CN109767544B - Image analysis method and image analysis system for negotiable securities - Google Patents

Image analysis method and image analysis system for negotiable securities Download PDF

Info

Publication number
CN109767544B
CN109767544B CN201811632173.XA CN201811632173A CN109767544B CN 109767544 B CN109767544 B CN 109767544B CN 201811632173 A CN201811632173 A CN 201811632173A CN 109767544 B CN109767544 B CN 109767544B
Authority
CN
China
Prior art keywords
image
information
unqualified
images
qualified
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.)
Active
Application number
CN201811632173.XA
Other languages
Chinese (zh)
Other versions
CN109767544A (en
Inventor
眭俊华
刘李泉
王建鑫
张健
卢继兵
宁焕成
秦庆旺
冯礼
毛林
王皓
陈勇
魏君
孙晓刚
张超
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.)
China Banknote Printing Technology Research Institute Co ltd
China Banknote Printing and Minting Group Co Ltd
Original Assignee
China Banknote Printing Technology Research Institute Co ltd
China Banknote Printing and Minting Corp
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 China Banknote Printing Technology Research Institute Co ltd, China Banknote Printing and Minting Corp filed Critical China Banknote Printing Technology Research Institute Co ltd
Priority to CN201811632173.XA priority Critical patent/CN109767544B/en
Publication of CN109767544A publication Critical patent/CN109767544A/en
Application granted granted Critical
Publication of CN109767544B publication Critical patent/CN109767544B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
    • G07D7/20—Testing patterns thereon
    • G07D7/2016—Testing patterns thereon using feature extraction, e.g. segmentation, edge detection or Hough-transformation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G06T7/001—Industrial image inspection using an image reference approach
    • 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
    • G07D7/187—Detecting defacement or contamination, e.g. dirt
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
    • G07D7/20—Testing patterns thereon
    • G07D7/2075—Setting acceptance levels or parameters
    • G07D7/2083—Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30144—Printing quality

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
  • Inspection Of Paper Currency And Valuable Securities (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides an image analysis method and an image analysis system of securities, wherein the image analysis method of the securities comprises the following steps: detecting a plurality of pieces of oriented information of the image of the valuable paper according to a preset sequence, wherein the oriented information comprises front information, back information, perspective information and/or infrared information; when any piece of orientation information is detected to be unqualified, judging that the image is unqualified, and when each piece of orientation information in the plurality of pieces of orientation information is detected to be qualified, judging that the image is qualified; and analyzing and recording the error type and the error process of the unqualified image so as to manage and count the unqualified image. By the technical scheme, whether the image of the negotiable securities is qualified or not can be judged efficiently and quickly, the judgment efficiency is improved, and the checking cost and the misjudgment rate are reduced.

