the banknote crack detecting device comprises: an image collecting unit for collecting an optical transmission image of the input banknote; a preprocessing unit for receiving the banknote image signal collected by the image collecting unit, and implementing a foreground region of the banknote image signal Positioning and cutting; a crack detecting unit, configured to receive an image of the foreground area of the banknote from the pre-processing unit, and detect whether there is a pixel segment having a crack feature at the edge of the foreground area, and if there is a pixel segment having the crack feature, the foreground There is a crack at the edge of the region, and the crack detecting unit continues to detect whether the crack extends to a row or a column deeper than the edge in a manner of detecting whether the edge has a crack, and accumulates the crack edge length and the crack depth; a determining unit is used for Determining whether the banknote is qualified according to the detection result of the banknote crack detecting unit, wherein the rule of determination is: if there are no cracks on the four edges
  • the pixel segment having the crack feature refers to a neighboring pixel segment of a certain step length, and the gray level of the pixel in the pixel segment exceeds a set gray threshold, and the pixel gray gradients at both end points of the pixel segment are Exceeded the set gradient threshold.
  • the invention also provides a banknote crack detecting method, comprising: step 1, inputting a banknote to be detected, the process starts; step 2, collecting an optical transmission image of the input banknote; step 3, detecting the foreground area of the banknote, and foreground After the area is cut, it is placed in the pixel coordinate system; in step 4, it is judged whether there is a crack at the edge of the foreground area, and if so, the process proceeds to step 5, otherwise to step 8; step 5, the cumulative crack edge length CL and the crack depth CH; step 6 And determining that the crack edge length CL is greater than a set threshold or the crack depth CH is greater than a set threshold, if the crack edge length CL is greater than a set threshold or the crack depth CH is greater than a set threshold, proceeding to step 7, otherwise proceeding to step 8; The banknote has a crack, the banknote is rejected, and the process ends; step 8, Receiving the banknote, the process ends.
  • the method for determining whether there is a crack in the edge of the foreground region comprises: sequentially detecting whether the gradation of the pixels in the adjacent pixel segments of a certain step on the upper, lower, left and right edges exceeds the set gray threshold. And whether the pixel gray level gradient at the two endpoints of the pixel segment exceeds a set gradient threshold, and if so, there is a crack at the edge of the foreground region; otherwise, there is no crack at the edge of the foreground region.
  • the method for accumulating the crack edge length CL and the crack depth CH in step 5 comprises: detecting whether the crack extends to a row or a column deeper than the edge according to whether there is a crack in the edge of the foreground region, if the crack is still extended Extension, then continue to accumulate the crack edge length CL and the crack depth CH, and so on to the deeper row or column until the crack or extension to the row or column, while accumulating the crack edge length CL and the crack depth CH.
  • the method for detecting edge cracks in the foreground region comprises:
  • Step 52 Search for a crack starting edge point and a ending edge point in a certain edge pixel of the foreground area, if the points P(x 01 , y 01 ) and P(x 02 , y 01 ) satisfy:
  • gthmax is the maximum value of the gray value of the optical transmission image when the medium has no crack, generally set to 200
  • gthmin is the crack region.
  • P M is the point between P (x 01 , y 01 ) and P (x 02 , y 01 );
  • the crack does not extend to the bank and the crack detection ends;
  • the banknote crack detecting method provided by the invention is based on the optical transmission image imaging principle of the banknote, and the gray scale of the banknote transmission image is closely related to the intensity of the sensor light source and the transmittance of the banknote, and the crack region and the non-crack of the banknote are unchanged when the intensity of the light source is constant.
  • the regional transmittance is very different, and the grayscale of the image in the crack region is concentrated, which is represented by a grayscale uniformity of all pixels from the edge of the banknote.
  • a connected domain of approximately 255. If the connected domain exists on the banknote transmission image, by calculating the length and depth of the connected domain edge and comparing with the preset threshold, it can be determined whether the input banknote is rejected or received.
  • the method has good stability, can accurately detect the crack of the banknote and calculate the length and depth of the crack.
  • FIG. 1 is a schematic diagram showing the logical structure of a banknote crack detecting device according to a preferred embodiment of the present invention
  • FIG. 2 is a flow chart of a method for detecting cracks in a banknote according to a preferred embodiment of the present invention
  • Figure 3 shows an optical transmission image of a banknote in the presence of a crack
  • Figure 4 shows the original image acquired by the optical sensor
  • Figure 5 shows an image of a foreground area of a banknote placed in a coordinate system
