WO2019174133A1 - 电子装置、物理印章识别方法和计算机可读存储介质 - Google Patents

电子装置、物理印章识别方法和计算机可读存储介质 Download PDF

Info

Publication number
WO2019174133A1
WO2019174133A1 PCT/CN2018/089426 CN2018089426W WO2019174133A1 WO 2019174133 A1 WO2019174133 A1 WO 2019174133A1 CN 2018089426 W CN2018089426 W CN 2018089426W WO 2019174133 A1 WO2019174133 A1 WO 2019174133A1
Authority
WO
WIPO (PCT)
Prior art keywords
seal
stamp
picture
result value
comparison result
Prior art date
Application number
PCT/CN2018/089426
Other languages
English (en)
French (fr)
Inventor
孟君
曲风龙
江琳
邓佳鹏
梁大祥
Original Assignee
平安科技（深圳）有限公司
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 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2019174133A1 publication Critical patent/WO2019174133A1/zh

Links

Images

Classifications

    • 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
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40—Document-oriented image-based pattern recognition
    • G06V30/41—Analysis of document content
    • G06V30/418—Document matching, e.g. of document images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/273—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion removing elements interfering with the pattern to be recognised
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/752—Contour matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40—Document-oriented image-based pattern recognition
    • G06V30/41—Analysis of document content
    • G06V30/412—Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
    • 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
    • G07D7/202—Testing patterns thereon using pattern matching
    • G07D7/206—Matching template patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/09—Recognition of logos