Description

Image analysis method and image analysis system for negotiable securities
Technical Field
The invention relates to the technical field of negotiable securities, in particular to an image analysis method and an image analysis system of negotiable securities.
Background
The quality check of the securities is directly performed by using a sorter and the like. However, the checking speed of the sorter is fast, which often causes misjudgment, for example, the original qualified securities are judged as disqualified. In the prior art, in order to avoid waste, the valuable papers judged to be unqualified by the sorter need to be checked for the second time in a manual mode, and the checking efficiency is low while more manpower and material resources are consumed.
Therefore, how to improve the accuracy of the verification and reduce the verification cost becomes a technical problem to be solved urgently at present.
Disclosure of Invention
Based on the problems, the invention provides a new image analysis scheme for the securities, which can effectively improve the accuracy of judgment and reduce the checking cost.
In view of the above, the present invention provides an image analysis method for securities, including: detecting a plurality of pieces of oriented information of the image of the valuable paper according to a preset sequence, wherein the oriented information comprises front information, back information, perspective information and/or infrared information; when any one of the orientation information is detected to be unqualified, judging that the image is unqualified; when each piece of orientation information in the plurality of pieces of orientation information is detected to be qualified, judging that the image is qualified; and analyzing and recording the error type and the error process of the unqualified image so as to manage and count the unqualified image.
In the technical scheme, multiple kinds of information of the images are detected for multiple times respectively, one set of images contain multi-directional information such as front, back, perspective, infrared and the like, if one side of the images is unqualified, the set of images is considered unqualified, and only if all the pieces of information are qualified, the set of images is considered qualified. Therefore, the image is detected for many times when the information is unqualified, so that the judgment result is more reliable, the judgment accuracy is effectively improved, manual detection is replaced, and the checking cost is reduced.
In the above technical solution, preferably, the method includes: when the number of the images needing to be detected is multiple, the multiple images are distributed to multiple different detection nodes, so that the multiple images are detected by the multiple different detection nodes at the same time.
In the technical scheme, when the number of the images needing to be judged in a certain batch is too large, the images can be judged in a multi-node concurrent operation mode, so that the judgment time of the images is saved. The multi-node operation relates to a scheduling method in a system, and images to be judged can be distributed to different nodes according to respective operation conditions of the nodes.
In any one of the above technical solutions, preferably, the method further includes: respectively acquiring crown word number information of the unqualified image and the qualified image; adding crown word number information of the unqualified images into a black list, adding crown word number information of the qualified images into a white list, and adding crown word number information meeting specified conditions in the crown word number information of the unqualified images or in the crown word number information of the qualified images into a gray list.
In the technical scheme, the access of the judgment result takes the database as a main carrier, the information of the judgment process and the final result are synchronously written into the database in the judgment process of the system, and when the software and hardware are abnormal or other breakdown conditions occur, the system can be intelligently recovered to be in the current judgment state from the database so as to keep the running consistency of the system. Therefore, the information of the prefix number of the image is added to the list and stored, so that the system can support the judgment result of the retrieval image under abnormal or other special conditions, and the judgment information of the past image is truly restored. Wherein, the system supports the output of three types of crown word number lists: the white list refers to a crown word number set of images judged to be qualified by the system; the blacklist refers to a crown word number set of images which are judged to be unqualified by the system; the grey list refers to a set of prefix numbers that meet specified conditions.
In any one of the above technical solutions, preferably, the error types of the faulty image include: smearing, ink stain, corner folding and missing printing; the error process of the defective image includes: white paper, offset printing, gravure.
In any one of the above technical solutions, preferably, the preset sequence is set according to an error type and/or an error procedure of the unqualified image.
In the technical scheme, the determination-oriented sequence can be self-defined, generally, in the determination, the front information of all images needing to be determined is determined firstly, if the front of a certain set of images is determined to be unqualified, the set of images is unqualified, and the rest of the set of images do not need to be determined again; and after the front judgment of all the images is finished, judging qualified images on the front, and then judging the back. The above rules are also applicable to determining other information-oriented information such as perspective and infrared. For example, the known perspective surfaces of the images of the batch are more unqualified, the default perspective surface is selected to be firstly judged, and the front surface, the back surface and other surfaces of the images are judged according to the perspective judgment result, so that the judgment time is saved, and the operation efficiency of the system is improved. In addition, the plurality of orientation settings may be set to a unified priority, that is, the plurality of orientation settings may be set to a criterion of the parallel first judgment. Because some information on the image needs to be combined into multiple faces to determine whether the information is qualified or not in some cases, any number of faces (such as only the front face/the infrared face) can be displayed at the same time to perform the determination of the comprehensive information. In this mode, the result of the system determination is the final result of the set of images, and other-oriented determinations are not required.
By the technical scheme, whether the images of the securities are qualified or not can be judged efficiently and rapidly, the judgment efficiency is improved, and the checking cost and the misjudgment rate are reduced.
Drawings
FIG. 1 shows a schematic flow chart of a method for image analysis of a value document according to an embodiment of the invention;
FIG. 2 shows a schematic block diagram of an image analysis system of a value document according to an embodiment of the invention;
fig. 3 shows a system process diagram of a method for image analysis of a value document according to an embodiment of the invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Fig. 1 shows a flow chart of a method for analyzing an image of a document of value according to an embodiment of the invention.
As shown in fig. 1, a method of analyzing a security image according to an embodiment of the present invention includes:
step 102, detecting a plurality of pieces of oriented information of the image of the valuable paper according to a preset sequence, wherein the oriented information comprises front information, back information, perspective information and/or infrared information.
And step 104, judging that the image is unqualified when any piece of orientation information is unqualified, and judging that the image is qualified when each piece of orientation information in the plurality of pieces of orientation information is qualified.
And 106, analyzing and recording the error types and error procedures of the unqualified images so as to manage and count the unqualified images.
In the technical scheme, multiple kinds of information of the images are detected for multiple times respectively, one set of images contain multi-directional information such as front, back, perspective, infrared and the like, and if one side of the images is unqualified, the set of images is considered to be unqualified. The set of images is qualified only if all the information-oriented data is qualified. Therefore, the image is detected for many times when the information is unqualified, so that the judgment result is more reliable, the judgment accuracy is effectively improved, manual detection is replaced, and the checking cost is reduced.