  • Figure 6 is a schematic view showing a case where the crack width of the previous row is 1 pixel
  • Fig. 7 is a view showing a case where the crack width of the previous row is 2 pixels.
  • the banknote crack detecting apparatus includes a control unit 10, an image collecting unit 20, a preprocessing unit 30, a crack detecting unit 40, and a determining unit 50.
  • the image acquisition unit 20 is configured to collect an optical transmission image of the input banknote;
  • the pre-processing unit 30 is configured to receive the banknote image signal collected by the image acquisition unit 20, and perform foreground region localization and cutting on the banknote image signal;
  • the detecting unit 40 is configured to receive a banknote foreground area image from the pre-processing unit 30, and detect whether there is a pixel segment having a crack feature at the edge of the foreground area, and if there is a pixel segment having the crack feature, there is a crack at the edge of the foreground area.
  • the crack detecting unit 40 continues to be used in such a manner as to detect whether there is a crack in the edge Detecting whether the crack extends to a row or a column deeper than the edge, and accumulating the crack edge length and the crack depth; the determining unit 50 is configured to determine whether the banknote is qualified according to the detection result of the banknote crack detecting unit, wherein the determining rule is: If there are no cracks on the four edges of the banknote, the incoming banknote is qualified to receive the banknote; if the banknote has a crack, and the length of the crack edge is greater than a set threshold or the crack depth is greater than a set threshold, the input banknote is unqualified.
  • the pixel segment having the crack feature refers to a neighboring pixel segment of a certain step length, and the gray level of the pixel in the pixel segment exceeds a set gray threshold, and the gray scale gradient of the pixel at both end points of the pixel segment exceeds the set Gradient threshold
  • the banknote crack detecting method includes: step 1, inputting a banknote to be detected, the process starts; step 2, collecting an optical transmission image of the input banknote; and step 3, detecting the foreground area of the input banknote, After cutting the foreground area, it is placed in the pixel coordinate system; in step 4, it is judged whether there is a crack at the edge of the foreground area, and if so, the process proceeds to step 5, otherwise proceeds to step 8; step 5, the cumulative crack edge length CL and the crack depth CH Step 6, it is determined that the crack edge length CL is greater than the set threshold or the crack depth CH is greater than the set threshold, if the crack edge length CL is greater than the set threshold or the crack depth CH is greater than the set threshold, then proceeds to step 7, otherwise proceeds to step 8; Step 7, the banknote has a crack, the banknote is rejected, and the process ends; in step 8, the banknote is received, and the process ends.
  • E is the energy of the light source
  • E 0 is the energy absorbed by the medium
  • E 1 is the energy reflected by the medium
  • E 2 is the energy transmitted through the medium, which is directly reflected as the gray value of the transmitted image
  • ⁇ is inherent to the optical transmission imaging system. Energy loss. If the light source passes through the crack, there is
  • the crack detecting scheme of the banknote crack detecting device of the present embodiment searches for such a white connected domain, calculates the length of the connected domain edge and the depth of the connected domain, and determines whether or not the input banknote is received according to the set threshold. The following describes the specific process of the banknote crack detection method:
  • gthmax is the maximum value of the gray value of the optical transmission image when the medium has no crack, generally set to 200
  • gthmin is the crack region.
  • P M is the point between P (x 01 , y 01 ) and P (x 02 , y 01 );
  • the crack does not extend to the bank and the crack detection ends;
  • the length and depth of the crack edge can be detected in a similar search manner, and a final decision is made to decide whether to accept the banknote or reject the banknote. I will not repeat them here.
  • the banknote crack detecting method provided by the invention is based on the optical transmission image imaging principle of the banknote, and the gray scale of the banknote transmission image is closely related to the intensity of the sensor light source and the transmittance of the banknote, and the crack region and the non-crack of the banknote are unchanged when the intensity of the light source is constant.
  • the regional transmittance varies greatly, and the grayscale of the image in the crack region is concentrated, which is expressed as a connected domain in which the gray levels of all the pixels from the edge of the banknote are close to 255. If the connected domain exists on the banknote transmission image, by calculating the length and depth of the connected domain edge and comparing with the preset threshold, it can be determined whether the input banknote is rejected or received.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Multimedia (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Inspection Of Paper Currency And Valuable Securities (AREA)
  • Image Analysis (AREA)
  • Medicines Containing Antibodies Or Antigens For Use As Internal Diagnostic Agents (AREA)