Definitions

  • the present application relates to the field of image processing technologies, and in particular, to an electronic device, a physical seal recognition method, and a computer readable storage medium.
  • the present application provides an electronic device, a physical seal recognition method, and a computer readable storage medium, which are intended to improve the accuracy and timeliness of physical seal recognition.
  • a first aspect of the present application provides an electronic device including a memory and a processor, the memory storing a physical seal recognition system operable on the processor, the physical seal recognition system being The processor implements the following steps when it executes:
  • the post-word processed stamp picture is compared with the seal verification picture by a preset similarity algorithm to obtain the de-word-processed seal picture and the seal verification picture. Similarity
  • a second aspect of the present application provides a physical seal identification method, where the physical seal recognition method includes:
  • the post-word processed stamp picture is compared with the seal verification picture by a preset similarity algorithm to obtain the de-word-processed seal picture and the seal verification picture. Similarity
  • a third aspect of the present application provides a computer readable storage medium storing a physical seal identification system, the physical seal recognition system being executable by at least one processor to cause the at least one processor Perform the following steps:
  • the post-word processed stamp picture is compared with the seal verification picture by a preset similarity algorithm to obtain the de-word-processed seal picture and the seal verification picture. Similarity
  • the technical solution of the present application cuts out the seal picture including the seal of the verification to be recognized from the scan piece, detects all the file characters in the seal picture and removes, and deducts the seal picture at Go to the blank area left by the text and the center point of the seal picture, synthesize the captured content into the original chapter mode picture to get the seal verification picture, and then rotate the deducted blank area relative to the original chapter mode picture, and calculate The degree of similarity between the stamp verification image after each rotation and the stamp image after the word processing, so as to find the seal verification map with the highest similarity to the stamp image after the word processing, and finally the seal verification map with the highest similarity is The seal picture after word processing is compared, and the authenticity of the seal on the seal picture is confirmed based on the comparison result.
  • the blank area left by the document text on the seal picture is synthesized into the original chapter mode picture, thereby adding and de-text processing on the original chapter mode picture.
  • the stamp image has the same blank coverage area, and then compares the stamp image after the word processing with the original chapter image after the compositing blank area to verify the authenticity of the stamp on the stamp image, thus avoiding the seal on the seal picture.
  • the influence of the document text on the seal picture on the verification comparison result improves the accuracy of the seal identification of the seal picture; and the program does not need a specific device after receiving the scanned piece to be verified. And specific scene requirements, the ability to immediately verify the processing, fast feedback verification results, timeliness.
  • FIG. 1 is a schematic flow chart of an embodiment of a physical seal identification method according to the present application.
  • FIG. 2 is a schematic flow chart of a second embodiment of a method for identifying a physical seal of the present application
  • FIG. 3 is a schematic flow chart of a third embodiment of a physical seal identification method of the present application.
  • FIG. 4 is a schematic diagram of an operating environment of an embodiment of a physical seal identification system of the present application.
  • FIG. 5 is a program block diagram of an embodiment of a physical seal identification system of the present application.
  • FIG. 6 is a program block diagram of a second embodiment of a physical seal identification system of the present application.
  • FIG. 7 is a program block diagram of three embodiments of the physical seal identification system of the present application.
  • FIG. 1 is a schematic flowchart of an embodiment of a physical seal identification method according to the present application.
  • the physical seal identification method includes:
  • Step S10 receiving a scan to be verified
  • the user When a user needs to perform physical stamp authenticity identification on a file, the user uploads a scanned copy of the file to be verified into the system, and the system receives the scanned piece to be verified.
  • Step S20 identifying a stamp center in the scan member, using the stamp center as a crop center, and cutting the scan member according to a preset cropping shape according to a preset cropping shape to obtain a stamp image to be verified;
  • the scanning part is first cut, and the stamp picture including the stamp of the authenticity to be recognized is cut out.
  • the stamp center of the stamp portion on the scan member is found, and the stamp center is used as the center of the crop region, and the scan member is cut according to a predetermined cropping size (ie, the crop size) by using a preset crop shape.
  • the cropped picture is the one to be verified.
  • the preset cropping shape is preferably a rectangle, that is, a rectangular image is obtained by cutting out; of course, the preset cropping shape may also be other shapes (for example, a circle).
  • Step S30 detecting file characters in the seal picture, and removing all detected file characters
  • the embodiment preferably adopts the method of removing the document characters in the stamp picture by: identifying different color points in the seal picture that are different from the preset reference color, and removing all the identified different color points; wherein, The reference color is the same as the color of the stamp of the stamp. Since the color of the document text is different from the stamp color of the stamp, after removing all the different color points different from the reference color, it is equivalent to removing all the files in the stamp image. In the text, only the imprinted portion of the stamp and the blank area left by the position of the text are left in the stamp image.
  • Step S40 deducting the center point from the stamp image after the word processing and removing the blank area left in the document text, so that the center point of the deduction coincides with the stamp center of the original chapter mode picture, and the blank area is synthesized into Forming a seal verification map on the original chapter mode picture;
  • the center point in the stamp image after the word processing ie, the stamp center on the stamp image
  • the stamp image after the word processing is removed from the stamp image after the word processing, and the blank area left in the document text is removed.
  • the content of the deduction is synthesized into the original chapter mode image to form a seal verification map; the center point of the deduction is coincident with the stamp center of the original chapter mode picture, so that the original chapter mode picture is added and de-texted.
  • the original chapter mode image is preferably the same size and shape as the clip image obtained by the cropping
  • Step S50 the blank area in the seal verification map is rotated successively in the same direction with the center point as the center, and each time the preset angle is rotated until one rotation, each time After the blank area is rotated relative to the original chapter mode picture, the post-word processed stamp picture is compared with the seal verification picture by a preset similarity algorithm to obtain the de-word-processed seal picture and the seal. Verify the similarity of the graph;
  • the next step is to adjust the coverage of the blank area on the original chapter image, so that the blank area is relative to the original stamp picture.
  • the position of the stamp is the same as the position of the blank image after the word processing; in this embodiment, the blank area on the stamp verification map is taken around the center of the original chapter mode picture.
  • the manner of rotation the same angle is rotated each time (ie, the preset angle is, for example, 0.5 degrees) until the blank area is rotated one week with respect to the original chapter mode picture, and after each rotation operation, the word processing is performed.
  • the post stamp image is compared with the stamp verification map by a preset similarity algorithm (for example, the peak signal to noise ratio psnr algorithm), and the similarity between the seal verification map after each rotation and the stamp image after the word processing is calculated. Therefore, the seal verification map with the highest similarity to the stamp image after the word processing can be found, and the seal verification map with the highest similarity is obtained.
  • a preset similarity algorithm for example, the peak signal to noise ratio psnr algorithm
  • Step S60 obtaining a seal verification map having the highest similarity with the stamp image after the de-word processing, comparing the seal verification map with the pre-word-processed seal image by using a preset comparison manner, and confirming the seal image according to the comparison result. The authenticity of the seal on it.
  • the seal verification map with the highest similarity to the stamp image after the word processing is found, and then the seal verification map is compared with the stamp image after the word processing by the preset comparison method, and the seal on the seal image is confirmed based on the comparison result.
  • the preset comparison mode may be a general seal comparison confirmation mode.
  • the seal picture including the seal of the verification to be recognized is cut out from the scan piece, all the file characters in the seal picture are detected and removed, and the seal picture is buckled.
  • the content of the deduction is synthesized into the original chapter mode picture to obtain the seal verification picture, and then the detained blank area is rotated successively with respect to the original chapter mode picture, and Calculate the similarity between the seal verification image after each rotation and the stamp image after the word processing, so as to find the seal verification diagram with the highest similarity to the stamp image after the word processing, and finally the seal verification diagram with the highest similarity and
  • the stamp image after the word processing is compared, and the authenticity of the stamp on the stamp image is confirmed based on the comparison result.
  • the file text in the seal picture to be verified is removed, and the blank area left by the file text on the seal picture is synthesized into the original chapter mode picture, thereby adding and deleting the word processing on the original chapter mode picture.
  • the stamp image after the word processing is compared with the original chapter image after the composite blank area to verify the authenticity of the seal on the seal picture, thus avoiding the seal on the seal picture.
  • the influence of the document text on the seal picture on the verification comparison result improves the accuracy of the seal identification of the seal picture; and the program does not need to be specific after receiving the scanned piece to be verified.
  • the step of comparing the seal verification map with the pre-word-processed seal image by using a preset comparison manner, and confirming the authenticity of the seal on the seal image according to the comparison result includes:
  • Extracting the stamped picture after the word processing is compared with the outline of the seal verification image to obtain a first comparison result value
  • first comparison result value, the second comparison result value, and the third comparison result value are weighted and summed according to a preset weight to obtain a determination result value
  • the seal contrast is divided into three parts and divided into three parts, which are the contrast of the seal outline, the contrast of the characters and numbers on the stamp, and the contrast of the five-pointed star on the stamp to obtain the respective comparison results, according to the respective comparison results.
  • the weight of the weight determines the final decision result value.
  • the first comparison result value A, the second comparison result value B, and the third comparison result value C each have a preset weight of 0.2, 0.5, and 0.3, respectively, and the determination result value is 0.2A+0.5B+0.3C.
  • the first threshold is 90%
  • the second threshold is 60%. If the determination result value is greater than 90%, it is determined that the seal on the seal picture is a true chapter, and if the determination result value is less than or equal to 60%, then Determining that the seal on the seal picture is false; in addition, if the value of the determination result is greater than 60% and less than or equal to 90%, the authenticity of the seal on the seal picture may not be clearly determined, and other means or The method is further identified.
  • FIG. 2 is a schematic flow chart of a second embodiment of the physical seal identification method of the present application.
  • the physical seal identification method before the step S30, the physical seal identification method further includes:
  • Step S70 performing noise detection on the stamp image to remove the detected noise.
  • the stamp image is used for noise detection to remove the detected noise (filtering can be used to filter discrete data points).
  • FIG. 3 is a schematic flowchart of a third embodiment of a physical seal identification method according to the present application.
  • the physical seal identification method of this embodiment replaces the step S20 with:
  • Step S80 identifying a seal center and a stamp specification in the scan component, determining a cropping specification corresponding to the scan component according to a predetermined mapping relationship between the stamp size and the cropping specification, and using the stamp center as a cropping center to pre-predetermine
  • the cutting shape is set to cut the scanning piece according to the determined cutting specification to obtain a stamp picture to be verified.
  • the seals are available in a variety of sizes and sizes. Different cut specifications are used for different seal specifications. Large seals are used, larger cut specifications are used, and smaller seals are used with smaller cut specifications, so that the seals to be verified are obtained.
  • the outer area of the seal in the picture is not too much, which is convenient for subsequent processing of the seal picture.
  • the system has a mapping table of preset stamp specifications and cutting specifications, and according to the stamp specifications in the identified scans, the corresponding cropping specifications are found from the mapping table, and the recognized stamp centers are identified according to the corresponding cutting specifications.