In the above technical solution, preferably, the method includes: when the number of the images needing to be detected is multiple, the multiple images are distributed to multiple different detection nodes, so that the multiple images are detected by the multiple different detection nodes at the same time.
In the technical scheme, when the number of the images needing to be judged in a certain batch is too large, the images can be judged in a multi-node concurrent operation mode, so that the judgment time of the images is saved. The multi-node operation relates to a scheduling method in a system, and images to be judged can be distributed to different nodes according to respective operation conditions of the nodes.
In any one of the above technical solutions, preferably, the method further includes: acquiring crown word number information of the unqualified image and the qualified image respectively; adding the crown number information of the unqualified images into a black list, adding the crown number information of the qualified images into a white list, and adding the crown number information meeting the specified conditions in the crown number information of the unqualified images or the crown number information of the qualified images into a gray list.
In the technical scheme, the access of the judgment result takes the database as a main carrier, the information of the judgment process and the final result are synchronously written into the database in the judgment process of the system, and when the software and hardware are abnormal or other breakdown conditions occur, the system can be intelligently recovered to be in the current judgment state from the database so as to keep the running consistency of the system. Therefore, the information of the prefix number of the image is added to the list and stored, so that the system can support the judgment result of the retrieval image under abnormal or other special conditions, and the judgment information of the past image is truly restored. Wherein, the system supports the output of three types of crown word number lists: the white list refers to a crown word number set of images judged to be qualified by the system; the blacklist refers to a crown word number set of images which are judged to be unqualified by the system; the grey list refers to a set of prefix numbers that meet specified conditions.
In any one of the above technical solutions, preferably, the error types of the faulty image include: smearing, ink stain, corner folding and missing printing; the error process of the defective image includes: white paper, offset printing, gravure.
In any of the above technical solutions, preferably, the preset sequence is set according to an error type and/or an error procedure of the failed image.
In the technical scheme, the determination-oriented sequence can be self-defined, generally, in the determination, the front information of all images needing to be determined is determined firstly, if the front of a certain set of images is determined to be unqualified, the set of images is unqualified, and the rest of the set of images do not need to be determined again; and after the front judgment of all the images is finished, judging qualified images on the front, and then judging the back. The above rules are also applicable to determining other information-oriented information such as perspective and infrared. For example, the known perspective surfaces of the images of the batch are more unqualified, the default perspective surface is selected to be firstly judged, and the front surface, the back surface and other surfaces of the images are judged according to the perspective judgment result, so that the judgment time is saved, and the operation efficiency of the system is improved. In addition, the plurality of orientation settings may be set to a unified priority, that is, the plurality of orientation settings may be set to a criterion of the parallel first judgment. Because some information on the image needs to be combined into multiple faces to determine whether the information is qualified or not in some cases, any number of faces (such as only the front face/the infrared face) can be displayed at the same time to perform the determination of the comprehensive information. In this mode, the result of the system determination is the final result of the set of images, and other-oriented determinations are not required.
FIG. 2 shows a schematic block diagram of an image analysis system of a value document according to an embodiment of the invention.
As shown in fig. 2, an analysis system 200 of a security image according to an embodiment of the present invention includes: detection unit 202, determination unit 204, and processing unit 206.
The detection unit 202 is configured to detect multiple pieces of information-oriented information of an image of a valuable document according to a preset sequence, where the information-oriented information includes front information, back information, perspective information, and/or infrared information; a determining unit 204 configured to determine that the image is not qualified when any piece of orientation information is detected to be not qualified, and determine that the image is qualified when each piece of orientation information in the plurality of pieces of orientation information is detected to be qualified; and the processing unit 206 is used for analyzing and recording the error types and error procedures of the unqualified images so as to manage and count the unqualified images.
In the technical scheme, multiple kinds of information of the images are detected for multiple times respectively, one set of images contain multi-directional information such as front, back, perspective, infrared and the like, and if one side of the images is unqualified, the set of images is considered to be unqualified. The set of images is qualified only if all the information-oriented data is qualified. Therefore, the image is detected for many times when the information is unqualified, so that the judgment result is more reliable, the judgment accuracy is effectively improved, manual detection is replaced, and the checking cost is reduced.
In the above technical solution, preferably, the method includes: the allocating unit 208 is configured to, when the number of images to be detected is multiple, allocate the multiple images to multiple different detection nodes, so as to detect the multiple images by using the multiple different detection nodes at the same time.
In the technical scheme, when the number of the images needing to be judged in a certain batch is too large, the images can be judged in a multi-node concurrent operation mode, so that the judgment time of the images is saved. The multi-node operation relates to a scheduling method in a system, and images to be judged can be distributed to different nodes according to respective operation conditions of the nodes.
In any one of the above technical solutions, preferably, the method further includes: an obtaining unit 210, configured to obtain crown word number information of the non-qualified image and the qualified image respectively; an adding unit 212, configured to add the crown number information of the unqualified image to a blacklist, add the crown number information of the qualified image to a whitelist, and add the crown number information meeting a specified condition in the crown number information of the unqualified image or in the crown number information of the qualified image to a grey list.
In the technical scheme, the access of the judgment result takes the database as a main carrier, the information of the judgment process and the final result are synchronously written into the database in the judgment process of the system, and when the software and hardware are abnormal or other breakdown conditions occur, the system can be intelligently recovered to be in the current judgment state from the database so as to keep the running consistency of the system. Therefore, the information of the prefix number of the image is added to the list and stored, so that the system can support the judgment result of the retrieval image under abnormal or other special conditions, and the judgment information of the past image is truly restored. Wherein, the system supports the output of three types of crown word number lists: the white list refers to a crown word number set of images judged to be qualified by the system; the blacklist refers to a crown word number set of images which are judged to be unqualified by the system; the grey list refers to a set of prefix numbers that meet specified conditions.