Abstract

一种钞票裂缝检测方法及装置，其包括：图像采集单元（20），用于采集投入钞票的光学透射图像；预处理单元（30），用于接收该图像采集单元采集到的钞票图像信号；裂缝检测单元（40），用于检测是否存在裂缝；判定单元（50），用于判断钞票是否合格；以及控制单元（10），用于控制上述各单元的运行。其能准确检测出钞票是否有裂缝。

Description

钞票裂缝检测方法及装置
本申请要求于2015年01月26日提交中国专利局、申请号为201510038608.8、发明名称为“钞票裂缝检测方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及图像处理领域，特别涉及一种钞票处理方法及装置。
背景技术
金融自助设备如ATM机等的广泛应用对钞票处理技术提出了越来越高的要求，钞票处理技术不再仅仅局限于基本的币种面值识别和真伪鉴别。特别是现金循环技术得到应用以来，钞票的可流通性检测显得越来越重要。一方面质量差的钞票容易损坏，不宜在市面上流通，另一方面质量差的钞票容易引起自助设备机器故障，比如出现重钞、连钞、卡钞等问题。在钞票的可流通性检测中，裂缝钞票的检测是公认的业内难题。钞票裂缝一般是钞票票面由于撕裂、折叠或者裁剪出现的一条或多条裂缝。如果客户在通过ATM机等自助设备交易的过程中有裂缝钞，很可能导致钞票在自助设备通道中走钞时引起设备卡钞，一旦发生卡钞故障，设备就只能停止服务，并通过专业人员清除卡钞后才能继续开通服务，对客户交易造成严重的影响。因此，有效检测出投入钞票是否存在裂缝并判断裂缝严重程度是否可能引起设备卡钞十分关键，钞票裂缝检测已经成为业界必须解决的技术难题。
发明内容
为了解决现有技术中钞票裂缝检测的难题，本发明提供一种钞票裂缝检测装置和方法，能准确检测出钞票是否有裂缝，且能计算钞票裂缝长度 和深度，为判断钞票损毁程度提供判断依据，从而将裂缝严重的钞票拒出，避免钞票裂缝引起设备卡钞等问题。
该钞票裂缝检测装置包括：一图像采集单元，用于采集投入钞票的光学透射图像；一预处理单元，用于接收该图像采集单元采集到的钞票图像信号，并对该钞票图像信号实施前景区域定位和切割；一裂缝检测单元，用于从该预处理单元接收钞票前景区域图像，并检测前景区域边缘是否存在一具有裂缝特征的像素段，如果存在该具有裂缝特征的像素段，则该前景区域边缘存在裂缝，该裂缝检测单元继续用于按照检测边缘是否有裂缝的方式检测该裂缝是否延拓至比边缘更深的一行或者一列，并累计裂缝边缘长度和裂缝深度；一判定单元，用于根据钞票裂缝检测单元的检测结果，判断钞票是否合格，其中该判定规则是：如果钞票四个边缘均无裂缝，则该投入钞票合格，接收该钞票；如果投入钞票有裂缝，并且该裂缝边缘长度大于设定阈值或者该裂缝深度大于设定阈值，则该投入钞票不合格，拒收该钞票；如果投入钞票有裂缝，并且该裂缝边缘长度小于设定阈值且该裂缝深度小于设定阈值，则该投入钞票合格，接收该钞票；以及一控制单元，用于控制上述各单元的运行。
具体的，该具有裂缝特征的像素段是指一定步长的相邻像素段，该像素段内像素的灰度都超过设定灰度阈值，且该像素段两个端点处像素灰度梯度都超过设定的梯度阈值。
本发明还提供一种钞票裂缝检测方法，其包括：步骤1，投入待检测钞票，流程开始；步骤2，采集该投入钞票的光学透射图像；步骤3，检测该投入钞票前景区域，并将前景区域切割后，置于像素坐标系内；步骤4，判断前景区域边缘是否存在裂缝，如果是，则进入步骤5，否则进入步骤8；步骤5，累计裂缝边缘长度CL和裂缝深度CH；步骤6，判断裂缝边缘长度CL大于设定阈值或裂缝深度CH大于设定阈值，满足裂缝边缘长度CL大于设定阈值或裂缝深度CH大于设定阈值，则进入步骤7，否则进入步骤8；步骤7，钞票有裂缝，拒出钞票，流程结束；步骤8， 接收钞票，流程结束。
优选的，步骤4中，判断前景区域边缘是否存在裂缝的方法包括：依次检测上、下、左、右边缘上一定步长的相邻像素段内像素的灰度是否都超过设定灰度阈值，且该像素段两个端点处像素灰度梯度是否超过设定的梯度阈值，如果是，则该前景区域边缘存在裂缝；否则该前景区域边缘不存在裂缝。
优选的，步骤5中累计裂缝边缘长度CL和裂缝深度CH的方法包括：按照检测前景区域边缘是否有裂缝的方式检测该裂缝是否延拓至比该边缘更深的一行或者一列，如果裂缝还在延拓，则继续累计裂缝边缘长度CL和裂缝深度CH，并以此类推至更深的行或列，直至该裂缝未延拓至的该行或该列，同时累计该裂缝边缘长度CL和该裂缝深度CH。
优选的，检测前景区域边缘裂缝的方法包括：
步骤51，初始化设置，设裂缝起始边缘点为PS，裂缝终止边缘点为PE，裂缝宽度Cw＝0，裂缝边缘长度Cl＝0，裂缝深度Ch＝0；
步骤52，搜索位于前景区域某一边缘像素中的裂缝起始边缘点和终止边缘点，如果点P(x01,y01)和P(x02,y01)满足：
Figure PCTCN2015083862-appb-000001
   (式3)；
其中x02-x01-1<＝2表示裂缝区域在前景区域图像上的宽度不超过2个像素，gthmax为介质没有裂缝时光学透射图像灰度最大值，一般设置为200，gthmin为裂缝区域光学透射图像灰度最小值，一般设置为250，PM为P(x01,y01)和P(x02,y01)之间的点；
则，更新PS＝P(x01,y01)，PE＝P(x02,y01)，CL＝Cl+2，CH＝Ch+1；
步骤53，当Cw＝1，即P(x01,y01)和P(x02,y01)之间有1个像素时，有
Figure PCTCN2015083862-appb-000002
   (式4)；
①如果
Figure PCTCN2015083862-appb-000003
   (式5)；
则更新该行裂缝起始点PS＝P(x01-1,y01+1)，终止点PE＝P(x01+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
②如果
Figure PCTCN2015083862-appb-000004
   (式6)；
则更新该行裂缝起始点PS＝P(x01+1,y01+1)，终止点PE＝P(x02+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
③如果
Figure PCTCN2015083862-appb-000005
   (式7)；
则更新该行裂缝起始点PS＝P(x01-1,y01+1)，终止点PE＝P(x02,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝2；
④如果
Figure PCTCN2015083862-appb-000006
   (式8)；
