CN109993739B - Seal authenticity identification method and device - Google Patents
Seal authenticity identification method and device Download PDFInfo
- Publication number
- CN109993739B CN109993739B CN201910255966.2A CN201910255966A CN109993739B CN 109993739 B CN109993739 B CN 109993739B CN 201910255966 A CN201910255966 A CN 201910255966A CN 109993739 B CN109993739 B CN 109993739B
- Authority
- CN
- China
- Prior art keywords
- seal
- image
- binarized
- matching
- module
- 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
Links
Images
Classifications
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention relates to a method and a device for identifying authenticity of a seal, wherein the method comprises the following steps: acquiring a polygon seal image to be identified, a preset polygon seal model image and Zhang Moshu character area information; preprocessing to generate a binary seal image and seal position information, regenerating a scaled binary seal image and an RGB seal image generated by segmentation, extracting a horizontal straight line of the RGB seal image, obtaining a seal frame and a Zhang Mo frame, rotating the seal image, and obtaining a binary rotary seal image; and matching the binarized rotary seal image with a preset polygonal seal model image to generate a maximum matching parameter, wherein if the maximum matching parameter is larger than a preset matching threshold value, the seal is a true seal, otherwise, the seal is a false seal. The method for identifying the authenticity of the polygonal seal can accurately identify whether the seal is a true seal or not when the polygonal seal is identified, improves the accuracy of the true seal inspection, and accurately refuses the seal image of the false seal, thereby improving the practicability of seal identification.
Description
Technical Field
The invention relates to the technical field of digital image processing and identification, in particular to a method and a device for identifying authenticity of a seal.
Background
Along with the development of the technology level, the manufacturing level and the process of the seal in the modern society are greatly improved, the forging technology of the seal is also developed very fast when the manufacturing level of the seal is improved, and the forged seal can cause serious loss to the social development, so that the identification of the authenticity of the seal is imperative.
At present, the seals are classified into circular seals, elliptic seals, square seals and the like according to the shapes, the traditional manual folding auxiliary human eye seal authenticity identification method cannot adapt to the development of the modern society, and the manual seal identification method is time-consuming and labor-consuming and has low identification accuracy. Therefore, along with the continuous development of image processing and recognition technology and computer hardware, automatic seal authenticity identification is widely used, but the current automatic seal identification method only carries out simple matching on the size, shape and content of the seal on a seal identification machine, the accuracy is lower, true and false seals cannot be detected efficiently, and the mechanism for researching the automatic seal identification algorithm at home and abroad is not many, although a plurality of professionals are researching the seal identification method, the practicability is not high, the identification accuracy is lower when the polygonal square seal is identified as true seals, the false seals have the phenomenon of missing detection, and the practicability is not strong.
Disclosure of Invention
In view of the above, the invention aims to overcome the defects of the prior art, and provides a method and a device for identifying the authenticity of a seal, which solve the problems of low identification accuracy, low passing rate for identifying the authenticity of the seal meeting the requirements and low practicability in the prior art when the authenticity of the seal is identified.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a method for authenticating a seal, comprising:
acquiring a polygon seal image to be identified and a preset polygon seal model image;
acquiring chapter module word area information of the preset polygon chapter module image;
performing binarization processing on the polygonal seal image to be identified to generate a binarized seal image;
roughly positioning seal position information of the polygon seal image to be identified;
dividing the polygonal seal image to be identified according to the seal position information to generate an RGB color mode seal image;
scaling the binarized seal image to generate a scaled binarized seal image;
extracting the maximum communication area of the scaled binarized seal image to obtain a seal frame of the polygonal seal image to be identified; obtaining Zhang Mo frames of the preset polygonal chapter mode image according to the Zhang Moshu character region information;
synthesizing the seal frame and the binarized seal image to generate a synthesized seal image, and obtaining the mass center of the synthesized seal image;
extracting a horizontal straight line in the RGB color mode seal image;
performing angle matching on the horizontal straight line and the Zhang Mo frame in the horizontal direction to obtain an inclined angle in the horizontal direction; according to the inclination angle, the RGB color mode seal image is rotated by taking the mass center as a center point, and an angle registration rotary seal image is generated;
performing binarization processing on the rotation seal image registered by the angle to generate a binarization rotation seal image;
performing image information matching on the binarized rotary seal image and the preset polygonal seal model image to obtain a maximum matching parameter;
judging whether the maximum matching parameter is larger than a preset matching threshold value, if the maximum matching parameter is larger than the preset matching threshold value, identifying the polygonal stamp to be identified as a true stamp, otherwise, identifying the polygonal stamp to be identified as a false stamp.