  • the scanning member is cut as a cutting center to obtain a stamp image to be verified, and the cutting shape may be a rectangle, a circle, or the like.
  • the present application also proposes a physical seal recognition system.
  • FIG. 4 is a schematic diagram of an operating environment of a preferred embodiment of the physical seal identification system 10 of the present application.
  • the physical seal recognition system 10 is installed and operated in the electronic device 1.
  • the electronic device 1 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a server.
  • the electronic device 1 may include, but is not limited to, a memory 11, a processor 12, and a display 13.
  • Figure 4 shows only the electronic device 1 with components 11-13, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.
  • the memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a hard disk or memory of the electronic device 1.
  • the memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in hard disk equipped on the electronic device 1, a smart memory card (SMC), and a secure digital (SD). Card, flash card, etc.
  • the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device.
  • the memory 11 is used to store application software and various types of data installed in the electronic device 1, such as program codes of the physical seal recognition system 10.
  • the memory 11 can also be used to temporarily store data that has been output or is about to be output.
  • the processor 12 in some embodiments, may be a Central Processing Unit (CPU), microprocessor or other data processing chip for running program code or processing data stored in the memory 11, such as performing physical seal recognition. System 10 and so on.
  • CPU Central Processing Unit
  • microprocessor or other data processing chip for running program code or processing data stored in the memory 11, such as performing physical seal recognition. System 10 and so on.
  • the display 13 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch sensor, or the like in some embodiments.
  • the display 13 is for displaying information processed in the electronic device 1 and a user interface or the like for displaying visualization.
  • the components 11-13 of the electronic device 1 communicate with one another via a system bus.
  • FIG. 5 is a program block diagram of a preferred embodiment of the physical seal identification system 10 of the present application.
  • the physical seal recognition system 10 can be divided into one or more modules, one or more modules are stored in the memory 11, and by one or more processors (the processor 12 in this embodiment) Executed to complete the application.
  • the physical seal recognition system 10 can be divided into a receiving module 101, a first cropping module 102, a detecting module 103, a synthesizing module 104, an adjusting module 105, and a verifying module 106.
  • a module as referred to in the present application refers to a series of computer program instruction segments capable of performing a specific function, and is more suitable than the program for describing the execution process of the physical seal recognition system 10 in the electronic device 1, wherein:
  • the receiving module 101 is configured to receive a scan to be verified
  • the user When a user needs to perform physical stamp authenticity identification on a file, the user uploads a scanned copy of the file to be verified into the system, and the system receives the scanned piece to be verified.
  • the first cropping module 102 is configured to identify a stamp center in the scan member, and use the stamp center as a crop center to cut the scan member according to a preset cropping shape according to a preset cropping shape to obtain a to-be-verified image.
  • the scanning part is first cut, and the stamp picture including the stamp of the authenticity to be recognized is cut out.
  • the stamp center of the stamp portion on the scan member is found, and the stamp center is used as the center of the crop region, and the scan member is cut according to a predetermined cropping size (ie, the crop size) by using a preset crop shape.
  • the cropped picture is the one to be verified.
  • the preset cropping shape is preferably a rectangle, that is, a rectangular image is obtained by cutting out; of course, the preset cropping shape may also be other shapes (for example, a circle).
  • the detecting module 103 is configured to detect file characters in the seal picture, and remove all detected file characters;
  • the embodiment preferably adopts the method of removing the document characters in the stamp picture by: identifying different color points in the seal picture that are different from the preset reference color, and removing all the identified different color points; wherein, The reference color is the same as the color of the stamp of the stamp. Since the color of the document text is different from the stamp color of the stamp, after removing all the different color points different from the reference color, it is equivalent to removing all the files in the stamp image. In the text, only the imprinted portion of the stamp and the blank area left by the position of the text are left in the stamp image.
  • the synthesizing module 104 is configured to deduct the center point from the stamp image after the de-word processing and remove the blank area left in the document text, so that the center point of the deduction coincides with the stamp center of the original chapter mode picture, and the blank is Forming a region onto the original chapter mode image to form a seal verification map;
  • the center point in the stamp image after the word processing ie, the stamp center on the stamp image
  • the stamp image after the word processing is removed from the stamp image after the word processing, and the blank area left in the document text is removed.
  • the content of the deduction is synthesized into the original chapter mode image to form a seal verification map; the center point of the deduction is coincident with the stamp center of the original chapter mode picture, so that the original chapter mode picture is added and de-texted.
  • the original chapter mode image is preferably the same size and shape as the clip image obtained by the cropping
  • the adjustment module 105 is configured to rotate the blank area in the seal verification map relative to the original chapter mode, and sequentially rotate in the same direction around the center point, and rotate the preset angle each time until one rotation. After each time the blank area is rotated relative to the original chapter mode picture, the post-word processed stamp picture is compared with the seal verification picture by a preset similarity algorithm to obtain a post-word processed seal picture and The seal verifies the similarity of the map;
  • the next step is to adjust the coverage of the blank area on the original chapter image, so that the blank area is relative to the original stamp picture.
  • the position of the stamp is the same as the position of the blank image after the word processing; in this embodiment, the blank area on the stamp verification map is taken around the center of the original chapter mode picture.
  • the manner of rotation the same angle is rotated each time (ie, the preset angle is, for example, 0.5 degrees) until the blank area is rotated one week with respect to the original chapter mode picture, and after each rotation operation, the word processing is performed.
  • the post stamp image is compared with the stamp verification map by a preset similarity algorithm (for example, the peak signal to noise ratio psnr algorithm), and the similarity between the seal verification map after each rotation and the stamp image after the word processing is calculated. Therefore, the seal verification map with the highest similarity to the stamp image after the word processing can be found, and the seal verification map with the highest similarity is obtained.
  • a preset similarity algorithm for example, the peak signal to noise ratio psnr algorithm
  • the verification module 106 is configured to obtain a seal verification map with the highest similarity to the stamp image after the de-word processing, and compare the seal verification map with the pre-word-processed seal image by using a preset comparison manner, and confirm the comparison according to the comparison result. The authenticity of the seal on the seal picture.
  • the seal verification map with the highest similarity to the stamp image after the word processing is found, and then the seal verification map is compared with the stamp image after the word processing by the preset comparison method, and the seal on the seal image is confirmed based on the comparison result.
  • the preset comparison mode may be a general seal comparison confirmation mode.
  • the seal picture including the seal of the verification to be recognized is cut out from the scan piece, all the file characters in the seal picture are detected and removed, and the seal picture is buckled.
  • the content of the deduction is synthesized into the original chapter mode picture to obtain the seal verification picture, and then the detained blank area is rotated successively with respect to the original chapter mode picture, and Calculate the similarity between the seal verification image after each rotation and the stamp image after the word processing, so as to find the seal verification diagram with the highest similarity to the stamp image after the word processing, and finally the seal verification diagram with the highest similarity and
  • the stamp image after the word processing is compared, and the authenticity of the stamp on the stamp image is confirmed based on the comparison result.
  • the file text in the seal picture to be verified is removed, and the blank area left by the file text on the seal picture is synthesized into the original chapter mode picture, thereby adding and deleting the word processing on the original chapter mode picture.
  • the stamp image after the word processing is compared with the original chapter image after the composite blank area to verify the authenticity of the seal on the seal picture, thus avoiding the seal on the seal picture.
  • the influence of the document text on the seal picture on the verification comparison result improves the accuracy of the seal identification of the seal picture; and the program does not need to be specific after receiving the scanned piece to be verified.
  • the verification module 106 includes:
  • a first comparison sub-module configured to extract a de-word-processed seal picture and compare the outline of the seal verification image to obtain a first comparison result value
  • a second comparison sub-module configured to separately extract the text of the stamp after the word processing and the characters and numbers on the stamp of the stamp verification map, and separately compare the characters and numbers extracted from the stamps of the two stamps, Obtaining a second comparison result value
  • a third comparison sub-module configured to compare the de-word-processed stamp image and the seal verification map by cutting five corners of the five-pointed star on the stamp into a fold line, and obtaining a third comparison result value ;
  • a calculation submodule configured to weight the first comparison result value, the second comparison result value, and the third comparison result value according to a preset weight to obtain a determination result value
  • the seal contrast is divided into three parts and divided into three parts, which are the contrast of the seal outline, the contrast of the characters and numbers on the stamp, and the contrast of the five-pointed star on the stamp to obtain the respective comparison results, according to the respective comparison results.
  • the weight of the weight determines the final decision result value.
  • the first comparison result value A, the second comparison result value B, and the third comparison result value C each have a preset weight of 0.2, 0.5, and 0.3, respectively, and the determination result value is 0.2A+0.5B+0.3C.
  • a result determining submodule configured to: when the determination result value is greater than the first threshold, determine that the seal on the seal picture is a true chapter, and when the determination result value is less than or equal to a second threshold, determine the seal picture The seal is a fake seal.
  • the first threshold is 90%
  • the second threshold is 60%. If the determination result value is greater than 90%, it is determined that the seal on the seal picture is a true chapter, and if the determination result value is less than or equal to 60%, then Determining that the seal on the seal picture is false; in addition, if the value of the determination result is greater than 60% and less than or equal to 90%, the authenticity of the seal on the seal picture may not be clearly determined, and other means or The method is further identified.
  • FIG. 6 is a program module diagram of a second embodiment of the physical seal identification system of the present application.
  • the physical seal recognition system further includes:
  • the filtering module 107 is configured to perform noise detection on the stamp image to remove the detected noise.
  • the stamp image is used for noise detection to remove the detected noise (filtering can be used to filter discrete data points).
  • FIG. 7 is a program module diagram of a third embodiment of the physical seal identification system of the present application.
  • the physical seal recognition system of the embodiment replaces the first cropping module 102 with a second cropping module 108, and the second cropping module 108 is configured to identify a stamp center and a stamp specification in the scan component according to a predetermined stamp specification. Determining a cutting specification corresponding to the cutting specification, determining a cutting specification corresponding to the scanning component, using the marking center as a cutting center, and cutting the scanning component according to the determined cutting specification by using a preset cutting shape to obtain a seal to be verified image.
  • the seals are available in a variety of sizes and sizes. Different cut specifications are used for different seal specifications. Large seals are used, larger cut specifications are used, and smaller seals are used with smaller cut specifications, so that the seals to be verified are obtained.
  • the outer area of the seal in the picture is not too much, which is convenient for subsequent processing of the seal picture.
  • the system has a mapping table of preset stamp specifications and cutting specifications, and according to the stamp specifications in the identified scans, the corresponding cropping specifications are found from the mapping table, and the recognized stamp centers are identified according to the corresponding cutting specifications.
  • the scanning member is cut as a cutting center to obtain a stamp image to be verified, and the cutting shape may be a rectangle, a circle, or the like.
  • the present application further provides a computer readable storage medium storing a physical seal recognition system, the physical seal recognition system being executable by at least one processor to cause the at least one process
  • the physical stamp recognition method in any of the above embodiments is performed.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Collating Specific Patterns (AREA)