In any one of the above technical solutions, preferably, the error types of the faulty image include: smearing, ink stain, corner folding and missing printing; the error process of the defective image includes: white paper, offset printing, gravure.
In any one of the above technical solutions, preferably, the error types of the faulty image include: smudge, ink stain, corner mark and/or lack of print; the error process of the defective image includes: white paper, offset printing and/or gravure printing.
In any one of the above technical solutions, preferably, the method further includes: a setting unit 214, configured to set the preset order according to the error type and/or the error procedure of the unqualified image.
In the technical scheme, the determination-oriented sequence can be self-defined, generally, in the determination, the front information of all images needing to be determined is determined firstly, if the front of a certain set of images is determined to be unqualified, the set of images is unqualified, and the rest of the set of images do not need to be determined again; and after the front judgment of all the images is finished, judging qualified images on the front, and then judging the back. The above rules are also applicable to determining other information-oriented information such as perspective and infrared. For example, the known perspective surfaces of the images of the batch are more unqualified, the default perspective surface is selected to be firstly judged, and the front surface, the back surface and other surfaces of the images are judged according to the perspective judgment result, so that the judgment time is saved, and the operation efficiency of the system is improved. In addition, the plurality of orientation settings may be set to a unified priority, that is, the plurality of orientation settings may be set to a criterion of the parallel first judgment. Because some information on the image needs to be combined into multiple faces to determine whether the information is qualified or not in some cases, any number of faces (such as only the front face/the infrared face) can be displayed at the same time to perform the determination of the comprehensive information. In this mode, the result of the system determination is the final result of the set of images, and other-oriented determinations are not required.
Specifically, the technical solution of the present invention can be embodied by a plurality of examples as follows:
the first embodiment is as follows: firstly, a preset sequence can be set according to the error type and/or the error process of the unqualified image, wherein the error type of the unqualified image comprises the following steps: smearing, ink stain, corner folding and/or lack of printing and the like; the error process of the defective image includes: white paper, offset printing, gravure printing and the like, then detecting a plurality of pieces of oriented information such as front information, back information, perspective information and/or infrared information of the image of the securities according to a preset sequence, and judging that the image is unqualified when any piece of oriented information is detected to be unqualified; only when each piece of oriented information in the plurality of pieces of oriented information is detected to be qualified, the image is judged to be qualified, and the error type and the error process of the unqualified image are analyzed and recorded so as to manage and count the unqualified image, so that the judgment result is more reliable, the judgment accuracy is effectively improved, manual detection is replaced, and the checking cost is reduced.
Example two: the method can also be implemented on the basis of the first embodiment, the number of the images to be detected is detected, when the number of the images to be detected is multiple, the multiple images are distributed to multiple different detection nodes, and the multiple images are detected by using the multiple different detection nodes at the same time, so that when the number of a certain batch of images to be determined is too large, the images can be determined by using a multi-node concurrent operation mode, the determination time of the multiple images is saved, the multi-node operation relates to a scheduling method in a system, and the images to be determined can be distributed to different nodes according to respective operation conditions of the nodes.
Example three: the detection of the crown word number information of the unqualified image and the crown word number information of the qualified image can be added on the basis of the first embodiment, the crown word number information of the unqualified image and the crown word number information of the qualified image are respectively obtained, the crown word number information of the unqualified image is added into a blacklist, the crown word number information of the qualified image is added into a whitelist, and the crown word number information meeting the specified conditions in the crown word number information of the unqualified image or in the crown word number information of the qualified image is added into a grey list, so that the system can support the judgment result of the retrieval image under abnormal or other special conditions, and the judgment information of the conventional image is really restored.
The technical solution of the present invention is further explained with reference to fig. 3.
As shown in fig. 3, the sorter 302 detects a plurality of orientation information of the image of the securities in a preset order, wherein the orientation information includes front information, back information, perspective information, and/or infrared information. The sorter 302 is connected to the secondary checking automatic detection system 304, and sends the detection result of the images of a certain number (e.g. 7000) of securities to the secondary checking automatic detection system 304, and the secondary checking automatic detection system 304 distinguishes qualified products, general waste products and serious waste products through the secondary checking, and sends the distinguishing result to the secondary checking image comprehensive analysis and judgment system 306. The secondary inspection image comprehensive analysis and judgment system 306 analyzes and records the error types and error procedures of the unqualified images so as to manage and count the unqualified images, respectively obtain the prefix number information of the images of qualified products, general waste products and serious waste products, and send the prefix number information to the corresponding output list. Wherein, the system supports the output of three types of crown word number lists: the white list refers to a crown word number set of images judged to be qualified by the system; the blacklist refers to a crown word number set of images which are judged to be unqualified by the system; the grey list refers to a set of prefix numbers that meet specified conditions.
In the technical scheme, multiple kinds of information of the images are detected for multiple times respectively, one set of images contain multi-directional information such as front, back, perspective, infrared and the like, and if one side of the images is unqualified, the set of images is considered to be unqualified. The set of images is qualified only if all the information-oriented data is qualified. Therefore, the image is detected for many times when the information is unqualified, so that the judgment result is more reliable, and the judgment accuracy is effectively improved.
In addition, the access of the judgment result takes the database as a main carrier, the information of the judgment process and the final result are synchronously written into the database in the judgment process of the system, and when the software and hardware are abnormal or other breakdown conditions occur, the system can be intelligently recovered to be in a current judgment state from the database so as to keep the running consistency of the system. Therefore, the information of the prefix number of the image is added to the list and stored, so that the system can support the judgment result of the retrieval image under abnormal or other special conditions, and the judgment information of the past image is truly restored.
The technical scheme of the invention is explained in detail by combining the attached drawings, and the invention provides a novel image analysis scheme of the negotiable securities, which can efficiently and quickly judge whether the images of the negotiable securities are qualified or not, and effectively improve the accuracy of checking by repeatedly checking the negotiable securities for many times.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (8)