Optionally, the acquiring the chapter module word area information of the preset polygon chapter module image includes:
performing binarization processing on the preset polygonal chapter model image to obtain a binarization Zhang Mo image;
performing forward and backward storage processing on the binarized seal model image to generate a forward stored binarized seal model image and a backward stored binarized Zhang Mo image;
and carrying out digital region segmentation on the forward-stored binarized chapter mode image and the reverse-stored binarized chapter mode image to generate the Zhang Moshu character region information.
Optionally, the positioning the stamp position information of the polygon stamp image to be identified includes: and extracting a seal maximum communicating region of the binarized seal image, wherein the seal maximum communicating region is the seal position information.
Optionally, the binarizing processing of the rotation seal image with the angle registration includes: and performing binarization processing on the angle registered rotary seal image by adopting an HSV color model algorithm.
Optionally, the method further comprises: accurately positioning the binarized rotary seal image to obtain an accurate center position coordinate of the binarized rotary seal image;
cutting each side of the binarized rotary seal image to obtain a seal text image of the seal, and carrying out image alignment on the seal text image and the preset polygonal seal model image.
Optionally, the maximum matching parameters include: maximum matching rate of seal width, maximum matching rate of seal pixels, maximum matching rate of seal digital area and maximum matching rate of seal anti-counterfeiting line;
the step of performing image information matching on the binarized rotary seal image and the preset polygon seal model image to obtain maximum matching parameters comprises the following steps:
performing seal width matching on the binarized rotary seal image and the preset polygonal seal model image to obtain the maximum seal width matching rate;
performing seal pixel matching on the binarized rotary seal image and the preset polygonal seal model image to obtain the maximum seal pixel matching rate;
performing seal digital coding region matching on the binarized rotary seal image and the preset polygonal seal model image to obtain the maximum matching rate of the seal digital region;
and performing seal anti-counterfeiting line region matching on the binarized rotary seal image and the preset polygonal seal mold image to obtain the maximum matching rate of the seal anti-counterfeiting line.
A seal authenticity identification device comprising: the first acquisition module is used for acquiring the polygon seal image to be identified and the preset polygon seal model image;
the second acquisition module is used for extracting chapter module word area information of the preset polygonal chapter module image;
the first binarization processing module is used for performing binarization processing on the polygonal seal image to be identified to generate a binarized seal image;
the rough positioning module is used for positioning the stamp position information of the polygonal stamp image to be identified;
the segmentation processing module is used for carrying out segmentation processing on the polygonal seal image to be identified according to the seal position information to generate an RGB color mode seal image;
the scaling module is used for scaling the binarized seal image to generate a scaled binarized seal image;
the first extraction module is used for extracting the maximum communication area of the scaled binarized seal image to obtain a seal frame of the polygonal seal image to be identified; obtaining Zhang Mo frames of the preset polygonal chapter mode image according to the Zhang Moshu character region information;
the synthesizing module is used for synthesizing the seal frame and the binarized seal image, generating a synthesized seal image and obtaining the mass center of the synthesized seal image;
the second extraction module is used for extracting the horizontal straight line of the RGB color mode seal image;
the angle registration module is used for performing angle matching on the horizontal straight line and the Zhang Mo frame in the horizontal direction to obtain an inclined angle in the horizontal direction, rotating the RGB color mode seal image by taking the mass center as a center point according to the inclined angle, and generating an angle registered rotary seal image;
the second binarization processing module is used for performing binarization processing on the rotation seal image registered by the angle to generate a binarization rotation seal image;
the image information matching module is used for matching the image information of the binarized rotary seal image and the preset polygonal seal model image to obtain the maximum matching parameter;
and the judging module is used for judging whether the maximum matching parameter is larger than a preset matching threshold value, if the maximum matching parameter is larger than the preset matching threshold value, the polygon seal to be identified is identified as a true seal, and if the maximum matching parameter is not larger than the preset matching threshold value, the polygon seal to be identified is identified as a false seal.
Optionally, the second obtaining module includes: a binarization processing sub-module, a positive and negative memory processing sub-module and a digital region segmentation sub-module;
the binarization processing submodule is used for carrying out binarization processing on the preset polygonal chapter model image to obtain a binarization Zhang Mo image;
the positive and negative memory processing submodule is used for carrying out positive and negative memory processing on the binarized seal model image to generate a positive memory binarized seal model image and a negative memory binarized Zhang Mo image;
the digital region segmentation sub-module is used for carrying out digital region segmentation on the positive-memory binarization chapter mode image and the negative-memory binarization chapter mode image to generate Zhang Moshu character region information.
Optionally, the method further comprises: the accurate positioning module and the cutting module are used for positioning the cutting module;
the accurate positioning module is used for accurately positioning the binarized rotary seal image to obtain the accurate center position coordinate of the binarized rotary seal image;
the cutting module is used for cutting each side of the binarized rotary seal image to obtain a seal text image of the seal, and carrying out image alignment on the seal text image of the seal and the preset polygonal seal model image.