Abstract

本申请公开一种电子装置、物理印章识别方法和计算机可读存储介质，该方法包括接收待验证的扫描件；识别扫描件中的印章中心，将印章中心作为裁剪中心对扫描件进行裁剪，得到待验证的印章图片；检测印章图片中的文件文字并去除；从印章图片中扣取中心点和去除文件文字处留下的空白区域合成到原始章模图片上，形成印章验证图；将印章验证图中的空白区域相对原始章模图片逐次旋转，每次旋转预设角度，在每次旋转后，将去文字处理后的印章图片与印章验证图进行预设的相似度算法比较；将相似度最高的印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，以确认印章图片上的印章的真伪。本申请技术方案提升物理印章识别的准确性和时效性。

Description

电子装置、物理印章识别方法和计算机可读存储介质
本申请基于巴黎公约申明享有2018年3月14日递交的申请号为CN 201810208740.2、名称为“电子装置、物理印章识别方法和计算机可读存储介质”中国专利申请的优先权，该中国专利申请的整体内容以参考的方式结合在本申请中。
技术领域
本申请涉及图像处理技术领域，特别涉及一种电子装置、物理印章识别方法和计算机可读存储介质。
背景技术
目前，对物理印章的真伪鉴定，主要依赖于个人经验的判断以及物理上的甄别。通过图像处理和机器学习进行智能判断印章真伪的产品很少。少数支持智能鉴别物理印章真伪的产品，对环境和设备条件要求高，需要在特定场景和特定设备下进行，通常在时效性和准确性上无法满足要求。
发明内容
本申请提供一种电子装置、物理印章识别方法和计算机可读存储介质，旨在提升物理印章识别的准确性和时效性。
本申请第一方面提供一种电子装置，所述电子装置包括存储器和处理器，所述存储器上存储有可在所述处理器上运行的物理印章识别系统，所述物理印章识别系统被所述处理器执行时实现如下步骤：
接收待验证的扫描件；
识别所述扫描件中的印章中心，将所述印章中心作为裁剪中心，以预设的裁剪形状按预设的裁剪规格对所述扫描件进行裁剪，得到待验证的印章图片；
检测所述印章图片中的文件文字，将检测出的所有文件文字去除；
从去文字处理后的印章图片中扣取中心点和去除文件文字处留下的空白区域，使扣取的中心点与原始章模图片的印章中心重合，将所述空白区域合成到所述原始章模图片上，形成印章验证图；
将所述印章验证图中的所述空白区域相对所述原始章模图片，以所述中心点为中心朝同一方向逐次旋转，每次旋转预设角度，直至旋转一周，在每次将空白区域相对所述原始章模图片旋转后，将去文字处理后的印章图片与所述印章验证图进行一次预设的相似度算法比较，以得出去文字处理后的印章图片与所述印章验证图的相似度；
获取与去文字处理后的印章图片相似度最高的印章验证图，将该 印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪。
本申请第二方面提供一种物理印章识别方法，所述物理印章识别方法包括：
接收待验证的扫描件；
识别所述扫描件中的印章中心，将所述印章中心作为裁剪中心，以预设的裁剪形状按预设的裁剪规格对所述扫描件进行裁剪，得到待验证的印章图片；
检测所述印章图片中的文件文字，将检测出的所有文件文字去除；
从去文字处理后的印章图片中扣取中心点和去除文件文字处留下的空白区域，使扣取的中心点与原始章模图片的印章中心重合，将所述空白区域合成到所述原始章模图片上，形成印章验证图；
将所述印章验证图中的所述空白区域相对所述原始章模图片，以所述中心点为中心朝同一方向逐次旋转，每次旋转预设角度，直至旋转一周，在每次将空白区域相对所述原始章模图片旋转后，将去文字处理后的印章图片与所述印章验证图进行一次预设的相似度算法比较，以得出去文字处理后的印章图片与所述印章验证图的相似度；
获取与去文字处理后的印章图片相似度最高的印章验证图，将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪。
本申请第三方面提供一种计算机可读存储介质，所述计算机可读存储介质存储有物理印章识别系统，所述物理印章识别系统可被至少一个处理器执行，以使所述至少一个处理器执行如下步骤：
接收待验证的扫描件；
识别所述扫描件中的印章中心，将所述印章中心作为裁剪中心，以预设的裁剪形状按预设的裁剪规格对所述扫描件进行裁剪，得到待验证的印章图片；
检测所述印章图片中的文件文字，将检测出的所有文件文字去除；
从去文字处理后的印章图片中扣取中心点和去除文件文字处留下的空白区域，使扣取的中心点与原始章模图片的印章中心重合，将所述空白区域合成到所述原始章模图片上，形成印章验证图；
将所述印章验证图中的所述空白区域相对所述原始章模图片，以所述中心点为中心朝同一方向逐次旋转，每次旋转预设角度，直至旋转一周，在每次将空白区域相对所述原始章模图片旋转后，将去文字处理后的印章图片与所述印章验证图进行一次预设的相似度算法比较，以得出去文字处理后的印章图片与所述印章验证图的相似度；
获取与去文字处理后的印章图片相似度最高的印章验证图，将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪。
本申请技术方案，在接收到待验证的扫描件后，从扫描件中裁剪出包括待识别验证真伪的印章的印章图片，检测出印章图片中的所有文件文字并去除，扣取印章图片在去文字处留下的空白区域和印章图片的中心点，将扣取的内容合成到原始章模图片上得到印章验证图，再将扣取的空白区域相对于原始章模图片逐次旋转，并计算每次旋转后的印章验证图与去文字处理后的印章图片的相似度，从而找到与去文字处理后的印章图片相似度最高的印章验证图，最终将该相似度最高的印章验证图与去文字处理后的印章图片进行比较，根据比较结果确认印章图片上的印章的真伪。本申请方案通过采用将待验证的印章图片中的文件文字去除，将印章图片上去除文件文字留下的空白区域合成到原始章模图片上，从而在原始章模图片上增加与去文字处理后的印章图片相同的空白覆盖区域，再将去文字处理后的印章图片与该合成空白区域后的原始章模图片比较以验证印章图片上的印章真伪，如此回避了在对印章图片的印章真伪识别验证过程中，印章图片上的文件文字对验证比较结果的影响，提升了对印章图片的印章真伪识别的准确率；并且本方案在接收到待验证的扫描件后，无需特定的设备和特定的场景要求，能够立即进行验证处理，快速的反馈验证结果，时效性好。
附图说明
图1为本申请物理印章识别方法一实施例的流程示意图；
图2为本申请物理印章识别方法二实施例的流程示意图；
图3为本申请物理印章识别方法三实施例的流程示意图；
图4为本申请物理印章识别系统一实施例的运行环境示意图；
图5为本申请物理印章识别系统一实施例的程序模块图；
图6为本申请物理印章识别系统二实施例的程序模块图；
图7为本申请物理印章识别系统三实施例的程序模块图。
具体实施方式
以下结合附图对本申请的原理和特征进行描述，所举实例只用于解释本申请，并非用于限定本申请的范围。
如图1所示，图1为本申请物理印章识别方法一实施例的流程示意图。
本实施例中，该物理印章识别方法包括：
步骤S10，接收待验证的扫描件；
当有用户需要对文件进行物理印章真伪识别需求时，用户将待验证文件的扫描件上传到系统中，系统接收待验证的扫描件。
步骤S20，识别所述扫描件中的印章中心，将所述印章中心作为裁剪中心，以预设的裁剪形状按预设的裁剪规格对所述扫描件进行裁剪，得到待验证的印章图片；
由于扫描件本身图片比较大，而需要识别的只是扫描件上的印章部分，因此先对扫描件进行裁剪，裁剪出包括待识别真伪的印章的印章图片。具体的，首先找到扫描件上的印章部分的印章中心，以这个印章中心作为裁剪区域的中心，采用预先设定的裁剪形状按照预先确定的裁剪规格(即裁剪尺寸大小)对扫描件进行裁剪，裁剪出来的则为待验证的印章图片。本实施中，预设的裁剪形状优选为矩形，即裁剪出来得到的是矩形图片；当然，预设的裁剪形状还可以为其它形状(例如圆形)。
步骤S30，检测所述印章图片中的文件文字，将检测出的所有文件文字去除；
在裁剪得到待验证的印章图片后，去检测找出该印章图片中的所有文件文字(即除印章文字外的其它文字)，然后把检测到的这些文件文字全部从印章图片上去除。本实施例优选采用去除印章图片中的文件文字的方式为：识别出所述印章图片中所有的颜色与预设的参考颜色不同的异色点，将识别出的所有异色点去除；其中，该参考颜色与所述印章的印记的颜色相同，由于文件文字的颜色与印章的印记颜色不同，因此，去除所有与参考颜色不同的异色点之后，就相当于去除了印章图片中的所有文件文字，印章图片中只剩下印章的印记部分和去除文字位置留下的空白区域。
步骤S40，从去文字处理后的印章图片中扣取中心点和去除文件文字处留下的空白区域，使扣取的中心点与原始章模图片的印章中心重合，将所述空白区域合成到所述原始章模图片上，形成印章验证图；