1. A method of image analysis of a value document, comprising:
detecting a plurality of pieces of oriented information of the image of the valuable paper according to a preset sequence, wherein the oriented information comprises front information, back information, perspective information and/or infrared information;
when any one of the orientation information is detected to be unqualified, judging that the image is unqualified;
when each piece of orientation information in the plurality of pieces of orientation information is detected to be qualified, judging that the image is qualified;
analyzing and recording the error type and the error process of the unqualified image so as to manage and count the unqualified image;
and setting the preset sequence according to the error type and/or the error process of the unqualified image.
2. The method for image analysis of a value document according to claim 1, comprising:
when the number of the images needing to be detected is multiple, the multiple images are distributed to multiple different detection nodes, so that the multiple images are detected by the multiple different detection nodes at the same time.
3. The method for image analysis of a value document according to claim 1, further comprising:
acquiring crown word number information of the unqualified image and the qualified image respectively;
adding crown word number information of the unqualified images into a black list, adding crown word number information of the qualified images into a white list, and adding crown word number information meeting specified conditions in the crown word number information of the unqualified images or in the crown word number information of the qualified images into a gray list.
4. The method for image analysis of a value document according to claim 1,
the error types of the non-compliant image include: smudge, ink stain, corner mark and/or lack of print;
the error process of the defective image includes: white paper, offset printing and/or gravure printing.
5. An image analysis system for value documents, comprising:
the detection unit is used for detecting a plurality of pieces of oriented information of the image of the valuable paper according to a preset sequence, wherein the oriented information comprises front information, back information, perspective information and/or infrared information;
a determination unit configured to determine that the image is not acceptable when any of the plurality of pieces of orientation information is not acceptable and determine that the image is acceptable when each of the plurality of pieces of orientation information is acceptable;
the processing unit is used for analyzing and recording the error type and the error process of the unqualified image so as to manage and count the unqualified image;
and the setting unit is used for setting the preset sequence according to the error type and/or the error process of the unqualified image.
6. An image analysis system of value documents according to claim 5, characterized in that it comprises:
the distribution unit is used for distributing the images to different detection nodes when the number of the images needing to be detected is multiple, so that the images can be detected by using the different detection nodes at the same time.
7. The system for image analysis of a value document according to claim 5, further comprising:
an obtaining unit, configured to obtain crown word number information of the non-qualified image and crown word number information of the qualified image respectively;
and the adding unit is used for adding the crown word number information of the unqualified image into a blacklist, adding the crown word number information of the qualified image into a white list, and adding the crown word number information meeting specified conditions in the crown word number information of the unqualified image or the crown word number information of the qualified image into a gray list.
8. An image analysis system of value documents according to claim 5,
the error types of the non-compliant image include: smudge, ink stain, corner mark and/or lack of print;
the error process of the defective image includes: white paper, offset printing and/or gravure printing.
CN201811632173.XA 2017-01-10 2017-01-10 Image analysis method and image analysis system for negotiable securities Active CN109767544B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811632173.XA CN109767544B (en) 2017-01-10 2017-01-10 Image analysis method and image analysis system for negotiable securities