Optionally, the maximum matching parameters include: maximum matching rate of seal width, maximum matching rate of seal pixels, maximum matching rate of seal digital area and maximum matching rate of seal anti-counterfeiting line;
the image information matching module comprises:
the seal width matching sub-module is used for performing seal width matching on the binarized rotary seal image and the preset polygonal seal model image to obtain the maximum seal width matching rate;
the seal pixel matching submodule is used for carrying out seal pixel matching on the binarized rotary seal image and the preset polygonal seal model image to obtain the maximum seal pixel matching rate;
the seal digital coding region matching submodule is used for carrying out seal digital coding region matching on the binarized rotary seal image and the preset polygonal seal model image to obtain the maximum matching rate of the seal digital region;
and the seal anti-counterfeiting line region matching submodule is used for carrying out seal anti-counterfeiting line region matching on the binarized rotary seal image and the preset polygonal seal die image to obtain the maximum matching rate of the seal anti-counterfeiting line.
The technical scheme that this application provided can include following beneficial effect:
the invention discloses a seal authenticity identification method, which comprises the following steps: acquiring a polygon seal image to be identified, a preset polygon seal model image and Zhang Moshu character area information; preprocessing a seal image, generating a binarized seal image and seal position information, regenerating a scaled binarized seal image and an RGB seal image generated by segmentation, extracting a horizontal straight line of the RGB seal image, extracting a maximum communication area of the scaled binarized seal image to obtain a seal frame and a Zhang Mo frame, rotating the seal image by taking a mass center of the seal image obtained by synthesizing the seal frame and the binarized seal image as a center point, and obtaining a binarized rotating seal image by rotating the seal image registered by the binarization processing angle; and matching the binarized rotary seal image with a preset polygonal seal model image to generate a maximum matching parameter, comparing the maximum matching parameter with a preset matching threshold value, and if the maximum matching parameter is larger than the preset matching threshold value, determining that the rotary seal is a true seal, otherwise, determining that the rotary seal is a false seal. The method for identifying the authenticity of the polygonal seal can accurately identify whether the seal is a true seal or not when the polygonal seal is identified, improves the accuracy of the true seal inspection, and accurately refuses the seal image of the false seal, thereby improving the practicability of seal identification.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for discriminating authenticity of a stamp according to an embodiment of the present application;
fig. 2 is a block diagram of a seal authenticity identification device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, based on the examples herein, which are within the scope of the invention as defined by the claims, will be within the scope of the invention as defined by the claims.
Fig. 1 is a flowchart of a method for identifying authenticity of a seal according to an embodiment of the present application, as shown in fig. 1, the method for identifying authenticity of a seal according to the embodiment includes:
and step 101, acquiring a polygon seal image to be identified and a preset polygon seal model image.
In this embodiment, the scanner is used to obtain the polygon stamp image to be authenticated and the preset polygon stamp mode image, and the dot count Per Inch (DPI) of the scanner is consistent with the DPI of the preset polygon stamp mode image, so that the physical size of the polygon stamp image to be authenticated can be determined, and further, the position of the polygon stamp image to be authenticated can be determined, then the pixel count of the polygon stamp image to be authenticated is naturally determined, and the physical size of the polygon stamp image to be authenticated is determined. Therefore, the obtained polygon seal image to be identified and the preset polygon seal model image are stored in the equipment memory.
In this embodiment, the chapter modulus word area information of the preset polygon chapter modulus image is 13 digital area information. And when obtaining the chapter modulus word area information, the method comprises the following steps: firstly, binarizing a preset polygonal seal model image according to color information to obtain a binarized Zhang Mo image, and then forward and backward storing the binarized seal model image to generate a forward-stored binarized seal model image and a backward-stored binarized Zhang Mo image, wherein the forward and backward storing image is used for upside down storing the image. For example: when the positive and negative memory is 69, the instrument can cause inaccurate segmentation of the image, so that the problem of inaccurate segmentation of the image can be effectively solved by reversing the positive and negative memory. And finally, carrying out digital region segmentation on the forward-stored binarized chapter model image and the backward-stored binarized chapter model image to generate Zhang Moshu character region information, wherein a momentum water drop algorithm is adopted when the digital region segmentation is carried out. The Zhang Moshu word area information acquired through the step is stored in the equipment memory, so that the matching of the digital areas is facilitated.
in this embodiment, preprocessing a polygonal seal image to be identified to generate a binarized seal image and seal position information includes: performing binarization processing on the polygonal seal image to be identified to generate a binarized seal image; rough positioning processing is carried out on the polygonal seal image to be identified, and seal position information is generated. In the embodiment, when binarizing the polygonal seal image to be identified, an HSV color model algorithm is adopted to binarize the seal image. Because the polygon seal image to be identified only has blue and red images, the HSV color model algorithm is adopted to carry out binary segmentation, and the value ranges of the tone H, the saturation S and the brightness V are all determined according to specific identification conditions.