印章图片去除文件文字后，从去文字处理后的印章图片中，扣取去文字处理后的印章图片中的中心点(即印章图片上的印章中心)和去除文件文字处留下的空白区域，将扣取的内容合成到原始章模图片上，形成印章验证图；在合成时采取扣取的中心点与原始章模图片的印章中心重合，这样则在原始章模图片上增加了与去文字处理后的印章图片上的空白区域相同的覆盖区域。原始章模图片优选采取与裁剪得到的印章图片的大小形状相同
步骤S50，将所述印章验证图中的所述空白区域相对所述原始章模图片，以所述中心点为中心朝同一方向逐次旋转，每次旋转预设角度，直至旋转一周，在每次将空白区域相对所述原始章模图片旋转后， 将去文字处理后的印章图片与所述印章验证图进行一次预设的相似度算法比较，以得出去文字处理后的印章图片与所述印章验证图的相似度；
在原始章模图片上增加了与去文字处理后的印章图片上的空白区域相同的覆盖区域后，接下来需要调节该空白区域在原始章模图片上的覆盖位置，使空白区域相对原始印章图片的位置与空白区域相对去文字处理后的印章图片的位置相同；本实施例采取让印章验证图上的所述空白区域相对于所述原始章模图片，绕所述原始章模图片的中心逐次旋转的方式，每次旋转相同的角度(即预设角度，例如为0.5度)，直到所述空白区域相对所述原始章模图片旋转一周，并且在每一次旋转操作后，都将去文字处理后的印章图片与所述印章验证图进行一次预设的相似度算法(例如峰值信噪比psnr算法)比较，算出每次旋转后的印章验证图与去文字处理后的印章图片的相似度，从而可以找到与去文字处理后的印章图片的相似度最高的印章验证图，该相似度最高的印章验证图相当于是在原始章模图片上增加了与去文字处理后的印章图片上的空白区域位置相同的覆盖区域(也是空白区域)，如此，去文字处理后的印章图片上和原始印章图片上的覆盖区域(即空白区域)相同(位置、大小、形状都相同)，覆盖区域对印章图片和原始章模图片的影响相同，只需将两者的剩余区域(除去空白区域)进行比较以确定印章图片上的印章的真伪。
步骤S60，获取与去文字处理后的印章图片相似度最高的印章验证图，将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪。
先找到与去文字处理后的印章图片相似度最高的印章验证图，然后将该印章验证图通过预设的比较方式与其文字处理后的印章图片进行比较，基于比较结果确认印章图片上的印章真伪。本实施例中，预设的比较方式可为通用的印章比较确认方式。
本实施例技术方案，在接收到待验证的扫描件后，从扫描件中裁剪出包括待识别验证真伪的印章的印章图片，检测出印章图片中的所有文件文字并去除，扣取印章图片在去文字处留下的空白区域和印章图片的中心点，将扣取的内容合成到原始章模图片上得到印章验证图，再将扣取的空白区域相对于原始章模图片逐次旋转，并计算每次旋转后的印章验证图与去文字处理后的印章图片的相似度，从而找到与去文字处理后的印章图片相似度最高的印章验证图，最终将该相似度最高的印章验证图与去文字处理后的印章图片进行比较，根据比较结果确认印章图片上的印章的真伪。本实施例方案通过采用将待验证的印章图片中的文件文字去除，将印章图片上去除文件文字留下的空白区域合成到原始章模图片上，从而在原始章模图片上增加与去文字 处理后的印章图片相同的空白覆盖区域，再将去文字处理后的印章图片与该合成空白区域后的原始章模图片比较以验证印章图片上的印章真伪，如此回避了在对印章图片的印章真伪识别验证过程中，印章图片上的文件文字对验证比较结果的影响，提升了对印章图片的印章真伪识别的准确率；并且本方案在接收到待验证的扫描件后，无需特定的设备和特定的场景要求，能够立即进行验证处理，快速的反馈验证结果，时效性好。
本实施例中，所述将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪的步骤包括：
提取去文字处理后的印章图片与所述印章验证图的轮廓进行对比，得到第一对比结果值；
分别提取去文字处理后的印章图片与所述印章验证图的印模上的文字及数字，将从两者的印模上提取的文字和数字分别进行单独对比，得到第二对比结果值；
将所述去文字处理后的印章图片与所述印章验证图的分别通过将印模上五角星的五个角切割为折线后进行对比，得到第三对比结果值；
将所述第一对比结果值、第二对比结果值和第三对比结果值按预设的权重加权求和得出判定结果值；
本实施例将印章对比分别分成三个部分分开对比，分别为印章轮廓对比、印模上的文字及数字的对比，以及印模上的五角星的对比，以得到各个对比结果，根据各个对比结果占的权重确定最终的判定结果值。例如，第一对比结果值A、第二对比结果值B和第三对比结果值C各自预设的权重分别为0.2、0.5、0.3，则判定结果值为0.2A+0.5B+0.3C。
若所述判定结果值大于第一阈值，则确定所述印章图片上的印章为真章；
若所述判定结果值小于等于第二阈值，则确定所述印章图片上的印章为假章。
例如，第一阈值为90％，第二阈值为60％，如果所述判定结果值大于90％，确定为所述印章图片上的印章为真章，如果所述判定结果值小于等于60％，则确定所述印章图片上的印章为假；另外，如果所述判定结果值大于60％且小于等于90％，则可能对该印章图片上的印章真伪不能明确确定真伪，需要通过其他手段或方法来进一步识别。
如图2所示，图2为本申请物理印章识别方法二实施例的流程示 意图。本实施例中，在所述步骤S30之前，所述物理印章识别方法还包括：
步骤S70，对所述印章图片进行噪点检测，去除检测出的噪点。
由于印章图片上通常会存在由于印泥造成的噪点或由于打印及扫描造成的一些不可控噪点，这些噪点会对印章图片的印章真伪识别造成干扰，影响识别验证结果的准确性，因此，需要对印章图片进行噪点检测，去除检测出的噪点(可采用滤波将离散的数据点过滤)。
如图3所示，图3为本申请物理印章识别方法三实施例的流程示意图。本实施例物理印章识别方法将所述步骤S20替换为：
步骤S80，识别所述扫描件中的印章中心和印章规格，根据预先确定的印章规格与裁剪规格的映射关系，确定所述扫描件对应的裁剪规格，将所述印章中心作为裁剪中心，以预设的裁剪形状按确定的裁剪规格对所述扫描件进行裁剪，得到待验证的印章图片。
印章有多种大小规格，针对不同的印章规格采取不同的裁剪规格，规格大的印章，采用较大的裁剪规格，规格小的印章相应采用较小的裁剪规格，使得裁剪得到的待验证的印章图片中的印章的外侧区域不会太多，方便后续对印章图片的处理。系统中具有预先设定的印章规格与裁剪规格的映射表，根据识别出的扫描件中的印章规格，从该映射表中找到对应的裁剪规格，根据该对应的裁剪规格以识别到的印章中心作为裁剪中心对扫描件进行裁剪，从而得到待验证的印章图片，裁剪形状可以为矩形、圆形等。
此外，本申请还提出一种物理印章识别系统。
请参阅图4，是本申请物理印章识别系统10较佳实施例的运行环境示意图。
在本实施例中，物理印章识别系统10安装并运行于电子装置1中。电子装置1可以是桌上型计算机、笔记本、掌上电脑及服务器等计算设备。该电子装置1可包括，但不仅限于，存储器11、处理器12及显示器13。图4仅示出了具有组件11-13的电子装置1，但是应理解的是，并不要求实施所有示出的组件，可以替代的实施更多或者更少的组件。
存储器11在一些实施例中可以是电子装置1的内部存储单元，例如该电子装置1的硬盘或内存。存储器11在另一些实施例中也可以是电子装置1的外部存储设备，例如电子装置1上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。进一步地，存储器11还可以既包括电子装置1的内部存储单元也包括外部存储设备。存储器11用于 存储安装于电子装置1的应用软件及各类数据，例如物理印章识别系统10的程序代码等。存储器11还可以用于暂时地存储已经输出或者将要输出的数据。
处理器12在一些实施例中可以是一中央处理器(Central Processing Unit,CPU)，微处理器或其他数据处理芯片，用于运行存储器11中存储的程序代码或处理数据，例如执行物理印章识别系统10等。
显示器13在一些实施例中可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(Organic Light-Emitting Diode，有机发光二极管)触摸器等。显示器13用于显示在电子装置1中处理的信息以及用于显示可视化的用户界面等。电子装置1的部件11-13通过系统总线相互通信。
请参阅图5，是本申请物理印章识别系统10较佳实施例的程序模块图。在本实施例中，物理印章识别系统10可以被分割成一个或多个模块，一个或者多个模块被存储于存储器11中，并由一个或多个处理器(本实施例为处理器12)所执行，以完成本申请。例如，在图5中，物理印章识别系统10可以被分割成接收模块101、第一裁剪模块102、检测模块103、合成模块104、调节模块105及验证模块106。本申请所称的模块是指能够完成特定功能的一系列计算机程序指令段，比程序更适合于描述物理印章识别系统10在电子装置1中的执行过程，其中：
接收模块101，用于接收待验证的扫描件；
当有用户需要对文件进行物理印章真伪识别需求时，用户将待验证文件的扫描件上传到系统中，系统接收待验证的扫描件。
第一裁剪模块102，用于识别所述扫描件中的印章中心，将所述印章中心作为裁剪中心，以预设的裁剪形状按预设的裁剪规格对所述扫描件进行裁剪，得到待验证的印章图片；
由于扫描件本身图片比较大，而需要识别的只是扫描件上的印章部分，因此先对扫描件进行裁剪，裁剪出包括待识别真伪的印章的印章图片。具体的，首先找到扫描件上的印章部分的印章中心，以这个印章中心作为裁剪区域的中心，采用预先设定的裁剪形状按照预先确定的裁剪规格(即裁剪尺寸大小)对扫描件进行裁剪，裁剪出来的则为待验证的印章图片。本实施中，预设的裁剪形状优选为矩形，即裁剪出来得到的是矩形图片；当然，预设的裁剪形状还可以为其它形状(例如圆形)。
检测模块103，用于检测所述印章图片中的文件文字，将检测出的所有文件文字去除；
在裁剪得到待验证的印章图片后，去检测找出该印章图片中的所 有文件文字(即除印章文字外的其它文字)，然后把检测到的这些文件文字全部从印章图片上去除。本实施例优选采用去除印章图片中的文件文字的方式为：识别出所述印章图片中所有的颜色与预设的参考颜色不同的异色点，将识别出的所有异色点去除；其中，该参考颜色与所述印章的印记的颜色相同，由于文件文字的颜色与印章的印记颜色不同，因此，去除所有与参考颜色不同的异色点之后，就相当于去除了印章图片中的所有文件文字，印章图片中只剩下印章的印记部分和去除文字位置留下的空白区域。
合成模块104，用于从去文字处理后的印章图片中扣取中心点和去除文件文字处留下的空白区域，使扣取的中心点与原始章模图片的印章中心重合，将所述空白区域合成到所述原始章模图片上，形成印章验证图；
印章图片去除文件文字后，从去文字处理后的印章图片中，扣取去文字处理后的印章图片中的中心点(即印章图片上的印章中心)和去除文件文字处留下的空白区域，将扣取的内容合成到原始章模图片上，形成印章验证图；在合成时采取扣取的中心点与原始章模图片的印章中心重合，这样则在原始章模图片上增加了与去文字处理后的印章图片上的空白区域相同的覆盖区域。原始章模图片优选采取与裁剪得到的印章图片的大小形状相同
调节模块105，用于将所述印章验证图中的所述空白区域相对所述原始章模图片，以所述中心点为中心朝同一方向逐次旋转，每次旋转预设角度，直至旋转一周，在每次将空白区域相对所述原始章模图片旋转后，将去文字处理后的印章图片与所述印章验证图进行一次预设的相似度算法比较，以得出去文字处理后的印章图片与所述印章验证图的相似度；
在原始章模图片上增加了与去文字处理后的印章图片上的空白区域相同的覆盖区域后，接下来需要调节该空白区域在原始章模图片上的覆盖位置，使空白区域相对原始印章图片的位置与空白区域相对去文字处理后的印章图片的位置相同；本实施例采取让印章验证图上的所述空白区域相对于所述原始章模图片，绕所述原始章模图片的中心逐次旋转的方式，每次旋转相同的角度(即预设角度，例如为0.5度)，直到所述空白区域相对所述原始章模图片旋转一周，并且在每一次旋转操作后，都将去文字处理后的印章图片与所述印章验证图进行一次预设的相似度算法(例如峰值信噪比psnr算法)比较，算出每次旋转后的印章验证图与去文字处理后的印章图片的相似度，从而可以找到与去文字处理后的印章图片的相似度最高的印章验证图，该相似度最高的印章验证图相当于是在原始章模图片上增加了与去文字处理后的印章图片上的空白区域位置相同的覆盖区域(也是空白区 域)，如此，去文字处理后的印章图片上和原始印章图片上的覆盖区域(即空白区域)相同(位置、大小、形状都相同)，覆盖区域对印章图片和原始章模图片的影响相同，只需将两者的剩余区域(除去空白区域)进行比较以确定印章图片上的印章的真伪。
验证模块106，用于获取与去文字处理后的印章图片相似度最高的印章验证图，将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪。
先找到与去文字处理后的印章图片相似度最高的印章验证图，然后将该印章验证图通过预设的比较方式与其文字处理后的印章图片进行比较，基于比较结果确认印章图片上的印章真伪。本实施例中，预设的比较方式可为通用的印章比较确认方式。
本实施例技术方案，在接收到待验证的扫描件后，从扫描件中裁剪出包括待识别验证真伪的印章的印章图片，检测出印章图片中的所有文件文字并去除，扣取印章图片在去文字处留下的空白区域和印章图片的中心点，将扣取的内容合成到原始章模图片上得到印章验证图，再将扣取的空白区域相对于原始章模图片逐次旋转，并计算每次旋转后的印章验证图与去文字处理后的印章图片的相似度，从而找到与去文字处理后的印章图片相似度最高的印章验证图，最终将该相似度最高的印章验证图与去文字处理后的印章图片进行比较，根据比较结果确认印章图片上的印章的真伪。本实施例方案通过采用将待验证的印章图片中的文件文字去除，将印章图片上去除文件文字留下的空白区域合成到原始章模图片上，从而在原始章模图片上增加与去文字处理后的印章图片相同的空白覆盖区域，再将去文字处理后的印章图片与该合成空白区域后的原始章模图片比较以验证印章图片上的印章真伪，如此回避了在对印章图片的印章真伪识别验证过程中，印章图片上的文件文字对验证比较结果的影响，提升了对印章图片的印章真伪识别的准确率；并且本方案在接收到待验证的扫描件后，无需特定的设备和特定的场景要求，能够立即进行验证处理，快速的反馈验证结果，时效性好。
进一步地，本实施例中，所述验证模块106包括：
获取子模块，用于获取与去文字处理后的印章图片相似度最高的印章验证图；
第一对比子模块，用于提取去文字处理后的印章图片与所述印章验证图的轮廓进行对比，得到第一对比结果值；
第二对比子模块，用于分别提取去文字处理后的印章图片与所述印章验证图的印模上的文字及数字，将从两者的印模上提取的文字和 数字分别进行单独对比，得到第二对比结果值；
第三对比子模块，用于将所述去文字处理后的印章图片与所述印章验证图的分别通过将印模上五角星的五个角切割为折线后进行对比，得到第三对比结果值；
计算子模块，用于将所述第一对比结果值、第二对比结果值和第三对比结果值按预设的权重加权求和得出判定结果值；
本实施例将印章对比分别分成三个部分分开对比，分别为印章轮廓对比、印模上的文字及数字的对比，以及印模上的五角星的对比，以得到各个对比结果，根据各个对比结果占的权重确定最终的判定结果值。例如，第一对比结果值A、第二对比结果值B和第三对比结果值C各自预设的权重分别为0.2、0.5、0.3，则判定结果值为0.2A+0.5B+0.3C。
结果确定子模块，用于在所述判定结果值大于第一阈值时，确定所述印章图片上的印章为真章，以及在所述判定结果值小于等于第二阈值时，确定所述印章图片上的印章为假章。
例如，第一阈值为90％，第二阈值为60％，如果所述判定结果值大于90％，确定为所述印章图片上的印章为真章，如果所述判定结果值小于等于60％，则确定所述印章图片上的印章为假；另外，如果所述判定结果值大于60％且小于等于90％，则可能对该印章图片上的印章真伪不能明确确定真伪，需要通过其他手段或方法来进一步识别。
如图6所示，图6为本申请物理印章识别系统二实施例的程序模块图。本实施例中，所述物理印章识别系统还包括：
过滤模块107，用于对所述印章图片进行噪点检测，去除检测出的噪点。
由于印章图片上通常会存在由于印泥造成的噪点或由于打印及扫描造成的一些不可控噪点，这些噪点会对印章图片的印章真伪识别造成干扰，影响识别验证结果的准确性，因此，需要对印章图片进行噪点检测，去除检测出的噪点(可采用滤波将离散的数据点过滤)。
如图7所示，图7为本申请物理印章识别系统三实施例的程序模块图。本实施例物理印章识别系统将所述第一裁剪模块102替换为第二裁剪模块108，第二裁剪模块108，用于识别所述扫描件中的印章中心和印章规格，根据预先确定的印章规格与裁剪规格的映射关系，确定所述扫描件对应的裁剪规格，将所述印章中心作为裁剪中心，以预设的裁剪形状按确定的裁剪规格对所述扫描件进行裁剪，得到待验证的印章图片。
印章有多种大小规格，针对不同的印章规格采取不同的裁剪规格，规格大的印章，采用较大的裁剪规格，规格小的印章相应采用较 小的裁剪规格，使得裁剪得到的待验证的印章图片中的印章的外侧区域不会太多，方便后续对印章图片的处理。系统中具有预先设定的印章规格与裁剪规格的映射表，根据识别出的扫描件中的印章规格，从该映射表中找到对应的裁剪规格，根据该对应的裁剪规格以识别到的印章中心作为裁剪中心对扫描件进行裁剪，从而得到待验证的印章图片，裁剪形状可以为矩形、圆形等。
进一步地，本申请还提出一种计算机可读存储介质，所述计算机可读存储介质存储有物理印章识别系统，所述物理印章识别系统可被至少一个处理器执行，以使所述至少一个处理器执行上述任一实施例中的物理印章识别方法。
以上所述仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是在本申请的申请构思下，利用本申请说明书及附图内容所作的等效结构变换，或直接/间接运用在其他相关的技术领域均包括在本申请的专利保护范围内。

Claims (20)

  1. 一种电子装置，其特征在于，所述电子装置包括存储器和处理器，所述存储器上存储有可在所述处理器上运行的物理印章识别系统，所述物理印章识别系统被所述处理器执行时实现如下步骤：
    A1、接收待验证的扫描件；
    A2、识别所述扫描件中的印章中心，将所述印章中心作为裁剪中心，以预设的裁剪形状按预设的裁剪规格对所述扫描件进行裁剪，得到待验证的印章图片；
    A3、检测所述印章图片中的文件文字，将检测出的所有文件文字去除；
    A4、从去文字处理后的印章图片中扣取中心点和去除文件文字处留下的空白区域，使扣取的中心点与原始章模图片的印章中心重合，将所述空白区域合成到所述原始章模图片上，形成印章验证图；
    A5、将所述印章验证图中的所述空白区域相对所述原始章模图片，以所述中心点为中心朝同一方向逐次旋转，每次旋转预设角度，直至旋转一周，在每次将空白区域相对所述原始章模图片旋转后，将去文字处理后的印章图片与所述印章验证图进行一次预设的相似度算法比较，以得出去文字处理后的印章图片与所述印章验证图的相似度；
    A6、获取与去文字处理后的印章图片相似度最高的印章验证图，将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪。
  2. 如权利要求1所述的电子装置，其特征在于，所述将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪的步骤包括：
    提取去文字处理后的印章图片与所述印章验证图的轮廓进行对比，得到第一对比结果值；
    分别提取去文字处理后的印章图片与所述印章验证图的印模上的文字及数字，将从两者的印模上提取的文字和数字分别进行单独对比，得到第二对比结果值；
    将所述去文字处理后的印章图片与所述印章验证图的分别通过将印模上五角星的五个角切割为折线后进行对比，得到第三对比结果值；
    将所述第一对比结果值、第二对比结果值和第三对比结果值按预设的权重加权求和得出判定结果值；
    若所述判定结果值大于第一阈值，则确定所述印章图片上的印章为真章；
    若所述判定结果值小于等于第二阈值，则确定所述印章图片上的印章为假章。
  3. 如权利要求1所述的电子装置，其特征在于，在所述步骤A3之前，所述处理器还用于执行所述物理印章识别系统，以实现以下步骤：
    对所述印章图片进行噪点检测，去除检测出的噪点。
  4. 如权利要求3所述的电子装置，其特征在于，所述将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪的步骤包括：
    提取去文字处理后的印章图片与所述印章验证图的轮廓进行对比，得到第一对比结果值；
    分别提取去文字处理后的印章图片与所述印章验证图的印模上的文字及数字，将从两者的印模上提取的文字和数字分别进行单独对比，得到第二对比结果值；
    将所述去文字处理后的印章图片与所述印章验证图的分别通过将印模上五角星的五个角切割为折线后进行对比，得到第三对比结果值；
    将所述第一对比结果值、第二对比结果值和第三对比结果值按预设的权重加权求和得出判定结果值；
    若所述判定结果值大于第一阈值，则确定所述印章图片上的印章为真章；
    若所述判定结果值小于等于第二阈值，则确定所述印章图片上的印章为假章。
  5. 如权利要求1所述的电子装置，其特征在于，所述步骤A3包括：
    识别出所述印章图片中所有的颜色与预设的参考颜色不同的异色点，所述参考颜色与所述印章的印记的颜色相同；
    将识别出的所有异色点去除。
  6. 如权利要求5所述的电子装置，其特征在于，所述将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪的步骤包括：
    提取去文字处理后的印章图片与所述印章验证图的轮廓进行对比，得到第一对比结果值；
    分别提取去文字处理后的印章图片与所述印章验证图的印模上的文字及数字，将从两者的印模上提取的文字和数字分别进行单独对比，得到第二对比结果值；
    将所述去文字处理后的印章图片与所述印章验证图的分别通过将印模上五角星的五个角切割为折线后进行对比，得到第三对比结果 值；
    将所述第一对比结果值、第二对比结果值和第三对比结果值按预设的权重加权求和得出判定结果值；
    若所述判定结果值大于第一阈值，则确定所述印章图片上的印章为真章；
    若所述判定结果值小于等于第二阈值，则确定所述印章图片上的印章为假章。
  7. 如权利要求1所述的电子装置，其特征在于，所述步骤A2替换为：
    识别所述扫描件中的印章中心和印章规格，根据预先确定的印章规格与裁剪规格的映射关系，确定所述扫描件对应的裁剪规格，将所述印章中心作为裁剪中心，以预设的裁剪形状按确定的裁剪规格对所述扫描件进行裁剪，得到待验证的印章图片。
  8. 如权利要求7所述的电子装置，其特征在于，所述将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪的步骤包括：
    提取去文字处理后的印章图片与所述印章验证图的轮廓进行对比，得到第一对比结果值；
    分别提取去文字处理后的印章图片与所述印章验证图的印模上的文字及数字，将从两者的印模上提取的文字和数字分别进行单独对比，得到第二对比结果值；
    将所述去文字处理后的印章图片与所述印章验证图的分别通过将印模上五角星的五个角切割为折线后进行对比，得到第三对比结果值；
    将所述第一对比结果值、第二对比结果值和第三对比结果值按预设的权重加权求和得出判定结果值；
    若所述判定结果值大于第一阈值，则确定所述印章图片上的印章为真章；
    若所述判定结果值小于等于第二阈值，则确定所述印章图片上的印章为假章。
  9. 一种物理印章识别方法，其特征在于，所述物理印章识别方法包括：
    B1、接收待验证的扫描件；
    B2、识别所述扫描件中的印章中心，将所述印章中心作为裁剪中心，以预设的裁剪形状按预设的裁剪规格对所述扫描件进行裁剪，得到待验证的印章图片；
    B3、检测所述印章图片中的文件文字，将检测出的所有文件文字去除；
    B4、从去文字处理后的印章图片中扣取中心点和去除文件文字处留下的空白区域，使扣取的中心点与原始章模图片的印章中心重合，将所述空白区域合成到所述原始章模图片上，形成印章验证图；
    B5、将所述印章验证图中的所述空白区域相对所述原始章模图片，以所述中心点为中心朝同一方向逐次旋转，每次旋转预设角度，直至旋转一周，在每次将空白区域相对所述原始章模图片旋转后，将去文字处理后的印章图片与所述印章验证图进行一次预设的相似度算法比较，以得出去文字处理后的印章图片与所述印章验证图的相似度；
    B6、获取与去文字处理后的印章图片相似度最高的印章验证图，将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪。
  10. 如权利要求9所述的物理印章识别方法，其特征在于，所述将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪的步骤包括：
    提取去文字处理后的印章图片与所述印章验证图的轮廓进行对比，得到第一对比结果值；
    分别提取去文字处理后的印章图片与所述印章验证图的印模上的文字及数字，将从两者的印模上提取的文字和数字分别进行单独对比，得到第二对比结果值；
    将所述去文字处理后的印章图片与所述印章验证图的分别通过将印模上五角星的五个角切割为折线后进行对比，得到第三对比结果值；
    将所述第一对比结果值、第二对比结果值和第三对比结果值按预设的权重加权求和得出判定结果值；
    若所述判定结果值大于第一阈值，则确定所述印章图片上的印章为真章；
    若所述判定结果值小于等于第二阈值，则确定所述印章图片上的印章为假章。
  11. 如权利要求9所述的物理印章识别方法，其特征在于，在所述步骤B3之前，所述物理印章识别方法还包括：
    对所述印章图片进行噪点检测，去除检测出的噪点。
  12. 如权利要求11所述的物理印章识别方法，其特征在于，所述将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪的步骤包括：
    提取去文字处理后的印章图片与所述印章验证图的轮廓进行对 比，得到第一对比结果值；
    分别提取去文字处理后的印章图片与所述印章验证图的印模上的文字及数字，将从两者的印模上提取的文字和数字分别进行单独对比，得到第二对比结果值；
    将所述去文字处理后的印章图片与所述印章验证图的分别通过将印模上五角星的五个角切割为折线后进行对比，得到第三对比结果值；
    将所述第一对比结果值、第二对比结果值和第三对比结果值按预设的权重加权求和得出判定结果值；
    若所述判定结果值大于第一阈值，则确定所述印章图片上的印章为真章；
    若所述判定结果值小于等于第二阈值，则确定所述印章图片上的印章为假章。
  13. 如权利要求9所述的物理印章识别方法，其特征在于，所述步骤B3包括：
    识别出所述印章图片中所有的颜色与预设的参考颜色不同的异色点，所述参考颜色与所述印章的印记的颜色相同；
    将识别出的所有异色点去除。
  14. 如权利要求13所述的物理印章识别方法，其特征在于，所述将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪的步骤包括：
    提取去文字处理后的印章图片与所述印章验证图的轮廓进行对比，得到第一对比结果值；
    分别提取去文字处理后的印章图片与所述印章验证图的印模上的文字及数字，将从两者的印模上提取的文字和数字分别进行单独对比，得到第二对比结果值；
    将所述去文字处理后的印章图片与所述印章验证图的分别通过将印模上五角星的五个角切割为折线后进行对比，得到第三对比结果值；
    将所述第一对比结果值、第二对比结果值和第三对比结果值按预设的权重加权求和得出判定结果值；
    若所述判定结果值大于第一阈值，则确定所述印章图片上的印章为真章；
    若所述判定结果值小于等于第二阈值，则确定所述印章图片上的印章为假章。
  15. 如权利要求9所述的物理印章识别方法，其特征在于，所述步骤B2替换为：
    识别所述扫描件中的印章中心和印章规格，根据预先确定的印章规格与裁剪规格的映射关系，确定所述扫描件对应的裁剪规格，将所述印章中心作为裁剪中心，以预设的裁剪形状按确定的裁剪规格对所述扫描件进行裁剪，得到待验证的印章图片。
  16. 如权利要求15所述的物理印章识别方法，其特征在于，所述将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪的步骤包括：
    提取去文字处理后的印章图片与所述印章验证图的轮廓进行对比，得到第一对比结果值；
    分别提取去文字处理后的印章图片与所述印章验证图的印模上的文字及数字，将从两者的印模上提取的文字和数字分别进行单独对比，得到第二对比结果值；
    将所述去文字处理后的印章图片与所述印章验证图的分别通过将印模上五角星的五个角切割为折线后进行对比，得到第三对比结果值；
    将所述第一对比结果值、第二对比结果值和第三对比结果值按预设的权重加权求和得出判定结果值；
    若所述判定结果值大于第一阈值，则确定所述印章图片上的印章为真章；
    若所述判定结果值小于等于第二阈值，则确定所述印章图片上的印章为假章。
  17. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有物理印章识别系统，所述物理印章识别系统可被至少一个处理器执行，以使所述至少一个处理器执行如下步骤：
    C1、接收待验证的扫描件；
    C2、识别所述扫描件中的印章中心，将所述印章中心作为裁剪中心，以预设的裁剪形状按预设的裁剪规格对所述扫描件进行裁剪，得到待验证的印章图片；
    C3、检测所述印章图片中的文件文字，将检测出的所有文件文字去除；
    C4、从去文字处理后的印章图片中扣取中心点和去除文件文字处留下的空白区域，使扣取的中心点与原始章模图片的印章中心重合，将所述空白区域合成到所述原始章模图片上，形成印章验证图；
    C5、将所述印章验证图中的所述空白区域相对所述原始章模图片，以所述中心点为中心朝同一方向逐次旋转，每次旋转预设角度，直至旋转一周，在每次将空白区域相对所述原始章模图片旋转后，将去文字处理后的印章图片与所述印章验证图进行一次预设的相似度 算法比较，以得出去文字处理后的印章图片与所述印章验证图的相似度；
    C6、获取与去文字处理后的印章图片相似度最高的印章验证图，将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪。
  18. 如权利要求17所述的计算机可读存储介质，其特征在于，在所述步骤C3之前，所述处理器还用于执行所述物理印章识别系统，以实现以下步骤：
    对所述印章图片进行噪点检测，去除检测出的噪点。
  19. 如权利要求17所述的计算机可读存储介质，其特征在于，所述步骤C2替换为：
    识别所述扫描件中的印章中心和印章规格，根据预先确定的印章规格与裁剪规格的映射关系，确定所述扫描件对应的裁剪规格，将所述印章中心作为裁剪中心，以预设的裁剪形状按确定的裁剪规格对所述扫描件进行裁剪，得到待验证的印章图片。
  20. 如权利要求17所述的计算机可读存储介质，其特征在于，所述将该印章验证图采用预设的比较方式与去文字处理后的印章图片进行比较，根据比较结果确认所述印章图片上的印章的真伪的步骤包括：
    提取去文字处理后的印章图片与所述印章验证图的轮廓进行对比，得到第一对比结果值；
    分别提取去文字处理后的印章图片与所述印章验证图的印模上的文字及数字，将从两者的印模上提取的文字和数字分别进行单独对比，得到第二对比结果值；
    将所述去文字处理后的印章图片与所述印章验证图的分别通过将印模上五角星的五个角切割为折线后进行对比，得到第三对比结果值；
    将所述第一对比结果值、第二对比结果值和第三对比结果值按预设的权重加权求和得出判定结果值；
    若所述判定结果值大于第一阈值，则确定所述印章图片上的印章为真章；
    若所述判定结果值小于等于第二阈值，则确定所述印章图片上的印章为假章。
PCT/CN2018/089426 2018-03-14 2018-06-01 电子装置、物理印章识别方法和计算机可读存储介质 WO2019174133A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810208740.2A CN108491870B (zh) 2018-03-14 2018-03-14 电子装置、物理印章识别方法和计算机可读存储介质
CN201810208740.2 2018-03-14

Publications (1)

Publication Number Publication Date
WO2019174133A1 true WO2019174133A1 (zh) 2019-09-19

Family

ID=63339220

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/089426 WO2019174133A1 (zh) 2018-03-14 2018-06-01 电子装置、物理印章识别方法和计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN108491870B (zh)
WO (1) WO2019174133A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111161380A (zh) * 2019-12-30 2020-05-15 杭州天谷信息科技有限公司 电子印章处理方法及其处理系统

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109460757A (zh) * 2018-11-16 2019-03-12 上海中信信息发展股份有限公司 印章位置识别方法及装置
CN110728277B (zh) * 2019-09-27 2024-04-05 达观数据有限公司 一种印章智能检测与识别的方法及系统
CN111695106B (zh) * 2020-05-29 2022-06-28 北京字节跳动网络技术有限公司 验证方法、装置和电子设备
CN112115921A (zh) * 2020-09-30 2020-12-22 北京百度网讯科技有限公司 一种真伪鉴别方法、装置以及电子设备
CN112380957A (zh) * 2020-11-10 2021-02-19 平安普惠企业管理有限公司 他项权证信息识别方法、装置、计算机设备和存储介质
CN112784835B (zh) * 2021-01-21 2024-04-12 恒安嘉新（北京）科技股份公司 圆形印章的真实性识别方法、装置、电子设备及存储介质
CN113077355B (zh) * 2021-06-04 2021-08-10 国任财产保险股份有限公司 保险理赔方法、装置、电子设备及存储介质
CN115063804A (zh) * 2022-06-29 2022-09-16 支付宝(杭州)信息技术有限公司 印章识别和防伪检测方法和系统
CN116502207B (zh) * 2023-06-28 2024-03-22 易签链(深圳)科技有限公司 一种实物印章反向验证印模真实性加密方法

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101894260A (zh) * 2010-06-04 2010-11-24 北京化工大学 基于匹配特征点随机生成特征线的伪造印章识别方法
CN104626771A (zh) * 2015-03-05 2015-05-20 深圳市创业印章实业有限公司 一种印章防伪方法及系统

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100594511C (zh) * 2007-11-02 2010-03-17 北京大学 圆形印章的印鉴图像检索方法
CN101398894B (zh) * 2008-06-17 2011-12-07 浙江师范大学 机动车车牌自动识别方法及其实现装置
KR101015740B1 (ko) * 2009-02-18 2011-02-24 삼성전자주식회사 문자 인식 방법 및 장치

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101894260A (zh) * 2010-06-04 2010-11-24 北京化工大学 基于匹配特征点随机生成特征线的伪造印章识别方法
CN104626771A (zh) * 2015-03-05 2015-05-20 深圳市创业印章实业有限公司 一种印章防伪方法及系统

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111161380A (zh) * 2019-12-30 2020-05-15 杭州天谷信息科技有限公司 电子印章处理方法及其处理系统
CN111161380B (zh) * 2019-12-30 2023-11-10 杭州天谷信息科技有限公司 电子印章处理方法及其处理系统

Also Published As

Publication number Publication date
CN108491870B (zh) 2020-01-21
CN108491870A (zh) 2018-09-04

Similar Documents

Publication Publication Date Title
WO2019174133A1 (zh) 电子装置、物理印章识别方法和计算机可读存储介质
WO2017041365A1 (zh) 用于处理图像信息的方法和装置
WO2019169532A1 (zh) 车牌识别方法及云系统
JP5620244B2 (ja) 画像比較および文書認証のための画像位置合わせの方法及びプログラム
JP5559619B2 (ja) 画像比較解析を用いた印刷文書における変更の検出方法
WO2019061658A1 (zh) 眼镜定位方法、装置及存储介质
US11238271B2 (en) Detecting artificial facial images using facial landmarks
WO2011129113A1 (ja) 帳票処理装置及び帳票処理方法及び記録媒体
WO2018099132A1 (zh) 面单图像的获取方法及装置
CN111079571A (zh) 证卡信息识别及其边缘检测模型训练方法、装置
US20210365536A1 (en) Certificate verification
JP7076772B2 (ja) 認証システムおよび認証方法
US8130419B2 (en) Embedding authentication data to create a secure identity document using combined identity-linked images
CN112419207A (zh) 一种图像矫正方法及装置、系统
CN113221897A (zh) 图像矫正方法、图像文本识别方法、身份验证方法及装置
CN111414914A (zh) 图像识别方法、装置、计算机设备和存储介质
RU2672395C1 (ru) Способ обучения классификатора, предназначенного для определения категории документа
JP6403207B2 (ja) 情報端末装置
JP3494388B2 (ja) 指紋照合方法および指紋照合装置
CN111626244B (zh) 图像识别方法、装置、电子设备和介质
JP5483467B2 (ja) 帳票読取装置、角印検出方法、および、角印検出プログラム
CN113269186A (zh) 图像处理方法和系统
JP3878495B2 (ja) 電子透かし方法、電子透かし埋込み方法および電子透かし検出方法
JP7405528B2 (ja) 媒体判別装置、媒体判別システム及び媒体判別方法
JP2010061449A (ja) 原画像探索装置及び原画像探索プログラム

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: 18909716

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 07/12/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18909716

Country of ref document: EP

Kind code of ref document: A1