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811632173.XA CN109767544B (en) 2017-01-10 2017-01-10 Image analysis method and image analysis system for negotiable securities
CN201710014778.1A CN106683263B (en) 2017-01-10 2017-01-10 The defect management method and system of valuable bills

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
CN201710014778.1A Division CN106683263B (en) 2017-01-10 2017-01-10 The defect management method and system of valuable bills

Publications (2)

Publication Number Publication Date
CN109767544A CN109767544A (en) 2019-05-17
CN109767544B true CN109767544B (en) 2022-02-15

Family

ID=58849544

Family Applications (6)

Application Number Title Priority Date Filing Date
CN201811634556.0A Active CN109767546B (en) 2017-01-10 2017-01-10 Quality checking and scheduling device and quality checking and scheduling method for valuable bills
CN201811653192.0A Active CN109767545B (en) 2017-01-10 2017-01-10 Method and system for classifying defects of valuable bills
CN201811632173.XA Active CN109767544B (en) 2017-01-10 2017-01-10 Image analysis method and image analysis system for negotiable securities
CN201811632486.5A Active CN109767430B (en) 2017-01-10 2017-01-10 Quality detection method and quality detection system for valuable bills
CN201710014778.1A Active CN106683263B (en) 2017-01-10 2017-01-10 The defect management method and system of valuable bills
CN201811632062.9A Active CN109754395B (en) 2017-01-10 2017-01-10 Method and device for extracting defects of value documents

Family Applications Before (2)

Application Number Title Priority Date Filing Date
CN201811634556.0A Active CN109767546B (en) 2017-01-10 2017-01-10 Quality checking and scheduling device and quality checking and scheduling method for valuable bills
CN201811653192.0A Active CN109767545B (en) 2017-01-10 2017-01-10 Method and system for classifying defects of valuable bills

Family Applications After (3)

Application Number Title Priority Date Filing Date
CN201811632486.5A Active CN109767430B (en) 2017-01-10 2017-01-10 Quality detection method and quality detection system for valuable bills
CN201710014778.1A Active CN106683263B (en) 2017-01-10 2017-01-10 The defect management method and system of valuable bills
CN201811632062.9A Active CN109754395B (en) 2017-01-10 2017-01-10 Method and device for extracting defects of value documents

Country Status (1)

Country Link
CN (6) CN109767546B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110363764B (en) * 2019-07-23 2022-03-11 安徽大学 Method for detecting integrity of running license printing information based on interframe difference
CN116823678B (en) * 2023-08-29 2023-11-17 国网江西省电力有限公司超高压分公司 Intelligent repairing system for image defect points

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN203552342U (en) * 2013-11-20 2014-04-16 北京华夏锐驰投资管理有限公司 Banknote sorter recognition device