In this embodiment, the rough positioning of the stamp position information of the polygon stamp image to be identified includes: and extracting a seal maximum communicating region of the binarized seal image, wherein the seal maximum communicating region is the seal position information. The maximum communicating area of the seal is the seal frame area, so that the seal position information can be positioned.
And 104, scaling the binarized seal image to generate a scaled binarized seal image.
And 105, dividing the polygonal seal image to be identified according to seal position information to generate an RGB color mode seal image.
In this embodiment, the real frame width of the Zhang Mo frame of the stamp die image can be obtained through the Zhang Mo frame of the obtained preset polygonal stamp die image.
And 107, extracting a horizontal straight line in the RGB color mode seal image.
in this embodiment, when the authenticity of the polygon seal image to be identified is identified, the polygon seal image to be identified and the preset polygon seal mold image need to be aligned, that is, a center point needs to be determined, and pixel matching can be performed between the two, and the center point is the centroid of the synthesized seal image in this embodiment.
in this embodiment, the width of the Zhang Mo frame of the preset polygonal stamp die image is required to be taken, and since the frame of the polygonal stamp is polygonal, the inclination angle of the stamp image can be determined when the straight line on the frame of the polygonal stamp to be identified is extracted, and then the polygonal stamp image to be identified is rotated according to the inclination angle, and when the inclination angle is 0, the rotated stamp image with the registered angle is generated.
And 110, performing binarization processing on the angle registered rotary seal image to generate a binarized rotary seal image.
In this embodiment, when the angular registration rotation seal image is processed, the binarization processing is performed on the angular registration rotation seal image by adopting an HSV color model algorithm.
After the binarized rotary seal image is generated, the binarized rotary seal image is required to be accurately positioned, and the accurate center point position coordinate of the binarized rotary seal image is obtained. When the position coordinates of the central points are determined, 20 x 20 small areas are selected at the central part of the binarized rotary seal image, each point is taken as the center, and the pixel point with the largest matching point is selected from the coordinates of [ -5,5] to serve as the accurate position coordinates of the central points of the binarized rotary seal image. And then, cutting the binarized rotary seal image by utilizing the projection of the histogram, selecting a plurality of edges with the largest projection area, cutting the binarized rotary seal image according to the edges, generating a seal text image which only remains the seal, namely only remains the seal, and carrying out image alignment on the seal text image and the preset polygonal seal model image.
And step 111, performing image information matching on the binarized rotary seal image and a preset polygonal seal model image to obtain the maximum matching parameters.
In this embodiment, the maximum matching parameters include: maximum matching rate of seal width, maximum matching rate of seal pixels, maximum matching rate of seal digital area and maximum matching rate of seal anti-counterfeiting line. And judging whether the difference between the width of the binarized rotary seal image and the width of the preset seal model image exceeds 2 percent of the national standard width, if so, judging that the polygonal seal image to be identified is unqualified, and identifying the polygonal seal image as a fake seal.
And 112, judging whether the maximum matching parameter is larger than a preset matching threshold, if so, identifying the polygonal stamp to be identified as a true stamp, otherwise, identifying the polygonal stamp to be identified as a false stamp.
In this embodiment, after the maximum matching parameter is obtained, it is determined whether the maximum matching parameter is greater than a preset matching threshold, if the maximum matching parameter is greater than the preset matching threshold, the polygon stamp to be identified is identified as a true stamp, otherwise the polygon stamp to be identified is a false stamp. Specifically, when the maximum matching rate of the seal width in the maximum matching parameters is 0.2, the maximum matching rate of the seal pixels is more than 0.9, the maximum matching rate of the seal digital area is more than 0.85 and the maximum matching rate of the seal anti-counterfeiting line is more than 0.9, the identified polygon seal image to be identified is identified as a true seal through identification, and step 113 is carried out; otherwise, the step 11 is carried out without authentication, and the fake seal is identified.
By the method for identifying the authenticity of the seal, the method for identifying the authenticity of the seal can accurately identify whether the seal is a true seal or not when the polygonal seal is identified, improves the inspection accuracy of the true seal, can accurately reject the image of the false seal which does not meet the requirements, and improves the practicability of seal identification.
Fig. 2 is a block diagram of a device for identifying authenticity of a seal according to an embodiment of the present application, referring to fig. 2, the device for identifying authenticity of a seal includes: the device comprises a first acquisition module 201, a second acquisition module 202, a preprocessing module 203, a scaling module 204, a segmentation processing module 205, a first extraction module 206, a second extraction module 207, a synthesis module 208, an angle registration module 209, a binarization processing module 210, an image information matching module 211 and a judging module 212;
wherein the second acquisition module 202 includes: a first binarization sub-module 2021, a positive and negative memory processing sub-module 2012, and a digital dividing sub-module 2013;
the preprocessing module 203 includes: a second binarization sub-module 2031, a coarse positioning module 2032.