则更新该行裂缝起始点PS＝P(x01,y01+1)，终止点PE＝P(x02+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝2；
步骤54，当Cw＝2，即PS和PE之间有2个像素时，有
Figure PCTCN2015083862-appb-000007
   (式9)；
①如果
Figure PCTCN2015083862-appb-000008
   (式10)；
则更新该行裂缝起始点PS＝P(x01-1,y01+1)，终止点PE＝P(x01+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
②如果
Figure PCTCN2015083862-appb-000009
   (式11)；
则更新该行裂缝起始点PS＝P(x01,y01+1)，终止点PE＝P(x01+2,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
③如果
Figure PCTCN2015083862-appb-000010
   (式12)；
则更新该行裂缝起始点PS＝P(x01+1,y01+1)，终止点PE＝P(x01+3,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
④如果
Figure PCTCN2015083862-appb-000011
   (式13)；
则更新该行裂缝起始点PS＝P(x01+2,y01+1)，终止点PE＝P(x02+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
⑤如果
Figure PCTCN2015083862-appb-000012
   (式14)；
则更新该行裂缝起始点PS＝P(x01-1,y01+1)，终止点PE＝P(x01+2,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝2；
⑥如果
Figure PCTCN2015083862-appb-000013
   (式15)；
则更新该行裂缝起始点PS＝P(x01,y01+1)，终止点PE＝P(x01+3,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝2；
⑦如果
Figure PCTCN2015083862-appb-000014
   (式16)；
则更新该行裂缝起始点PS＝P(x01+1,y01+1)，终止点PE＝P(x02+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝2；
其他情况下，该裂缝未延伸到本行，裂缝检测结束；
步骤55，迭代计算，如果Cw＝1，重复执行步骤53；如果Cw＝2，重复执行步骤54，直到实现对一条裂缝的完全检测。
本发明提供的钞票裂缝检测方法根据钞票光学透射图像成像原理，钞票透射图像灰度与传感器光源强度和钞票的透光度紧密相关，在光源强度不变的情况下，钞票的裂缝区域和非裂缝区域透过率差异巨大，并且裂缝区域内图像灰度集中，表现为一个从钞票边缘开始的所有像素点灰度均接 近于255的连通域。如果钞票透射图像上存在上述连通域，通过计算连通域边缘长度和深度并和预设阈值进行比较判定，能决定对投入钞票是拒钞还是接收。该方法稳定性好，能准确检测出钞票裂缝以及计算出裂缝的长度和深度。
附图说明
图1是本发明一较佳实施例提供的钞票裂缝检测装置逻辑结构示意图；
图2是本发明一较佳实施例提供的钞票裂缝检测方法流程图；
图3表示钞票存在裂缝时的光学透射图像；
图4表示光学传感器采集到的原始图像；
图5表示置于坐标系中的钞票前景区域图像；
图6表示前一行裂缝宽度为1个像素时的示意图；
图7表示前一行裂缝宽度为2个像素时的示意图。
具体实施方式
为进一步阐述本发明所提供的钞票裂缝检测装置和方法，本实施方式结合图示进行详细说明。
如图1所示，本实施例提供的钞票裂缝检测装置包括一控制单元10、一图像采集单元20、一预处理单元30、一裂缝检测单元40以及一判定单元50。该图像采集单元20用于采集投入钞票的光学透射图像；该预处理单元30用于接收该图像采集单元20采集到的钞票图像信号，并对该钞票图像信号实施前景区域定位和切割；该裂缝检测单元40用于从该预处理单元30接收钞票前景区域图像，并检测前景区域边缘是否存在一具有裂缝特征的像素段，如果存在该具有裂缝特征的像素段，则该前景区域边缘存在裂缝，该裂缝检测单元40继续用于按照检测边缘是否有裂缝的方式 检测该裂缝是否延拓至比边缘更深的一行或者一列，并累计裂缝边缘长度和裂缝深度；该判定单元50用于根据钞票裂缝检测单元的检测结果，判断钞票是否合格，其中该判定规则是：如果钞票四个边缘均无裂缝，则该投入钞票合格，接收该钞票；如果投入钞票有裂缝，并且该裂缝边缘长度大于设定阈值或者该裂缝深度大于设定阈值，则该投入钞票不合格，拒收该钞票；如果投入钞票有裂缝，并且该裂缝边缘长度小于设定阈值且该裂缝深度小于设定阈值，则该投入钞票合格，接收该钞票；该控制单元10用于控制上述各单元的运行。其中该具有裂缝特征的像素段是指一定步长的相邻像素段，该像素段内像素的灰度都超过设定灰度阈值，且该像素段两个端点处像素灰度梯度都超过设定的梯度阈值
如图2所示，本实施例提供的钞票裂缝检测方法包括：步骤1，投入待检测钞票，流程开始；步骤2，采集该投入钞票的光学透射图像；步骤3，检测该投入钞票前景区域，并将前景区域切割后，置于像素坐标系内；步骤4，判断前景区域边缘是否存在裂缝，如果是，则进入步骤5，否则进入步骤8；步骤5，累计裂缝边缘长度CL和裂缝深度CH；步骤6，判断裂缝边缘长度CL大于设定阈值或裂缝深度CH大于设定阈值，满足裂缝边缘长度CL大于设定阈值或裂缝深度CH大于设定阈值，则进入步骤7，否则进入步骤8；步骤7，钞票有裂缝，拒出钞票，流程结束；步骤8，接收钞票，流程结束。
以下详细介绍该钞票裂缝检测方法的原理和各步骤详细内容：
在钞票经过光学透射传感器成像的过程中，存在如下的能量方程：
E＝E0+E1+E2+ε，   (式1)；
其中E为光源能量，E0为被介质吸收的能量，E1为本介质反射的能量，E2为透过介质的能量，直接反映为透射图像的灰度值，ε为光学透射成像系统固有的能量损失。如果光源从裂缝穿过，则有
Figure PCTCN2015083862-appb-000015
   (式2)；
表现为透过介质裂缝区域的能量大幅增加，反映在透射图像上即是图像灰度值接近255，整个钞票裂缝区域则呈现为宽度为1-2个像素的白色连通域，如图3所示。本实施例的钞票裂缝检测装置的裂缝检测方案即是搜索到这样的白色连通域，并计算连通域边缘的长度以及连通域的深度，并根据设定阈值判定该投入钞票是否接收。以下说明钞票裂缝检测方法的具体过程：