Family Cites Families (44)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19646454A1 (en) * 1996-11-11 1998-05-14 Giesecke & Devrient Gmbh Process for processing sheet material, such as. B. banknotes
JP3583979B2 (en) * 2000-08-15 2004-11-04 三洋電機株式会社 Inspection target type determination method
US7252222B2 (en) * 2003-12-19 2007-08-07 Scientific Game Royalty Corporation Embedded optical signatures in documents
US7266548B2 (en) * 2004-06-30 2007-09-04 Microsoft Corporation Automated taxonomy generation
CN100354144C (en) * 2004-11-05 2007-12-12 中国印钞造币总公司 Quality on-line detection device of value added tax receipt imprint
EP1901241A1 (en) * 2006-09-06 2008-03-19 Kba-Giori S.A. Method for controlling the quality of printed documents based on pattern matching
US7949175B2 (en) * 2007-01-23 2011-05-24 Xerox Corporation Counterfeit deterrence using dispersed miniature security marks
JP2008250418A (en) * 2007-03-29 2008-10-16 Toshiba Corp Paper sheet processing system
US8780206B2 (en) * 2008-11-25 2014-07-15 De La Rue North America Inc. Sequenced illumination
JP2010195514A (en) * 2009-02-24 2010-09-09 Toshiba Corp Paper sheet processing device
DE102009058438A1 (en) * 2009-12-16 2011-06-22 Giesecke & Devrient GmbH, 81677 Method for checking value documents
JP5605746B2 (en) * 2010-03-23 2014-10-15 富士ゼロックス株式会社 Print control apparatus, image forming system, and program
CN101908241B (en) * 2010-08-03 2012-05-16 广州广电运通金融电子股份有限公司 Method and system for identifying valued documents
CN101944122A (en) * 2010-09-17 2011-01-12 浙江工商大学 Incremental learning-fused support vector machine multi-class classification method
CN102456246B (en) * 2010-10-19 2014-04-30 山东新北洋信息技术股份有限公司 Stuck banknotes detection method, apparatus thereof and self-service terminal
CN102096960B (en) * 2010-12-14 2013-04-17 朱杰 Processing method of bill currency count machine system
CN102157024B (en) * 2011-05-03 2013-01-09 西安印钞有限公司 System and method for on-line secondary detection checking of checking data of large-sheet checking machine
CN102236925B (en) * 2011-05-03 2013-08-14 西安印钞有限公司 System and method for offline secondary detection and checking of machine detected data of large-piece checker
JP5799651B2 (en) * 2011-08-16 2015-10-28 沖電気工業株式会社 Bill deposit / withdrawal apparatus and bill deposit / withdrawal control method
CN102645280B (en) * 2012-04-27 2014-12-03 中国电子科技集团公司第四十一研究所 High-efficient spectrum restoring method
CN102722726B (en) * 2012-06-05 2014-01-15 江苏省电力公司南京供电公司 Multi-class support vector machine classification method based on dynamic binary tree
CN102831703B (en) * 2012-09-03 2014-12-24 上海印钞有限公司 Quality analysis device and method for banknote product
CN102915447B (en) * 2012-09-20 2015-07-08 西安科技大学 Binary tree-based SVM (support vector machine) classification method
KR101682268B1 (en) * 2013-05-14 2016-12-05 중앙대학교 산학협력단 Apparatus and method for gesture recognition using multiclass Support Vector Machine and tree classification
CN103325171B (en) * 2013-06-17 2018-07-10 中国人民银行印制科学技术研究所 Valuable bills separation system and valuable bills method for separating
KR101460779B1 (en) * 2013-09-06 2014-11-19 기산전자 주식회사 Banknote processing device and control method thereof
CN103685574A (en) * 2014-01-02 2014-03-26 清华大学 Service-oriented general Internet of Things resource distributing method
CN103745234B (en) * 2014-01-23 2017-01-25 东北大学 Band steel surface defect feature extraction and classification method
CN104916029A (en) * 2014-03-13 2015-09-16 广州南沙资讯科技园有限公司博士后科研工作站 Paper money verification system and paper money verification method based on system
EP2940662B1 (en) * 2014-04-30 2019-10-30 Wincor Nixdorf International GmbH Method for operating an automatic teller machine when multiple withdrawals are made
CN104156701A (en) * 2014-07-26 2014-11-19 佳都新太科技股份有限公司 Plate number similar character recognition method based on decision-making tree and SVM
CN104574638A (en) * 2014-09-30 2015-04-29 上海层峰金融设备有限公司 Method for identifying RMB
CN104331976A (en) * 2014-10-31 2015-02-04 苏州保瑟佳货币检测科技有限公司 Detecting method and device of negotiable securities
CN104616392B (en) * 2015-01-30 2018-02-02 华中科技大学 A kind of paper money discrimination method based on local binary patterns
CN104794675B (en) * 2015-04-24 2017-10-24 华南师范大学 Image concealing, reduction and encrypted transmission method based on cut Fourier transformation
CN104764712B (en) * 2015-04-29 2017-08-25 浙江工业大学 A kind of detection method of PCB vias inwall quality
CN104966058A (en) * 2015-06-12 2015-10-07 南京邮电大学 Behavior identification method based on layered binary tree
CN105354835A (en) * 2015-10-16 2016-02-24 浙江工业大学 Method for evaluating medical image quality in combination with phase consistency, gradient magnitude and structural prominence
CN105374105A (en) * 2015-10-16 2016-03-02 浙江依特诺科技股份有限公司 Method used by mobile terminal for identifying authenticity of banknote
CN105631474B (en) * 2015-12-26 2019-01-11 哈尔滨工业大学 Based on Jeffries-Matusita distance and class to the more classification methods of the high-spectral data of decision tree
CN105678612A (en) * 2015-12-30 2016-06-15 远光软件股份有限公司 Mobile terminal original certificate electronic intelligent filling system and method
CN105930872A (en) * 2016-04-28 2016-09-07 上海应用技术学院 Bus driving state classification method based on class-similar binary tree support vector machine
CN106056752B (en) * 2016-05-25 2018-08-21 武汉大学 A kind of banknote false distinguishing method based on random forest
CN106169084A (en) * 2016-07-08 2016-11-30 福州大学 A kind of SVM mammary gland sorting technique based on Gauss kernel parameter selection