The first obtaining module 201 is connected to the first binarization processing sub-module 2021 in the second obtaining module 202, and is configured to obtain a polygon seal image to be identified and a preset polygon seal model image, and perform binarization processing on the preset polygon seal model image to obtain a binarized seal model image. The positive and negative memory processing sub-module 2022 is respectively connected with the first binarization processing sub-module 2021 and the digital region segmentation sub-module 2023, and is used for receiving the binarized Zhang Mo image, performing positive and negative memory processing on the binarized chapter model image, generating a positive memory binarized chapter model image and a negative memory binarized Zhang Mo image, and sending the positive memory binarized chapter model image and the negative memory binarized Zhang Mo image to the digital region segmentation sub-module; the digital region segmentation sub-module 2023 is connected to the first extraction module 206, and is configured to perform digital region segmentation on the forward-stored binarized chapter mode image and the backward-stored binarized chapter mode image, generate the Zhang Moshu word region information, and send the Zhang Moshu word region information to the first extraction module 206.
In this embodiment, the first obtaining module 201 is further connected to the second binarization processing sub-module 2031 in the preprocessing module 203, and is configured to send the obtained polygon seal image to be identified to the second binarization processing sub-module 2031. The second binarization submodule 2031 is connected with the scaling module 204, and is used for performing binarization processing on the polygonal seal image to be identified, generating a binarized seal image, and sending the binarized seal image to the scaling module 204. In this embodiment, the first obtaining module 201 is further connected to the rough positioning sub-module 2032, and sends the obtained polygon seal image to be identified to the rough positioning sub-module 2032; and the rough positioning sub-module 2032 is connected to the segmentation processing module 205, and is configured to position seal position information of the polygon seal image to be identified, generate seal position information, and send the seal position information to the segmentation processing module 205.
In this embodiment, the scaling module 204 is connected to the first extraction module 206, and is configured to scale the binary seal image, generate a scaled binary seal image, and send the scaled binary seal image to the first extraction module 206.
In this embodiment, the segmentation processing module 205 is connected to the second extraction module 207, and is configured to perform segmentation processing on the polygonal seal image to be identified according to the seal position information, generate an RGB color mode seal image, and send the RGB color mode seal image to the second extraction module 207.
In this embodiment, the first extraction module 206 is connected to the synthesis module 208, and is configured to receive the scaled binary seal image and extract a maximum connected region of the scaled binary seal image, so as to obtain a seal frame of the polygonal seal image to be identified; and Zhang Mo frames of the preset polygonal seal die image are obtained according to the Zhang Moshu character region information, and the seal frames are sent to the synthesis module 208.
In this embodiment, the second extraction module 207 is connected to the angle registration module 209, and is configured to receive the RGB color mode stamp image, extract a horizontal line of the RGB color mode stamp image, and send the horizontal line to the angle registration module 209.
In this embodiment, the synthesizing module 208 is connected to the angle registration sub-module 209, and is configured to synthesize the seal frame and the binary seal image, generate a synthesized seal image, obtain a centroid of the synthesized seal image, and send the centroid of the synthesized seal image to the angle registration sub-module 209.
In this embodiment, the angle registration module 209 is connected to the binarization processing module 210, and is configured to perform angle matching on a horizontal straight line and a Zhang Mo frame in a horizontal direction to obtain an inclination angle in the horizontal direction, rotate the RGB color mode seal image with a centroid as a center point according to the inclination angle, generate an angle registered rotary seal image, and send the angle registered rotary seal image to the binarization processing module 210.
In this embodiment, the binarization processing module 210 is connected to the image information matching module 211, and is configured to perform binarization processing on the angle registered rotary stamp image after receiving the angle registered rotary stamp image, generate a binarized rotary stamp image, and send the binarized rotary stamp image to the image information matching module 211.