1.初始化设置，设裂缝起始边缘点PS和终止边缘点PE，裂缝宽度Cw＝0，裂缝边缘长度Cl＝0，裂缝深度Ch＝0。
2.开始流程，投入钞票，采集钞票的光学透射图像，设图像传感器分辨率为wdpi，设变量CL和CH分别表示裂缝边缘长度和裂缝深度，采集到的钞票透射图像如图4所示。
3.图像切割，检测前景区域边缘，将前景区域切割出来并置于像素坐标系xoy中，其中前景区域左下顶点位于坐标系坐标原点，设前景区域高度H，宽度W，如图5所示。
4.前景区域上边缘的裂缝检测：
(1)搜索位于前景区域上边缘像素中的裂缝起始边缘点和终止边缘点，如果点P(x01,y01)和P(x02,y01)满足：
Figure PCTCN2015083862-appb-000016
    (式3)；
其中x02-x01-1<＝2表示裂缝区域在前景区域图像上的宽度不超过2个像素，gthmax为介质没有裂缝时光学透射图像灰度最大值，一般设置为200，gthmin为裂缝区域光学透射图像灰度最小值，一般设置为250，PM为P(x01,y01)和P(x02,y01)之间的点；
则，更新PS＝P(x01,y01)，PE＝P(x02,y01)，CL＝Cl+2，CH＝Ch+1；
(2)，当Cw＝1，即P(x01,y01)和P(x02,y01)之间有1个像素时，有
Figure PCTCN2015083862-appb-000017
   (式4)；
①如果
Figure PCTCN2015083862-appb-000018
   (式5)；
则更新该行裂缝起始点PS＝P(x01-1,y01+1)，终止点PE＝P(x01+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
②如果
Figure PCTCN2015083862-appb-000019
   (式6)；
则更新该行裂缝起始点PS＝P(x01+1,y01+1)，终止点PE＝P(x02+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
③如果
Figure PCTCN2015083862-appb-000020
   (式7)；
则更新该行裂缝起始点PS＝P(x01-1,y01+1)，终止点PE＝P(x02,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝2；
④如果
Figure PCTCN2015083862-appb-000021
   (式8)；
则更新该行裂缝起始点PS＝P(x01,y01+1)，终止点PE＝P(x02+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝2；
(3)，当Cw＝2，即PS和PE之间有2个像素时，有
Figure PCTCN2015083862-appb-000022
   (式9)；
①如果
Figure PCTCN2015083862-appb-000023
   (式10)；
则更新该行裂缝起始点PS＝P(x01-1,y01+1)，终止点PE＝P(x01+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
②如果
Figure PCTCN2015083862-appb-000024
   (式11)；
则更新该行裂缝起始点PS＝P(x01,y01+1)，终止点PE＝P(x01+2,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
③如果
Figure PCTCN2015083862-appb-000025
   (式12)；
则更新该行裂缝起始点PS＝P(x01+1,y01+1)，终止点PE＝P(x01+3,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
④如果
Figure PCTCN2015083862-appb-000026
   (式13)；
则更新该行裂缝起始点PS＝P(x01+2,y01+1)，终止点PE＝P(x02+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
⑤如果
Figure PCTCN2015083862-appb-000027
   (式14)；
则更新该行裂缝起始点PS＝P(x01-1,y01+1)，终止点PE＝P(x01+2,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝2；
⑥如果
Figure PCTCN2015083862-appb-000028
   (式15)；
则更新该行裂缝起始点PS＝P(x01,y01+1)，终止点PE＝P(x01+3,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝2；
⑦如果
Figure PCTCN2015083862-appb-000029
   (式16)；
则更新该行裂缝起始点PS＝P(x01+1,y01+1)，终止点PE＝P(x02+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝2；
其他情况下，该裂缝未延伸到本行，裂缝检测结束；
(4)，迭代计算，如果Cw＝1，重复执行(2)；如果Cw＝2，重复执行(3)，直到实现对一条裂缝的完全检测。
最后，如果CH>CHth或者CL>CLth，也就是说，CH大于其预设阈值，或者CL大于其预设阈值，则拒收投入钞票，否则接收投入钞票。
如果投入钞票在左边缘、右边缘或者下边缘存在裂缝，也可以按照类似的搜索方式，完成对裂缝边缘长度和深度的检测，并作出最终判定，决定接收钞票或拒出钞票。在此不再赘述。
本发明提供的钞票裂缝检测方法根据钞票光学透射图像成像原理，钞票透射图像灰度与传感器光源强度和钞票的透光度紧密相关，在光源强度不变的情况下，钞票的裂缝区域和非裂缝区域透过率差异巨大，并且裂缝区域内图像灰度集中，表现为一个从钞票边缘开始的所有像素点灰度均接近于255的连通域。如果钞票透射图像上存在上述连通域，通过计算连通域边缘长度和深度并和预设阈值进行比较判定，能决定对投入钞票是拒钞还是接收。
以上仅是本发明的优选实施方式，应当指出的是，上述优选实施方式不应视为对本发明的限制，本发明的保护范围应当以权利要求所限定的范围为准。对于本技术领域的普通技术人员来说，在不脱离本发明的精神和范围内，还可以做出若干改进和润饰，这些改进和润饰也应视为本发明的保护范围。

Claims (6)

  1. 一种钞票裂缝检测装置，其包括：
    一图像采集单元，用于采集投入钞票的光学透射图像；
    一预处理单元，用于接收该图像采集单元采集到的钞票图像信号，并对该钞票图像信号实施前景区域定位和切割；
    一裂缝检测单元，用于从该预处理单元接收钞票前景区域图像，并检测前景区域边缘是否存在一具有裂缝特征的像素段，如果存在该具有裂缝特征的像素段，则该前景区域边缘存在裂缝，该裂缝检测单元继续用于按照检测边缘是否有裂缝的方式检测该裂缝是否延拓至比边缘更深的一行或者一列，并累计裂缝边缘长度和裂缝深度；
    一判定单元，用于根据钞票裂缝检测单元的检测结果，判断钞票是否合格，其中该判定规则是：如果钞票四个边缘均无裂缝，则该投入钞票合格，接收该钞票；如果投入钞票有裂缝，并且该裂缝边缘长度大于设定阈值或者该裂缝深度大于设定阈值，则该投入钞票不合格，拒收该钞票；如果投入钞票有裂缝，并且该裂缝边缘长度小于设定阈值且该裂缝深度小于设定阈值，则该投入钞票合格，接收该钞票；以及
    一控制单元，用于控制上述各单元的运行。
  2. 如权利要求1所述的钞票裂缝检测装置，其特征在于，该具有裂缝特征的像素段是指一定步长的相邻像素段，该像素段内像素的灰度都超过设定灰度阈值，且该像素段两个端点处像素灰度梯度都超过设定的梯度阈值。
  3. 一种钞票裂缝检测方法，包括：
    步骤1，投入待检测钞票，流程开始；
    步骤2，采集该投入钞票的光学透射图像；
    步骤3，检测该投入钞票前景区域，并将前景区域切割后，置于像素坐标系内；
    步骤4，判断前景区域边缘是否存在裂缝，如果是，则进入步骤5，否则进入步骤8；
    步骤5，累计裂缝边缘长度CL和裂缝深度CH；
    步骤6，判断裂缝边缘长度CL大于设定阈值或裂缝深度CH大于设定阈值，满足裂缝边缘长度CL大于设定阈值或裂缝深度CH大于设定阈值，则进入步骤7，否则进入步骤8；
    步骤7，钞票有裂缝，拒出钞票，流程结束；
    步骤8，接收钞票，流程结束。
  4. 如权利要求3所述的钞票裂缝检测方法，其特征在于，步骤4中，判断前景区域边缘是否存在裂缝的方法包括：依次检测上、下、左、右边缘上一定步长的相邻像素段内像素的灰度是否都超过设定灰度阈值，且该像素段两个端点处像素灰度梯度是否超过设定的梯度阈值，如果是，则该前景区域边缘存在裂缝；否则该前景区域边缘不存在裂缝。
  5. 如权利要求4所述的钞票裂缝检测方法，其特征在于，步骤5中累计裂缝边缘长度CL和裂缝深度CH的方法包括：按照检测前景区域边缘是否有裂缝的方式检测该裂缝是否延拓至比该边缘更深的一行或者一列，如果裂缝还在延拓，则继续累计裂缝边缘长度CL和裂缝深度CH，并以此类推至更深的行或列，直至该裂缝未延拓至的该行或该列，同时累计该裂缝边缘长度CL和该裂缝深度CH。
  6. 如权利要求5所述的钞票裂缝检测方法，其特征在于，检测前景区域边缘裂缝的方法包括：
    步骤51，初始化设置，设裂缝起始边缘点为PS，裂缝终止边缘点为PE，裂缝宽度Cw＝0，裂缝边缘长度Cl＝0，裂缝深度Ch＝0；
    步骤52，搜索位于前景区域某一边缘像素中的裂缝起始边缘点和终止边缘点，如果点P(x01,y01)和P(x02,y01)满足：
    Figure PCTCN2015083862-appb-100001
    其中x02-x01-1<＝2表示裂缝区域在前景区域图像上的宽度不超过2个像素，gthmax为介质没有裂缝时光学透射图像灰度最大值，一般设置为200，gthmin为裂缝区域光学透射图像灰度最小值，一般设置为250，PM为P(x01,y01)和P(x02,y01)之间的点；
    则，更新PS＝P(x01,y01)，PE＝P(x02,y01)，CL＝Cl+2，CH＝Ch+1；
    步骤53，当Cw＝1，即P(x01,y01)和P(x02,y01)之间有1个像素时，有
    Figure PCTCN2015083862-appb-100002
    ①如果
    Figure PCTCN2015083862-appb-100003
    则更新该行裂缝起始点PS＝P(x01-1,y01+1)，终止点PE＝P(x01+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
    ②如果
    Figure PCTCN2015083862-appb-100004
    则更新该行裂缝起始点PS＝P(x01+1,y01+1)，终止点PE＝P(x02+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
    ③如果
    Figure PCTCN2015083862-appb-100005
    则更新该行裂缝起始点PS＝P(x01-1,y01+1)，终止点PE＝P(x02,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝2；
    ④如果
    Figure PCTCN2015083862-appb-100006
    则更新该行裂缝起始点PS＝P(x01,y01+1)，终止点PE＝P(x02+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝2；
    步骤54，当Cw＝2，即PS和PE之间有2个像素时，有
    Figure PCTCN2015083862-appb-100007
    ①如果
    Figure PCTCN2015083862-appb-100008
    则更新该行裂缝起始点PS＝P(x01-1,y01+1)，终止点PE＝P(x01+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
    ②如果
    Figure PCTCN2015083862-appb-100009
    则更新该行裂缝起始点PS＝P(x01,y01+1)，终止点PE＝P(x01+2,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
    ③如果
    Figure PCTCN2015083862-appb-100010
    则更新该行裂缝起始点PS＝P(x01+1,y01+1)，终止点PE＝P(x01+3,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
    ④如果
    Figure PCTCN2015083862-appb-100011
    则更新该行裂缝起始点PS＝P(x01+2,y01+1)，终止点PE＝P(x02+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝1；
    ⑤如果
    Figure PCTCN2015083862-appb-100012
    则更新该行裂缝起始点PS＝P(x01-1,y01+1)，终止点PE＝P(x01+2,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝2；
    ⑥如果
    Figure PCTCN2015083862-appb-100013
    则更新该行裂缝起始点PS＝P(x01,y01+1)，终止点PE＝P(x01+3,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝2；
    ⑦如果
    Figure PCTCN2015083862-appb-100014
    则更新该行裂缝起始点PS＝P(x01+1,y01+1)，终止点PE＝P(x02+1,y01+1)，裂缝边缘长度CL＝Cl+2，裂缝深度CH＝Ch+1，裂缝宽度Cw＝2；
    其他情况下，该裂缝未延伸到本行，裂缝检测结束；
    步骤55，迭代计算，如果Cw＝1，重复执行步骤53；如果Cw＝2，重复执行步骤54，直到实现对一条裂缝的完全检测。
PCT/CN2015/083862 2015-01-26 2015-07-13 钞票裂缝检测方法及装置 Ceased WO2016119410A1 (zh)

Priority Applications (5)

Application Number Priority Date Filing Date Title
EP15879610.2A EP3252710B1 (en) 2015-01-26 2015-07-13 Banknote crack detection method and apparatus
RU2017129563A RU2678493C1 (ru) 2015-01-26 2015-07-13 Способ и устройство обнаружения надрыва банкноты
US15/543,551 US10319172B2 (en) 2015-01-26 2015-07-13 Banknote crack detection method and apparatus
HK18105762.5A HK1246476A1 (zh) 2015-01-26 2015-07-13 钞票裂缝检测方法及装置
ZA2017/05304A ZA201705304B (en) 2015-01-26 2017-08-04 Banknote crack detection method and apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510038608.8 2015-01-26
CN201510038608.8A CN104504727B (zh) 2015-01-26 2015-01-26 钞票裂缝检测方法及装置

Publications (1)

Publication Number Publication Date
WO2016119410A1 true WO2016119410A1 (zh) 2016-08-04

Family

ID=52946121

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/083862 Ceased WO2016119410A1 (zh) 2015-01-26 2015-07-13 钞票裂缝检测方法及装置

Country Status (8)

Country Link
US (1) US10319172B2 (zh)
EP (1) EP3252710B1 (zh)
CN (1) CN104504727B (zh)
HK (1) HK1246476A1 (zh)
RU (1) RU2678493C1 (zh)
TR (1) TR201907436T4 (zh)
WO (1) WO2016119410A1 (zh)
ZA (1) ZA201705304B (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107730706A (zh) * 2017-09-11 2018-02-23 深圳怡化电脑股份有限公司 一种纸币识别方法、装置、终端设备及可读存储介质
CN108073927A (zh) * 2016-11-18 2018-05-25 深圳怡化电脑股份有限公司 一种字符识别方法及装置
CN111260616A (zh) * 2020-01-13 2020-06-09 三峡大学 一种基于Canny算子二维阈值分割优化的绝缘子裂纹检测方法

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104504727B (zh) * 2015-01-26 2018-01-12 广州广电运通金融电子股份有限公司 钞票裂缝检测方法及装置
CN104809800B (zh) * 2015-04-14 2017-09-29 深圳怡化电脑股份有限公司 提取纸币拼接痕迹的预处理方法、拼接钞识别方法及装置
CN104851184B (zh) * 2015-05-27 2017-06-30 深圳怡化电脑股份有限公司 一种横向拼接纸币的识别方法及装置
CN108109284B (zh) * 2017-12-05 2020-08-18 深圳怡化电脑股份有限公司 存款业务处理方法、设备及计算机可读存储介质
CN108492446B (zh) * 2018-02-07 2020-09-15 深圳怡化电脑股份有限公司 一种纸币边缘查找方法以及系统
CN113139927B (zh) * 2020-01-02 2024-12-06 深圳怡化电脑股份有限公司 纸币裂痕检测方法、装置、设备及可读介质
CN118037734B (zh) * 2024-04-12 2024-06-18 济宁丰玺生物材料有限公司 一种全降解塑料制品质量检测方法
CN120807490B (zh) * 2025-09-02 2025-11-18 安康市汉滨区周林生态农业开发有限公司 一种茶叶破壁率检测方法、设备及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010117803A (ja) * 2008-11-12 2010-05-27 Hitachi Omron Terminal Solutions Corp 紙葉類処理装置及び紙葉類処理プログラム
CN101833815A (zh) * 2010-01-20 2010-09-15 上海古鳌电子机械有限公司 一种纸币清分机的图像识别系统及其控制方法
CN102236897A (zh) * 2011-05-09 2011-11-09 哈尔滨工业大学 基于纸币退化能量函数的清分机纸币新旧和残缺检测方法
CN203950377U (zh) * 2014-07-08 2014-11-19 国家电网公司 一种电力自助缴费终端内置纸币识别器
CN104504727A (zh) * 2015-01-26 2015-04-08 广州广电运通金融电子股份有限公司 钞票裂缝检测方法及装置

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
SU1575210A1 (ru) * 1988-04-19 1990-06-30 Институт кибернетики им.В.М.Глушкова Устройство дл оптического контрол документов
DE19517194A1 (de) * 1995-05-11 1996-11-14 Giesecke & Devrient Gmbh Vorrichtung und Verfahren zur Prüfung von Blattgut, wie z.B. Banknoten oder Wertpapiere
JP4374143B2 (ja) * 2000-10-20 2009-12-02 日立オムロンターミナルソリューションズ株式会社 紙幣判別装置および紙幣判別装置を備えた紙幣自動取引装置
JP3846695B2 (ja) * 2001-07-30 2006-11-15 日立オムロンターミナルソリューションズ株式会社 紙幣自動取引装置
DE10242398B4 (de) * 2002-09-12 2007-03-22 Giesecke & Devrient Gmbh Vorrichtung für die Überprüfung des Zustands von Banknoten
US8041107B2 (en) * 2004-09-07 2011-10-18 National Printing Bureau, Incorporated Administrative Agency OVD (optical variable device) inspection method and inspection apparatus
GB0427484D0 (en) 2004-12-15 2005-01-19 Money Controls Ltd Acceptor device for sheet objects
WO2007044570A2 (en) * 2005-10-05 2007-04-19 Cummins-Allison Corp. Currency processing system with fitness detection
JP5635968B2 (ja) * 2011-12-26 2014-12-03 日立オムロンターミナルソリューションズ株式会社 紙幣取扱装置及び現金自動取引装置
US8983168B2 (en) * 2012-04-30 2015-03-17 Ncr Corporation System and method of categorising defects in a media item
DE102012223472A1 (de) * 2012-12-17 2014-06-18 Bundesdruckerei Gmbh Verfahren und Vorrichtung zur Herstellung eines Wert- und/oder Sicherheitsdokuments mit einer Antennenstruktur
CN103324946B (zh) 2013-07-11 2016-08-17 广州广电运通金融电子股份有限公司 一种纸币识别分类的方法及系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010117803A (ja) * 2008-11-12 2010-05-27 Hitachi Omron Terminal Solutions Corp 紙葉類処理装置及び紙葉類処理プログラム
CN101833815A (zh) * 2010-01-20 2010-09-15 上海古鳌电子机械有限公司 一种纸币清分机的图像识别系统及其控制方法
CN102236897A (zh) * 2011-05-09 2011-11-09 哈尔滨工业大学 基于纸币退化能量函数的清分机纸币新旧和残缺检测方法
CN203950377U (zh) * 2014-07-08 2014-11-19 国家电网公司 一种电力自助缴费终端内置纸币识别器
CN104504727A (zh) * 2015-01-26 2015-04-08 广州广电运通金融电子股份有限公司 钞票裂缝检测方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3252710A4 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108073927A (zh) * 2016-11-18 2018-05-25 深圳怡化电脑股份有限公司 一种字符识别方法及装置
CN107730706A (zh) * 2017-09-11 2018-02-23 深圳怡化电脑股份有限公司 一种纸币识别方法、装置、终端设备及可读存储介质
CN107730706B (zh) * 2017-09-11 2019-08-27 深圳怡化电脑股份有限公司 一种纸币识别方法、装置、终端设备及可读存储介质
CN111260616A (zh) * 2020-01-13 2020-06-09 三峡大学 一种基于Canny算子二维阈值分割优化的绝缘子裂纹检测方法

Also Published As

Publication number Publication date
EP3252710B1 (en) 2019-05-15
ZA201705304B (en) 2019-07-31
US20180025571A1 (en) 2018-01-25
HK1246476A1 (zh) 2018-09-07
US10319172B2 (en) 2019-06-11
CN104504727B (zh) 2018-01-12
RU2678493C1 (ru) 2019-01-29
EP3252710A1 (en) 2017-12-06
TR201907436T4 (tr) 2019-06-21
EP3252710A4 (en) 2018-01-17
CN104504727A (zh) 2015-04-08

Similar Documents

Publication Publication Date Title
WO2016119410A1 (zh) 钞票裂缝检测方法及装置
Wang et al. Research on crack detection algorithm of the concrete bridge based on image processing
CN106296974B (zh) 一种粘贴钞检测方法和装置
EP2660787B1 (en) Defect Categorisation in a digital image
CN107481393B (zh) 一种拼接票据的检测方法及拼接票据的检测装置
CN108698774A (zh) 对移动玻璃卷材进行边缘表面检查的方法和设备
WO2015096535A1 (zh) 残缺或变形的四边形图像的校正方法
WO2016078455A1 (zh) 纸币褶皱的识别装置和方法
WO2016037523A1 (zh) 一种基于清分机积灰条件下的钞票识别方法及清分机
JP6534278B2 (ja) 紙葉類判別装置及び紙葉類判別方法
KR101328204B1 (ko) 열간 슬라브의 스크래치 검출 장치 및 방법
CN107481391A (zh) 纸币涂鸦的检测方法及装置
CN106447897A (zh) 一种检测纸币磁性特征的方法及装置
US9047723B2 (en) Defect categorization
CN109767543B (zh) 一种纸币检测方法和系统
CN106447908A (zh) 一种纸币鉴伪方法及装置
CN106296975A (zh) 一种美元纸币面值的识别方法及装置
CN102592351B (zh) 纸页类介质的鉴别方法
CN102592352A (zh) 纸页类介质识别装置及识别方法
CN106780958B (zh) 检测纸币在厚度传感器的检测范围上越界的方法和装置
CN106596590A (zh) 托盘ic检测方法
CN107218929B (zh) 一种基于机器视觉技术的水松纸折边检测方法
KR20090062782A (ko) 매체이미지 검출장치 및 방법, 그리고 그를 이용한매체취급시스템
US20170323434A1 (en) System, method and computer program product for detecting defects in a fabricated target component using consistent modulation for the target and reference components
KR20250092883A (ko) 주기성 결함 검출 방법 및 주기성 결함 검출 장치

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: 15879610

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15543551

Country of ref document: US

REEP Request for entry into the european phase

Ref document number: 2015879610

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2017129563

Country of ref document: RU

Kind code of ref document: A