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN203552342U (en) * 2013-11-20 2014-04-16 北京华夏锐驰投资管理有限公司 Banknote sorter recognition device

Also Published As

Publication number Publication date
CN106683263A (en) 2017-05-17
CN109767544A (en) 2019-05-17
CN109767545B (en) 2021-06-08
CN109767545A (en) 2019-05-17
CN109754395A (en) 2019-05-14
CN109767430A (en) 2019-05-17
CN109767546A (en) 2019-05-17
CN109754395B (en) 2021-03-02
CN109767546B (en) 2022-02-15
CN109767430B (en) 2021-06-08
CN106683263B (en) 2019-07-19

Similar Documents

Publication Publication Date Title
US8099384B2 (en) Operation procedure extrapolating system, operation procedure extrapolating method, computer-readable medium and computer data signal
US20110081051A1 (en) Automated quality and usability assessment of scanned documents
JP2009532233A (en) Weighted sheet inspection device
US20060238780A1 (en) Validation of a print verification system
JP6162085B2 (en) Printed product inspection apparatus, inspection method, and program
US20160142560A1 (en) Inspecting device, method for changing threshold, and computer-readable storage medium
CN109903210B (en) Watermark removal method, watermark removal device and server
SA516371755B1 (en) Methods and a system for verifying the identity of a printed item
WO2015081765A1 (en) Automatic fault diagnosis method and device for sorting machine
CN109767544B (en) Image analysis method and image analysis system for negotiable securities
EP0841808B1 (en) System and method for detecting the black and white points of a color image
CN103106859B (en) The detection method of display screen and device
KR20110012740A (en) Device and method for detecting duplicate contents
US20190356789A1 (en) Image processing apparatus, image processing system, and program
US8280689B2 (en) Saving history and format information of a document together
US20120320388A1 (en) Relevance based print integrity verification
CN105894602A (en) Work order processing method and device
JP7412185B2 (en) MN (missing nozzle) detection in printed images
US7925460B2 (en) System and method for improving print shop operability
CN107977578B (en) Distributed storage system and data restoration method and device thereof
US11614902B2 (en) Job processing system, method for controlling the same, and storage medium
US9193173B1 (en) Method and apparatus for preventing illegitimate exit of printed document by applying security material
CN110764716B (en) Flow-based network printer security detection method, device and storage medium
US8964192B2 (en) Print verification database mechanism
CN113256554B (en) Deterministic image inspection

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
TA01 Transfer of patent application right

Effective date of registration: 20210419

Address after: 100070 8th floor, building 2, No.5 Zhonghe Road, Fengtai Science City, Fengtai District, Beijing

Applicant after: China Banknote Printing Technology Research Institute Co.,Ltd.

Applicant after: CHINA BANKNOTE PRINTING AND MINTING Corp.

Address before: 100070, Beijing, Fengtai District, Fengtai Science City Road, No. 2, No. 5 Building

Applicant before: SECURITY PRINTING INSTITUTE OF PEOPLE'S BANK OF CHINA

Applicant before: CHINA BANKNOTE PRINTING AND MINTING Corp.

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant
CP01 Change in the name or title of a patent holder

Address after: 100070 8th floor, building 2, No.5 Zhonghe Road, Fengtai Science City, Fengtai District, Beijing

Patentee after: China Banknote Printing Technology Research Institute Co.,Ltd.

Patentee after: China Banknote Printing and Minting Group Co.,Ltd.

Address before: 100070 8th floor, building 2, No.5 Zhonghe Road, Fengtai Science City, Fengtai District, Beijing

Patentee before: China Banknote Printing Technology Research Institute Co.,Ltd.

Patentee before: CHINA BANKNOTE PRINTING AND MINTING Corp.

CP01 Change in the name or title of a patent holder