In this embodiment, the image information matching module 211 is connected to the judging module 212, and is configured to receive the binarized rotary stamp image, match the binarized rotary stamp image with the preset polygon stamp model image to obtain a maximum matching parameter, and send the maximum matching parameter to the judging module 212. In this embodiment, the maximum matching parameters include: maximum matching rate of seal width, maximum matching rate of seal pixels, maximum matching rate of seal digital area and maximum matching rate of seal anti-counterfeiting line; and the image information matching module 211 includes:
(1) The seal width matching submodule is used for performing seal width matching on the binarized rotary seal image and a preset polygonal seal die image to obtain the maximum seal width matching rate;
(2) The seal pixel matching submodule is used for performing seal pixel matching on the binarized rotary seal image and the preset polygonal seal model image to obtain a maximum seal pixel matching rate;
(3) The seal digital coding region matching submodule is used for carrying out seal digital coding region matching on the binarized rotary seal image and a preset polygonal seal die image to obtain the maximum matching rate of the silver cup digital region;
(4) The seal anti-counterfeiting line region matching submodule is used for performing seal anti-counterfeiting line region matching on the binarized rotary seal image and the preset polygonal seal die image to obtain the maximum matching rate of the seal anti-counterfeiting line
In this embodiment, after the maximum matching parameter is obtained, it is determined whether the maximum matching parameter is greater than a preset matching threshold, if the maximum matching parameter is greater than the preset matching threshold, the polygon stamp to be identified is identified as a true stamp, otherwise the polygon stamp to be identified is a false stamp. Specifically, when the maximum matching rate of the seal width, the maximum matching rate of the seal pixels, the maximum matching rate of the seal digital area and the maximum matching rate of the seal anti-counterfeiting line in the maximum matching parameters are simultaneously 0.2, 0.85 and 0.9, the identified polygonal seal image to be identified is identified as a true seal through identification; otherwise, the stamp cannot be identified as a fake stamp through identification.
Through the device of the true and false identification of seal of this embodiment, can more convenient and accurate realization seal is distinguished all steps, has higher practicality, has improved the degree of accuracy of distinguishing true seal, and can reject the false seal image accuracy that does not meet the requirements and refuse the discernment, has improved the practicality of seal identification.
It is to be understood that the same or similar parts in the above embodiments may be referred to each other, and that in some detailed embodiments, the description may be referred to the same or similar parts in other embodiments.
It should be noted that in the description of the present invention, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Furthermore, in the description of the present invention, unless otherwise indicated, the meaning of "plurality" means at least six.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (10)
1. A method for authenticating a stamp, comprising:
acquiring a polygon seal image to be identified and a preset polygon seal model image;
acquiring chapter module word area information of the preset polygon chapter module image;
preprocessing the polygonal seal image to be identified to generate a binarized seal image and seal position information;
scaling the binarized seal image to generate a scaled binarized seal image;
dividing the polygonal seal image to be identified according to the seal position information to generate an RGB color mode seal image;
extracting the maximum communication area of the scaled binarized seal image to obtain a seal frame of the polygonal seal image to be identified; obtaining Zhang Mo frames of the preset polygonal chapter mode image according to the Zhang Moshu character region information;
extracting a horizontal straight line in the RGB color mode seal image;
synthesizing the seal frame and the binarized seal image to generate a synthesized seal image, and obtaining the mass center of the synthesized seal image;
performing angle matching on the horizontal straight line and the Zhang Mo frame in the horizontal direction to obtain an inclined angle in the horizontal direction; according to the inclination angle, the RGB color mode seal image is rotated by taking the mass center as a center point, and an angle registration rotary seal image is generated;
performing binarization processing on the rotation seal image registered by the angle to generate a binarization rotation seal image;
performing image information matching on the binarized rotary seal image and the preset polygonal seal model image to obtain a maximum matching parameter;
judging whether the maximum matching parameter is larger than a preset matching threshold value, if the maximum matching parameter is larger than the preset matching threshold value, identifying the polygonal stamp to be identified as a true stamp, otherwise, identifying the polygonal stamp to be identified as a false stamp.
2. The method for authenticating a seal according to claim 1, wherein the step of obtaining the seal modulus word area information of the preset polygonal seal modulus image includes:
performing binarization processing on the preset polygonal chapter model image to obtain a binarization Zhang Mo image;
performing forward and backward storage processing on the binarized seal model image to generate a forward stored binarized seal model image and a backward stored binarized Zhang Mo image;
and carrying out digital region segmentation on the forward-stored binarized chapter mode image and the reverse-stored binarized chapter mode image to generate the Zhang Moshu character region information.
3. The seal authenticity identification method according to claim 1, wherein roughly locating seal position information of the polygon seal image to be identified comprises: and extracting a seal maximum communicating region of the binarized seal image, wherein the seal maximum communicating region is the seal position information.
4. The method for authenticating a seal according to claim 1, wherein the preprocessing the polygon seal image to be authenticated to generate a binary seal image and seal position information includes:
performing binarization processing on the polygonal seal image to be identified to generate a binarized seal image;
and performing rough positioning processing on the polygonal seal image to be identified to generate seal position information.
5. The method for authenticating a stamp according to claim 1, further comprising: accurately positioning the binarized rotary seal image to obtain the accurate center point position coordinate of the binarized rotary seal image;
cutting each side of the binarized rotary seal image to obtain a seal text image of the seal, and carrying out image alignment on the seal text image and the preset polygonal seal model image.
6. The method for authenticating a stamp according to claim 1, wherein the maximum matching parameters include: maximum matching rate of seal width, maximum matching rate of seal pixels, maximum matching rate of seal digital area and maximum matching rate of seal anti-counterfeiting line;
the step of performing image information matching on the binarized rotary seal image and the preset polygon seal model image to obtain maximum matching parameters comprises the following steps:
performing seal width matching on the binarized rotary seal image and the preset polygonal seal model image to obtain the maximum seal width matching rate;
performing seal pixel matching on the binarized rotary seal image and the preset polygonal seal model image to obtain the maximum seal pixel matching rate;
performing seal digital coding region matching on the binarized rotary seal image and the preset polygonal seal model image to obtain the maximum matching rate of the seal digital region;
and performing seal anti-counterfeiting line region matching on the binarized rotary seal image and the preset polygonal seal mold image to obtain the maximum matching rate of the seal anti-counterfeiting line.
7. A seal authenticity identification device, comprising:
the first acquisition module is used for acquiring the polygon seal image to be identified and the preset polygon seal model image;
the second acquisition module is used for extracting chapter module word area information of the preset polygonal chapter module image;
the preprocessing module is used for preprocessing the polygonal seal image to be identified to generate a binarized seal image and seal position information;
the scaling module is used for scaling the binarized seal image to generate a scaled binarized seal image;
the segmentation processing module is used for carrying out segmentation processing on the polygonal seal image to be identified according to the seal position information to generate an RGB color mode seal image;
the first extraction module is used for extracting the maximum communication area of the scaled binarized seal image to obtain a seal frame of the polygonal seal image to be identified; obtaining Zhang Mo frames of the preset polygonal chapter mode image according to the Zhang Moshu character region information;
the second extraction module is used for extracting the horizontal straight line of the RGB color mode seal image;
the synthesizing module is used for synthesizing the seal frame and the binarized seal image, generating a synthesized seal image and obtaining the mass center of the synthesized seal image;
the angle registration module is used for performing angle matching on the horizontal straight line and the Zhang Mo frame in the horizontal direction to obtain an inclined angle in the horizontal direction, rotating the RGB color mode seal image by taking the mass center as a center point according to the inclined angle, and generating an angle registered rotary seal image;
the binarization processing module is used for performing binarization processing on the rotation seal image registered by the angle to generate a binarization rotation seal image;
the image information matching module is used for matching the image information of the binarized rotary seal image and the preset polygonal seal model image to obtain the maximum matching parameter;
and the judging module is used for judging whether the maximum matching parameter is larger than a preset matching threshold value, if the maximum matching parameter is larger than the preset matching threshold value, the polygon seal to be identified is identified as a true seal, and if the maximum matching parameter is not larger than the preset matching threshold value, the polygon seal to be identified is identified as a false seal.
8. The stamp authentication apparatus according to claim 7, wherein said second acquisition module includes: a first binarization processing sub-module, a positive and negative memory processing sub-module and a digital region segmentation sub-module;
the first binarization processing submodule is used for carrying out binarization processing on the preset polygon seal model image to obtain a binarization Zhang Mo image;
the positive and negative memory processing submodule is used for carrying out positive and negative memory processing on the binarized seal model image to generate a positive memory binarized seal model image and a negative memory binarized Zhang Mo image;
the digital region segmentation sub-module is used for carrying out digital region segmentation on the positive-memory binarization chapter mode image and the negative-memory binarization chapter mode image to generate Zhang Moshu character region information.
9. The stamp authentication apparatus according to claim 7, wherein the preprocessing module includes: the second binarization processing sub-module and the rough positioning sub-module;
the second binarization processing submodule is used for carrying out binarization processing on the polygonal seal image to be identified to generate a binarized seal image;
the rough positioning sub-module is used for positioning the stamp position information of the polygonal stamp image to be identified and generating the stamp position information.
10. The stamp authentication apparatus according to claim 7, wherein said maximum matching parameters include: maximum matching rate of seal width, maximum matching rate of seal pixels, maximum matching rate of seal digital area and maximum matching rate of seal anti-counterfeiting line;
the image information matching module comprises:
the seal width matching sub-module is used for performing seal width matching on the binarized rotary seal image and the preset polygonal seal model image to obtain the maximum seal width matching rate;
the seal pixel matching submodule is used for carrying out seal pixel matching on the binarized rotary seal image and the preset polygonal seal model image to obtain the maximum seal pixel matching rate;
the seal digital coding region matching submodule is used for carrying out seal digital coding region matching on the binarized rotary seal image and the preset polygonal seal model image to obtain the maximum matching rate of the seal digital region;
and the seal anti-counterfeiting line region matching submodule is used for carrying out seal anti-counterfeiting line region matching on the binarized rotary seal image and the preset polygonal seal die image to obtain the maximum matching rate of the seal anti-counterfeiting line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910255966.2A CN109993739B (en) | 2019-03-29 | 2019-03-29 | Seal authenticity identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910255966.2A CN109993739B (en) | 2019-03-29 | 2019-03-29 | Seal authenticity identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109993739A CN109993739A (en) | 2019-07-09 |
| CN109993739B true CN109993739B (en) | 2023-04-28 |
Family
ID=67131871
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910255966.2A Active CN109993739B (en) | 2019-03-29 | 2019-03-29 | Seal authenticity identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109993739B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110414525B (en) * | 2019-07-31 | 2022-02-25 | 新华三信息安全技术有限公司 | Character recognition method and device |
| CN112883974B (en) * | 2021-05-06 | 2021-07-09 | 江西省江咨金发数据科技发展有限公司 | Electronic letter identification system based on image verification |
| CN113486901B (en) * | 2021-06-23 | 2023-05-02 | 内江师范学院 | Novel high imitation round seal identification method |
| CN114419655A (en) * | 2022-03-31 | 2022-04-29 | 北京惠朗时代科技有限公司 | Seal verification method, seal verification device, seal verification medium and seal verification equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102136908A (en) * | 2010-01-22 | 2011-07-27 | 张胤微 | Method for stamping electronic seal by using stamp and stamping device realized by same |
| CN108509992A (en) * | 2017-12-27 | 2018-09-07 | 广西新章物电防伪技术开发有限公司 | A kind of seal impression Weigh sensor method for anti-counterfeit based on machine learning techniques |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1635533A (en) * | 2003-12-30 | 2005-07-06 | 刘瑞祯 | Digital stamp system |
| CN100568264C (en) * | 2007-01-18 | 2009-12-09 | 章毅 | Print identification control method |
| WO2010126269A2 (en) * | 2009-04-27 | 2010-11-04 | 대한민국(관리부서:행정안전부 국립과학수사연구소장) | Method and recording medium for seal forgery inspection |
-
2019
- 2019-03-29 CN CN201910255966.2A patent/CN109993739B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102136908A (en) * | 2010-01-22 | 2011-07-27 | 张胤微 | Method for stamping electronic seal by using stamp and stamping device realized by same |
| CN108509992A (en) * | 2017-12-27 | 2018-09-07 | 广西新章物电防伪技术开发有限公司 | A kind of seal impression Weigh sensor method for anti-counterfeit based on machine learning techniques |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109993739A (en) | 2019-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109993739B (en) | Seal authenticity identification method and device | |
| CN102163284B (en) | Chinese environment-oriented complex scene text positioning method | |
| CN104298982B (en) | A kind of character recognition method and device | |
| TWI281126B (en) | Image detection method based on region | |
| RU2601185C2 (en) | Method, system and computer data medium for face detection | |
| JP6139396B2 (en) | Method and program for compressing binary image representing document | |
| CN102930265B (en) | A kind of many I.D.s scan method and device | |
| US9785850B2 (en) | Real time object measurement | |
| CN105046252A (en) | Method for recognizing Renminbi (Chinese currency yuan) crown codes | |
| CN108133216B (en) | Nixie tube reading identification method capable of realizing decimal point reading based on machine vision | |
| CN105588845A (en) | Weld defect characteristic parameter extraction method | |
| CN110378351B (en) | Seal identification method and device | |
| CN102073872B (en) | Image-based method for identifying shape of parasite egg | |
| CN107490583A (en) | A kind of intermediate plate defect inspection method based on machine vision | |
| CN104361335B (en) | A kind of processing method that black surround is automatically removed based on scan image | |
| CN109767436B (en) | Method and device for identifying authenticity of seal | |
| CN111461131A (en) | Identification method, device, equipment and storage medium for ID card number information | |
| CN115082776A (en) | Electric energy meter automatic detection system and method based on image recognition | |
| CN111401364A (en) | License plate positioning algorithm based on combination of color features and template matching | |
| CN107742357A (en) | A kind of recognition methods of paper money number and device | |
| CN117636359A (en) | Method, device, processor and computer readable storage medium for implementing character recognition and extraction processing for seal face | |
| US20170352170A1 (en) | Nearsighted camera object detection | |
| CN110378337B (en) | Visual input method and system for drawing identification information of metal cutting tool | |
| CN104408430B (en) | License plate positioning method and device | |
| WO2019237560A1 (en) | Border and page number scanning system |
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: 20230413 Address after: 518000 419, Building 4, Software Industry Base, No. 19, 17 and 18, Haitian 1st Road, Binhai Community, Yuehai Street, Nanshan District, Shenzhen, Guangdong Province Applicant after: Shenzhen Anyin Technology Co.,Ltd. Address before: 518000 whole building of Qilin road production center, Nanshan District, Shenzhen City, Guangdong Province Applicant before: SHENZHEN CHUANGYE SIGNET INDUSTRIAL CO.,LTD. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |