CN115527067A - Method, system and storage medium for verifying contents of image-text printed matter - Google Patents
Method, system and storage medium for verifying contents of image-text printed matter Download PDFInfo
- Publication number
- CN115527067A CN115527067A CN202211221321.5A CN202211221321A CN115527067A CN 115527067 A CN115527067 A CN 115527067A CN 202211221321 A CN202211221321 A CN 202211221321A CN 115527067 A CN115527067 A CN 115527067A
- Authority
- CN
- China
- Prior art keywords
- finished product
- character
- subregion
- printing finished
- target printing
- 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.)
- Withdrawn
Links
Images
Classifications
-
- 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
- G06V10/761—Proximity, similarity or dissimilarity 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
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
- G06V30/19153—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation using rules for classification or partitioning the feature space
-
- 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
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
- G06V30/19173—Classification techniques
Abstract
The invention relates to the technical field of content verification of image-text printed matters, and particularly discloses a method, a system and a storage medium for verifying the content of the image-text printed matters. The method analyzes the basic information matching index, the radical matching index, the stroke matching index and the position matching index corresponding to each character subregion, and further comprehensively analyzes the character content matching index corresponding to each character subregion, so that on one hand, the method breaks the limitation and one-sidedness of character matching degree analysis of the image-text printed matter in the prior art, and effectively avoids errors existing in the character matching degree analysis result of the image-text printed matter; on the other hand, the method not only provides powerful data support for the content verification and analysis of the subsequent image-text printed matters to a great extent, but also greatly improves the rationality and reliability of the content verification and analysis of the image-text printed matters.
Description
Technical Field
The invention relates to the technical field of content verification of image-text printed matters, in particular to a method and a system for verifying content of image-text printed matters and a storage medium.
Background
In a colloquial language, books are a step of human progress, with the continuous improvement of the living standard of people, the content quality of the image-text printed matter is one of the aspects of wide attention of the current society, and the integrity, conformity and the like of the content need to be accurately detected and screened, so that the importance of the content verification of the image-text printed matter is highlighted.
At present, the detection of the image-text printed matter still remains the detection of shallow display of the apparent quality such as color, definition and the like of the image-text printed matter, the content of the image-text printed matter is not checked, detected and analyzed, the accuracy of the content quality of the image-text printed matter cannot be guaranteed, and the method is embodied in the following aspects: 1. the image-text printed matter is usually a printed product with mixed image-text, when the image of the image-text printed matter is checked and analyzed, the color distribution, the image size, the printing definition and the like of the image are mainly analyzed, the image is not subjected to gray level processing, the matching degree of the image content cannot be identified, the accuracy of checking the image content of the image-text printed matter is reduced, and the conformity of the image content in the image-text printed matter cannot be ensured.
2. When the characters in the image-text printed matter are checked and analyzed at present, the sizes, the number and the outlines of the characters are mainly checked and analyzed, and the radicals and the pen surface of the characters are not checked and analyzed, so that the image-text printed matter and the standard image-text printed matter are compared and analyzed in a one-sided manner, certain errors exist in the analysis result of the matching degree of the characters in the image-text printed matter easily, the reasonability and the reliability of the content checking and analyzing of the image-text printed matter are reduced, and the condition that the content checking and analyzing of the image-text printed matter is lack of powerful data support is caused to a great extent.
Disclosure of Invention
In order to overcome the disadvantages in the background art, embodiments of the present invention provide a method, a system, and a storage medium for verifying contents of an image-text printed matter, which can effectively solve the problems related to the background art.
The purpose of the invention can be realized by the following technical scheme:
the invention provides a method for verifying the content of an image-text printed matter, which comprises the following steps: a1, dividing a target printing finished product: dividing the target printing finished product according to the picture area and the character area, dividing the picture area corresponding to the target printing finished product into all picture sub-areas according to the number of pictures, and dividing the character area corresponding to the target printing finished product according to a preset dividing mode to obtain all character sub-areas.
A2, processing a target printing finished product picture: and correspondingly processing each image subregion in the target printing finished product to obtain the image parameters corresponding to each image subregion in the target printing finished product.
A3, checking and analyzing a target printing finished product picture: and comparing and analyzing each picture subregion in the target printing finished product with the set standard printing finished product to obtain a picture content matching index corresponding to each picture subregion in the target printing finished product.
A4, processing the target printing finished product characters: and carrying out corresponding processing on each character subarea in the target printing finished product to obtain character parameters corresponding to each character subarea in the target printing finished product.
A5, checking and analyzing the characters of the target printing finished product: and comparing and analyzing each character subregion in the target printing finished product and the set standard printing finished product to obtain a character content matching index corresponding to each character subregion in the target printing finished product.
A6, checking and analyzing the content of the target printing finished product: and comprehensively analyzing the picture content matching index corresponding to each picture subregion and the character content matching index corresponding to each character subregion in the target printed finished product to obtain a content matching coefficient corresponding to the target printed finished product, and correspondingly displaying the content matching coefficient through a target printed finished product content verification display module.
As a further improvement of the present invention, in the step A2, each image subregion in the target printed product is correspondingly processed, and the specific processing procedure is as follows: carrying out graying treatment on each image subregion in the target printing finished product, classifying the same gray value in each image subregion to obtain each gray region corresponding to each image subregion, acquiring the distribution quantity corresponding to each gray region in each image subregion, and acquiring the area of each distribution block corresponding to each gray region in each image subregion.
The method comprises the steps of obtaining the position of a central point corresponding to each picture subregion, simultaneously constructing a coordinate system corresponding to each picture subregion based on the position of the central point corresponding to each picture subregion, and simultaneously obtaining the position coordinates of the central point of each distribution block corresponding to each gray level region in each picture subregion.
And the picture parameters corresponding to the image sub-regions in the target printing finished product are formed by the number of the distribution blocks corresponding to the gray scale regions in the image sub-regions, the areas of the distribution blocks and the position coordinates of the central point.
As a further improvement of the present invention, in the step A3, each image subregion in the target printed finished product is compared and analyzed with the set standard printed finished product, and the specific analysis process is as follows: dividing the set standard printing finished product according to the dividing mode of each image subregion corresponding to the target printing finished product to obtain each standard image subregion corresponding to the standard printing finished product, performing graying processing on each standard image subregion corresponding to the standard printing finished product, and classifying the same gray value in each standard image subregion to obtain each gray region corresponding to each standard image subregion.
And acquiring standard picture parameters corresponding to the standard picture subregions in the standard printing finished product according to the acquisition method that the picture parameters corresponding to the picture subregions in the target printing finished product are the same.
Extracting the number of distribution blocks corresponding to each gray scale region in each image sub-region, the area of each distribution block and the position coordinates of the central point from the image parameters corresponding to each image sub-region in the target printing finished product, and respectively recording the number, the area and the position coordinates of the central point as
And
i denotes the number of each picture sub-region, i =1,2, a.
Extracting the number of distribution blocks corresponding to each gray scale region in each standard picture subregion, the area of each distribution block and the position coordinates of a central point from standard picture parameters corresponding to each standard picture subregion in a standard printing finished product, and respectively recording the number, the area and the position coordinates as R i ′ j 、S i ′ j f and (x) i ′ j f,y i ′ j f)。
According to the formula
Calculating the picture distribution coincidence index of each picture subregion corresponding to each gray level region in the target printing finished product
Δ R, Δ S are respectively expressed as a set allowable individual processing quantity difference, an allowable distribution block area difference, a 1 、a 2 The values are expressed as influence factors corresponding to the set number and area, respectively.
According to the formula
Calculating the picture position offset index of each picture subregion corresponding to each gray level region in the target printing finished product
e is expressed as a natural constant, a 3 、a 4 And respectively representing the influence factors corresponding to the set x-axis coordinate point and the set y-axis coordinate point.
According to the formula
Calculating the picture content matching index corresponding to each picture subregion in the target printing finished product,
expressed as a picture content matching index corresponding to the ith picture subregion in the target printed finished product, a 5 、a 6 Respectively expressed as weight factors corresponding to the set picture distribution conformity index and the picture position deviation index.
As a further improvement of the present invention, in the step A4, each character subarea in the target printed product is correspondingly processed, and a specific processing manner is as follows: and acquiring the number of characters corresponding to each character subregion in the target printing finished product, the word size of each character and the number of punctuation marks by using the intelligent camera.
Extracting the radicals corresponding to the characters in the character subareas from the characters corresponding to the character subareas in the target printing finished product, acquiring the area of the radicals corresponding to the characters in the character subareas, and acquiring the area ratio of the radicals corresponding to the characters in the character subareas to the characters, and recording the area ratio as the occupation ratio.
And extracting the total stroke number, the length and the area of each stroke corresponding to each character in each character subregion from each character corresponding to each character subregion in the target printing finished product.
The method comprises the steps of obtaining the central point of each character subregion corresponding to a target printed finished product, constructing a character coordinate system corresponding to each character subregion based on the central point of each character subregion corresponding to the target printed finished product, and obtaining the position coordinate of the central point corresponding to each character in each character subregion.
The character parameters corresponding to each character subregion in the target printing finished product are formed by the number of characters in each character subregion, the word size of each character, the number of punctuation marks, the area of each character corresponding to a radical, the proportion of the radical, the total stroke number, the length of each stroke, the area of each stroke and the position coordinates of a central point.
As a further improvement of the present invention, in the step A5, each character subregion in the target printed finished product is compared and analyzed with the set standard printed finished product, and the specific analysis process is as follows: a501: dividing the set standard printing finished product according to the dividing mode of each character subregion corresponding to the target printing finished product to obtain each standard character subregion corresponding to the standard printing finished product, and acquiring the standard character parameters corresponding to each standard character subregion in the standard printing finished product according to the same acquiring method of the character parameters corresponding to each character subregion in the target printing finished product.
A502: extracting the number of characters in each character subregion, the word size of each character, the number of punctuation marks, the area of a radical corresponding to each character, the proportion of the radical, the total stroke number, the length of each stroke, the area of each stroke and the position coordinate of a central point from the character parameters corresponding to each character subregion in a target printing finished product, and respectively recording the position coordinates as N r 、
M r 、
And
r denotes the number of each text subregion, r =1,2,.. The t, p denotes the number of each text, p =1,2,.. The k, q denotes the number of each stroke, and q =1,2,.. The.
A503: extracting the number of characters in each standard character subarea, the word size of each character, the number of punctuation marks, the area of the corresponding radical of each character, the proportion of the radical, the total stroke number, the length of each stroke, the area of each stroke and the position coordinate of a central point from the standard character parameters corresponding to each standard character subarea in the standard printing finished product, and respectively recording the number of characters, the number of character numbers, the number of punctuation marks, the area of each stroke and the position coordinate of the central point as N r ′、Z r ′ p 、M r ′、J r ′ p 、C r ′ p 、B r ′ p 、L r ′ p q、U r ′ p q and (X) r ′ p ,Y r ′ p )。
A504: obtaining basic information matching indexes corresponding to all character subregions in the target printing finished product through calculation, and recording the basic information matching indexes as
A505: calculating to obtain the radical matching index corresponding to each character subregion in the target printing finished product, and recording the index as
A506: calculating to obtain stroke matching index corresponding to each character subregion in the target printing finished product, and recording as
A507: calculating to obtain the position matching index corresponding to each character subregion in the target printing finished product, and recording the position matching index as
A508: according to the formula
Calculating the character content matching index eta corresponding to each character subregion in the target printing finished product r ，ε 1 、ε 2 、ε 3 、ε 4 And the weight factors are respectively expressed as the weight factors corresponding to the set basic information matching index, the radical matching index, the stroke matching index and the position matching index.
As a further improvement of the present invention, in the step a505, the specific calculation formula of the radical matching index corresponding to each character subregion in the target printing finished product is as follows:
Δ J and Δ C are expressed as a set allowable radical area difference and an allowable radical proportion difference, respectively, b 1 、b 2 Respectively expressed as the influence factors corresponding to the area and the proportion of the radicals.
As a further improvement of the present invention, the stroke matching index corresponding to each character subregion in the target printing finished product in step a506 has a specific calculation formula as follows:
Δ B, Δ L, Δ U are respectively expressed as setting allowable total stroke number difference, allowable stroke length difference, allowable stroke picture product difference, B 3 、b 4 、b 5 Respectively expressed as the influence factors corresponding to the set total stroke number, stroke length and stroke area.
As a further improvement of the present invention, the content matching coefficient corresponding to the target printing finished product in step A6 has a specific calculation formula as follows:
xi is expressed as a content matching coefficient, delta, corresponding to the target printed finished product 1 、δ 2 And the coefficient factors are respectively expressed as the coefficient factors corresponding to the set picture content matching index and the set character content matching index.
A second aspect of the present invention provides a system for verifying contents of a printed matter, including: and the target printing finished product dividing module is used for dividing the target printing finished product into each picture subregion and each character subregion according to a preset dividing mode.
And the target printing finished product image processing module is used for correspondingly processing each image subregion in the target printing finished product to obtain image parameters corresponding to each image subregion in the target printing finished product.
And the target printing finished product image checking and analyzing module is used for comparing and analyzing each image subregion in the target printing finished product with the set standard printing finished product to obtain an image content matching index corresponding to each image subregion in the target printing finished product.
And the target printing finished product character processing module is used for carrying out corresponding processing on each character subregion in the target printing finished product to obtain the character parameters corresponding to each character subregion in the target printing finished product.
And the target printing finished product character checking and analyzing module is used for comparing and analyzing each character subregion in the target printing finished product and the set standard printing finished product to obtain a character content matching index corresponding to each character subregion in the target printing finished product.
And the target printing finished product content checking and analyzing module is used for comprehensively analyzing the picture content matching index corresponding to each picture subregion and the character content matching index corresponding to each character subregion in the target printing finished product to obtain a content matching coefficient corresponding to the target printing finished product.
And the target printing finished product content verification display module is used for correspondingly displaying the content matching coefficient corresponding to the target printing finished product.
The third aspect of the present invention provides a storage medium for content verification of an image-text printed matter, where the storage medium for content verification of an image-text printed matter is burned with a computer program, and the computer program implements the above method for content verification of an image-text printed matter when running in a memory of a server.
Compared with the prior art, the embodiment of the invention has at least the following advantages or beneficial effects: 1. according to the invention, the image-text printed matter is divided according to the preset dividing mode to obtain each image sub-area and each character sub-area, and the image sub-areas are subjected to graying treatment, so that the defect of graying treatment on the image in the prior art is overcome, and meanwhile, the image distribution coincidence index and the image position deviation index corresponding to each gray area in each image sub-area are analyzed, so that the image content matching index corresponding to each image sub-area is obtained through comprehensive analysis, the reliability of image content matching identification is improved to a great extent, the accuracy of content verification of the image-text printed matter is improved, and meanwhile, the coincidence degree of the image content in the image-text printed matter is met to a great extent.
2. The method analyzes the basic information matching index, the radical matching index, the stroke matching index and the position matching index corresponding to each character subregion, and further comprehensively analyzes the character content matching index corresponding to each character subregion, so that on one hand, the limitation and the one-sidedness of character matching degree analysis of the image-text printed matter in the prior art are broken, and the error of the character matching degree analysis result in the image-text printed matter is effectively avoided; on the other hand, the method not only provides powerful data support for the content verification and analysis of the subsequent image-text printed matters to a great extent, but also greatly improves the rationality and reliability of the content verification and analysis of the image-text printed matters.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
FIG. 1 is a schematic flow chart of the steps of the present invention.
FIG. 2 is a schematic diagram of the system module connection according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a first aspect of the present invention provides a method for verifying contents of an image-text printed matter, including the following steps: a1, dividing a target printing finished product: dividing the target printing finished product according to the picture area and the character area, dividing the picture area corresponding to the target printing finished product into all picture sub-areas according to the number of pictures, and dividing the character area corresponding to the target printing finished product according to a preset dividing mode to obtain all character sub-areas.
It should be noted that the text area corresponding to the target printed product is divided according to a preset dividing mode, and the specific dividing mode is as follows: and uniformly dividing the paper according to the size of the paper corresponding to the target printing finished product.
A2, processing a target printing finished product picture: and correspondingly processing each image subregion in the target printing finished product to obtain the image parameters corresponding to each image subregion in the target printing finished product.
As a further improvement of the present invention, in the step A2, each image subregion in the target printed product is correspondingly processed, and the specific processing procedure is as follows: carrying out graying treatment on each image subregion in the target printing finished product, classifying the same gray value in each image subregion to obtain each gray region corresponding to each image subregion, acquiring the distribution quantity corresponding to each gray region in each image subregion, and acquiring the area of each distribution block corresponding to each gray region in each image subregion.
Specifically, each gray scale region is: the same gray value forms a gray area, and different gray values form different gray areas, so that each gray area corresponding to each picture sub-area is obtained.
It should be noted that the distribution quantity corresponding to each gray scale region in each picture sub-region specifically includes: each gray scale region in each picture sub-region is not necessarily a continuous region, and there may be a dispersed region, which is taken as each distribution block corresponding to each gray scale region.
The method comprises the steps of obtaining the position of a central point corresponding to each picture subregion, simultaneously constructing a coordinate system corresponding to each picture subregion based on the position of the central point corresponding to each picture subregion, and simultaneously obtaining the position coordinates of the central point of each distribution block corresponding to each gray level region in each picture subregion.
And the number of the distribution blocks corresponding to each gray level area in each picture subarea, the area of each distribution block and the position coordinates of the central point form picture parameters corresponding to each picture subarea in the target printing finished product.
A3, checking and analyzing the target printing finished product picture: and comparing and analyzing each picture subregion in the target printing finished product with the set standard printing finished product to obtain a picture content matching index corresponding to each picture subregion in the target printing finished product.
As a further improvement of the present invention, in the step A3, each image subregion in the target printed finished product is compared and analyzed with the set standard printed finished product, and a specific analysis process is as follows: dividing the set standard printing finished product according to the dividing mode of each image subregion corresponding to the target printing finished product to obtain each standard image subregion corresponding to the standard printing finished product, performing graying processing on each standard image subregion corresponding to the standard printing finished product, and classifying the same gray value in each standard image subregion to obtain each gray region corresponding to each standard image subregion.
And acquiring standard picture parameters corresponding to the standard picture subregions in the standard printing finished product according to the acquisition method that the picture parameters corresponding to the picture subregions in the target printing finished product are the same.
Extracting each image from the image parameters corresponding to each image subregion in the target printing finished productThe number of distribution blocks corresponding to each gray scale region in the picture sub-region, the area of each distribution block and the position coordinates of the central point are respectively recorded as
And
i denotes the number of each picture sub-region, i =1,2, a.
Extracting the number of distribution blocks corresponding to each gray scale region in each standard picture subregion, the area of each distribution block and the position coordinates of a central point from standard picture parameters corresponding to each standard picture subregion in a standard printing finished product, and respectively recording the number, the area and the position coordinates as R i ′ j 、S i ′ j f and (x) i ′ j f,y i ′ j f)。
According to the formula
Calculating the picture distribution coincidence index of each picture subregion corresponding to each gray level region in the target printing finished product
Δ R, Δ S are expressed as a set allowable individual process quantity difference, an allowable distribution block area difference, a 1 、a 2 The values are expressed as influence factors corresponding to the set number and area, respectively.
According to the formula
Calculating the picture position offset index of each picture subregion corresponding to each gray level region in the target printing finished product
e is expressed as a natural constant, a 3 、a 4 Respectively expressed as the influence of the corresponding set x-axis coordinate point and y-axis coordinate pointA factor.
According to the formula
Calculating the picture content matching index corresponding to each picture subregion in the target printing finished product,
expressed as a picture content matching index corresponding to the ith picture subregion in the target printing finished product, a 5 、a 6 Respectively expressed as weight factors corresponding to the set picture distribution conformity index and the picture position deviation index.
In a specific embodiment, the image-text printed matter is divided according to a preset dividing mode to obtain each image sub-area and each text sub-area, and the image sub-areas are subjected to graying processing, so that the defect of graying processing on the image in the prior art is overcome, and meanwhile, the image distribution coincidence index and the image position offset index corresponding to each gray area in each image sub-area are analyzed, so that the image content matching index corresponding to each image sub-area is comprehensively analyzed, the reliability of image content matching identification is improved to a great extent, the accuracy of content verification of the image-text printed matter is improved, and the coincidence degree of the image content in the image-text printed matter is also met to a great extent.
A4, processing the target printing finished product characters: and carrying out corresponding processing on each character subregion in the target printing finished product to obtain character parameters corresponding to each character subregion in the target printing finished product.
As a further improvement of the present invention, in the step A4, each character subregion in the target printed product is correspondingly processed, and the specific processing manner is as follows: and acquiring the number of characters corresponding to each character subregion in the target printing finished product, the word size of each character and the number of punctuation marks by using the intelligent camera.
Extracting the radicals corresponding to the characters in the character sub-regions from the characters corresponding to the character sub-regions in the target printing finished product, acquiring the area of the radicals corresponding to the characters in the character sub-regions, and acquiring the area ratio of the radicals corresponding to the characters in the character sub-regions to the characters, and recording the area ratio as the occupation ratio.
And extracting the total stroke number, the length and the area of each stroke corresponding to each character in each character subregion from each character corresponding to each character subregion in the target printing finished product.
The method comprises the steps of obtaining the central point of each character subregion corresponding to a target printed finished product, constructing a character coordinate system corresponding to each character subregion based on the central point of each character subregion corresponding to the target printed finished product, and obtaining the position coordinate of the central point corresponding to each character in each character subregion.
The character parameters corresponding to each character subregion in the target printing finished product are formed by the number of characters in each character subregion, the word size of each character, the number of punctuation marks, the area of each character corresponding to a radical, the proportion of the radical, the total stroke number, the length of each stroke, the area of each stroke and the position coordinates of a central point.
A5, checking and analyzing the characters of the target printing finished product: and comparing and analyzing each character subregion in the target printing finished product and the set standard printing finished product to obtain a character content matching index corresponding to each character subregion in the target printing finished product.
As a further improvement of the present invention, in the step A5, each character subregion in the target printed finished product is compared and analyzed with the set standard printed finished product, and the specific analysis process is as follows: a501: dividing the set standard printing finished product according to the dividing mode of each character subregion corresponding to the target printing finished product to obtain each standard character subregion corresponding to the standard printing finished product, and obtaining the standard character parameters corresponding to each standard character subregion in the standard printing finished product according to the same obtaining method of the character parameters corresponding to each character subregion in the target printing finished product.
A502: extracting the number of characters in each character subarea, the word size of each character, the number of punctuation marks, the area of the radical corresponding to each character, the proportion of the radical, the total stroke number, the length of each stroke, and the length of each stroke from the character parameters corresponding to each character subarea in the target printing finished productThe area of the stroke and the position coordinate of the central point are respectively marked as N r 、
M r 、
And
r denotes the number of each text subregion, r =1,2,.. The t, p denotes the number of each text, p =1,2,.. The k, q denotes the number of each stroke, and q =1,2,.. The.
A503: extracting the number of characters in each standard character subregion, the word size of each character, the number of punctuation marks, the area of the radical corresponding to each character, the proportion of the radicals, the total stroke number, the length of each stroke, the area of each stroke and the position coordinate of the center point from the standard character parameters corresponding to each standard character subregion in the standard printing finished product, and respectively recording the number as N' r 、Z′ rp 、M′ r 、J′ rp 、C′ rp 、B′ rp 、L′ rp q、U′ rp q and (X' rp ,Y′ rp )。
A504: obtaining basic information matching indexes corresponding to all character subregions in the target printing finished product through calculation, and recording the basic information matching indexes as
It is to be noted that, according to the formula
Calculating the basic information matching index corresponding to each character subregion in the target printing finished product, wherein the delta N, the delta Z and the delta M are respectively expressed as set allowable character number difference, allowable punctuation mark number difference, d 1 、d 2 、d 3 Respectively representing the influence factors corresponding to the set number of characters, the character size and the number of punctuation marks.
A505: calculating to obtain the radical matching index corresponding to each character subregion in the target printing finished product, and recording the index as
As a further improvement of the present invention, in the step a505, the specific calculation formula of the radical matching index corresponding to each character subregion in the target printing finished product is as follows:
Δ J and Δ C are expressed as a set allowable radical area difference and an allowable radical proportion difference, respectively, b 1 、b 2 Respectively expressed as the influence factors corresponding to the area and the proportion of the radicals.
A506: calculating to obtain stroke matching index corresponding to each character subregion in the target printing finished product, and recording as
As a further improvement of the present invention, the stroke matching index corresponding to each character subregion in the target printing finished product in step a506 has a specific calculation formula as follows:
Δ B, Δ L, Δ U are respectively expressed as setting allowable total stroke number difference, allowable stroke length difference, allowable stroke picture product difference, B 3 、b 4 、b 5 Respectively expressed as the influence factors corresponding to the set total stroke number, stroke length and stroke area.
A507: calculating to obtain the position matching index corresponding to each character subregion in the target printing finished product, and recording the position matching index as
It is to be noted that, according to the formula
Calculating the position matching index corresponding to each character subregion in the target printing finished product, d 4 、d 5 Respectively representing the influence factors corresponding to the x-axis coordinate and the y-axis coordinate of the set character center point.
A508: according to the formula
Calculating the character content matching index eta corresponding to each character subregion in the target printing finished product r ，ε 1 、ε 2 、ε 3 、ε 4 And the weight factors are respectively expressed as the weight factors corresponding to the set basic information matching index, the radical matching index, the stroke matching index and the position matching index.
In a specific embodiment, the method analyzes the basic information matching index, the radical matching index, the stroke matching index and the position matching index corresponding to each character subregion, and further comprehensively analyzes the character content matching index corresponding to each character subregion, so that on one hand, the method breaks the limitation and one-sidedness of character matching degree analysis of the image-text printed matter in the prior art, and effectively avoids the error of the character matching degree analysis result in the image-text printed matter; on the other hand, the method not only provides powerful data support for the verification and analysis of the contents of the subsequent image-text printed matters to a great extent, but also greatly improves the rationality and reliability of the verification and analysis of the contents of the image-text printed matters.
A6, checking and analyzing the content of the target printing finished product: and comprehensively analyzing the picture content matching index corresponding to each picture subregion and the character content matching index corresponding to each character subregion in the target printed finished product to obtain a content matching coefficient corresponding to the target printed finished product, and correspondingly displaying the content matching coefficient through a target printed finished product content verification display module.
As a further improvement of the present invention, the content matching coefficient corresponding to the target printing finished product in step A6 has a specific calculation formula as follows:
xi is expressed as target printingContent matching coefficient, delta, corresponding to the finished product 1 、δ 2 And respectively representing the coefficient factors corresponding to the set picture content matching index and the set text content matching index.
Referring to fig. 2, a second aspect of the present invention provides a system for verifying contents of an image-text printed matter, including: the system comprises a target printing finished product dividing module, a target printing finished product picture processing module, a target printing finished product picture checking and analyzing module, a target printing finished product word processing module, a target printing finished product word checking and analyzing module, a target printing finished product content checking and analyzing module and a target printing finished product content checking and displaying module.
The target printing finished product dividing module is respectively connected with the target printing finished product picture processing module and the target printing finished product word processing module, the target printing finished product picture processing module is connected with the target printing finished product picture checking and analyzing module, the target printing finished product word processing module is connected with the target printing finished product word checking and analyzing module, and the target printing finished product content checking and analyzing module is respectively connected with the target printing finished product picture checking and analyzing module, the target printing finished product word checking and analyzing module and the target printing finished product content checking and displaying module.
And the target printing finished product dividing module is used for dividing the target printing finished product into each picture sub-area and each character sub-area according to a preset dividing mode.
And the target printing finished product image processing module is used for carrying out corresponding processing on each image subregion in the target printing finished product to obtain the image parameters corresponding to each image subregion in the target printing finished product.
And the target printing finished product image checking and analyzing module is used for comparing and analyzing each image subregion in the target printing finished product with the set standard printing finished product to obtain an image content matching index corresponding to each image subregion in the target printing finished product.
And the target printing finished product character processing module is used for carrying out corresponding processing on each character subregion in the target printing finished product to obtain the character parameters corresponding to each character subregion in the target printing finished product.
And the target printing finished product character checking and analyzing module is used for comparing and analyzing each character subregion in the target printing finished product and the set standard printing finished product to obtain a character content matching index corresponding to each character subregion in the target printing finished product.
And the target printing finished product content checking and analyzing module is used for comprehensively analyzing the picture content matching index corresponding to each picture subregion and the character content matching index corresponding to each character subregion in the target printing finished product to obtain a content matching coefficient corresponding to the target printing finished product.
And the target printing finished product content verification display module is used for correspondingly displaying the content matching coefficient corresponding to the target printing finished product.
The third aspect of the present invention provides a storage medium for content verification of an image-text printed matter, where the storage medium is burned with a computer program, and the computer program realizes the above method for content verification of an image-text printed matter when running in a memory of a server.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (10)
1. A method for verifying the content of an image-text printed matter is characterized by comprising the following steps:
a1, dividing a target printing finished product: dividing a target printing finished product according to a picture area and a character area, dividing the picture area corresponding to the target printing finished product into all picture sub-areas according to the number of pictures, and dividing the character area corresponding to the target printing finished product according to a preset dividing mode to obtain all character sub-areas;
a2, processing a target printing finished product picture: carrying out corresponding processing on each image subregion in the target printing finished product to obtain image parameters corresponding to each image subregion in the target printing finished product;
a3, checking and analyzing the target printing finished product picture: comparing and analyzing each picture subregion in the target printing finished product with a set standard printing finished product to obtain a picture content matching index corresponding to each picture subregion in the target printing finished product;
a4, processing the target printing finished product characters: performing corresponding processing on each character subarea in the target printing finished product to obtain character parameters corresponding to each character subarea in the target printing finished product;
a5, checking and analyzing the characters of the target printing finished product: comparing and analyzing each character subregion in the target printing finished product and a set standard printing finished product to obtain a character content matching index corresponding to each character subregion in the target printing finished product;
a6, checking and analyzing the content of the target printing finished product: and comprehensively analyzing the picture content matching index corresponding to each picture subregion and the character content matching index corresponding to each character subregion in the target printed finished product to obtain a content matching coefficient corresponding to the target printed finished product, and correspondingly displaying the content matching coefficient through a target printed finished product content verification display module.
2. A method of verifying the contents of an image-text printed matter according to claim 1, characterized in that: in the step A2, the image sub-regions in the target printed product are correspondingly processed, and the specific processing process is as follows:
graying each picture subregion in the target printing finished product, classifying the same gray value in each picture subregion to obtain each gray region corresponding to each picture subregion, acquiring the distribution quantity corresponding to each gray region in each picture subregion, and acquiring the area of each distribution block corresponding to each gray region in each picture subregion;
acquiring the central point position corresponding to each picture sub-region, simultaneously constructing a coordinate system corresponding to each picture sub-region based on the central point position corresponding to each picture region, and simultaneously acquiring the central point position coordinates of each distribution block corresponding to each gray region in each picture sub-region;
and the picture parameters corresponding to the image sub-regions in the target printing finished product are formed by the number of the distribution blocks corresponding to the gray scale regions in the image sub-regions, the areas of the distribution blocks and the position coordinates of the central point.
3. A method of verifying the contents of an image-text printed matter according to claim 1, characterized in that: in the step A3, each image subregion in the target printed finished product is compared and analyzed with the set standard printed finished product, and the specific analysis process is as follows:
dividing the set standard printing finished product according to the dividing mode of each image subregion corresponding to the target printing finished product to obtain each standard image subregion corresponding to the standard printing finished product, performing graying processing on each standard image subregion corresponding to the standard printing finished product, and classifying the same gray value in each standard image subregion to obtain each gray region corresponding to each standard image subregion;
acquiring standard picture parameters corresponding to all standard picture subregions in a standard printing finished product according to the same acquisition method of the picture parameters corresponding to all the picture subregions in the target printing finished product;
extracting the number of distribution blocks corresponding to each gray scale region in each image subregion, the area of each distribution block and the position coordinates of a central point from the image parameters corresponding to each image subregion in the target printing finished product, and respectively recording the quantity, the area and the position coordinates of the central point as
And
i denotes the number of each picture sub-region, i =1,2, a.. Page, n, j denotes the number of each gray scale region, j =1,2, a.. Page, m, f denotes the number of each distribution block, f =1,2, a.. Page, g;
extracting the number of distribution blocks corresponding to each gray scale region in each standard picture subregion, the area of each distribution block and the position coordinates of a center point from standard picture parameters corresponding to each standard picture subregion in a standard printing finished product, and respectively recording the number of distribution blocks, the area of each distribution block and the position coordinates of the center point as R' ij 、S′ ij f and (x)′ ij f,y′ ij f)；
According to the formula
Calculating the picture distribution coincidence index of each picture subregion corresponding to each gray level region in the target printing finished product
Δ R, Δ S are expressed as a set allowable individual process quantity difference, an allowable distribution block area difference, a 1 、a 2 Respectively representing the influence factors corresponding to the set quantity and area;
according to the formula
Calculating the picture position offset index of each picture subregion corresponding to each gray level region in the target printing finished product
e is expressed as a natural constant, a 3 、a 4 Respectively representing the influence factors corresponding to the set x-axis coordinate point and the set y-axis coordinate point;
according to the formula
Calculating the picture content matching index corresponding to each picture subregion in the target printing finished product,
expressed as a picture content matching index corresponding to the ith picture subregion in the target printed finished product, a 5 、a 6 Respectively expressed as weight factors corresponding to the set picture distribution conformity index and the picture position deviation index.
4. A method of verifying the contents of an image-text printed matter according to claim 1, characterized in that: in the step A4, the character subareas in the target printed finished product are correspondingly processed in the following specific processing mode:
acquiring the number of characters corresponding to each character subregion in a target printing finished product, the word size of each character and the number of punctuation marks by an intelligent camera;
extracting the radicals corresponding to the characters in the character subareas from the characters corresponding to the character subareas in the target printing finished product, acquiring the area of the radicals corresponding to the characters in the character subareas, and acquiring the area ratio of the radicals corresponding to the characters in the character subareas to the characters, and recording the area ratio as the occupation ratio;
extracting the total stroke number, the length and the area of each stroke corresponding to each character in each character subregion from each character corresponding to each character subregion in the target printing finished product;
acquiring central points of the target printing finished product corresponding to the character sub-regions, constructing a character coordinate system corresponding to each character sub-region based on the central points of the target printing finished product corresponding to each character sub-region, and acquiring position coordinates of the central points of the characters in each character sub-region;
the character parameters corresponding to each character subregion in the target printing finished product are formed by the number of characters in each character subregion, the word size of each character, the number of punctuation marks, the area of each character corresponding to a radical, the proportion of the radical, the total stroke number, the length of each stroke, the area of each stroke and the position coordinates of a central point.
5. A method of verifying the contents of a teletext print according to claim 3, wherein: in the step A5, each character subregion in the target printed finished product is compared and analyzed with the set standard printed finished product, and the specific analysis process is as follows:
a501: dividing the set standard printing finished product according to the dividing mode of each character subregion corresponding to the target printing finished product to obtain each standard character subregion corresponding to the standard printing finished product, and obtaining the standard character parameters corresponding to each standard character subregion in the standard printing finished product according to the same obtaining method of the character parameters corresponding to each character subregion in the target printing finished product;
a502: extracting the number of characters in each character subregion, the word size of each character, the number of punctuation marks, the area of radicals corresponding to each character, the proportion of radicals, the total stroke number, the length of each stroke, the area of each stroke and the position coordinate of a central point from the character parameters corresponding to each character subregion in the target printing finished product, and respectively recording the number of characters, the word size of each character, the number of punctuation marks, the area of each stroke, the position coordinate of the central point as N r 、
M r 、
And
r denotes the number of each text subregion, r =1,2,. ·. a, t, p denotes the number of each text, p =1,2,.. A, k, q denotes the number of each stroke, q =1,2,... A.w.;
a503: extracting the number of characters in each standard character subregion, the word size of each character, the number of punctuation marks, the area of the radical corresponding to each character, the proportion of the radicals, the total stroke number, the length of each stroke, the area of each stroke and the position coordinate of the center point from the standard character parameters corresponding to each standard character subregion in the standard printing finished product, and respectively recording the number as N' r 、Z′ rp 、M′ r 、J′ rp 、C′ rp 、B′ rp 、L′ rp q、U′ rp q and (X' rp ,Y′ rp )；
A504: obtaining basic information matching indexes corresponding to all character subregions in the target printing finished product through calculation, and recording the basic information matching indexes as
A505: calculating to obtain the radical matching index corresponding to each character subregion in the target printing finished product, and recording the index as
A506: calculating to obtain stroke matching index corresponding to each character subregion in the target printing finished product, and recording as
A507: calculating to obtain the position matching index corresponding to each character subregion in the target printing finished product, and recording the position matching index as
A508: according to the formula
Calculating the character content matching index eta corresponding to each character subregion in the target printing finished product r ，ε 1 、ε 2 、ε 3 、ε 4 And the weight factors are respectively expressed as the weight factors corresponding to the set basic information matching index, the radical matching index, the stroke matching index and the position matching index.
6. The method for verifying the contents of a graphic print according to claim 5, wherein: the specific calculation formula of the radical matching index corresponding to each character subregion in the target printing finished product in the step a505 is as follows:
Δ J and Δ C are expressed as a set allowable radical area difference and an allowable radical proportion difference, respectively, b 1 、b 2 Respectively expressed as the influence factors corresponding to the area and the proportion of the radicals.
7. The method for verifying the contents of a graphic print according to claim 5, wherein: in the step a506, the stroke matching index corresponding to each character subregion in the target printing finished product has a specific calculation formula as follows:
Δ B, Δ L, Δ U are expressed as setting allowable total stroke number difference, allowable stroke length difference, allowable stroke picture product difference, B 3 、b 4 、b 5 Respectively expressed as the influence factors corresponding to the set total stroke number, stroke length and stroke area.
8. The method for verifying the contents of a graphic print according to claim 5, wherein: the content matching coefficient corresponding to the target printing finished product in the step A6 has a specific calculation formula as follows:
xi is expressed as a content matching coefficient, delta, corresponding to the target printed finished product 1 、δ 2 And the coefficient factors are respectively expressed as the coefficient factors corresponding to the set picture content matching index and the set character content matching index.
9. A system for verifying the contents of an image-text printed matter, comprising:
the target printing finished product dividing module is used for dividing the target printing finished product into each picture subregion and each character subregion according to a preset dividing mode;
the target printing finished product image processing module is used for carrying out corresponding processing on each image subregion in the target printing finished product to obtain image parameters corresponding to each image subregion in the target printing finished product;
the target printing finished product image checking and analyzing module is used for comparing and analyzing each image subregion in the target printing finished product with a set standard printing finished product to obtain an image content matching index corresponding to each image subregion in the target printing finished product;
the target printing finished product character processing module is used for carrying out corresponding processing on each character subarea in the target printing finished product to obtain character parameters corresponding to each character subarea in the target printing finished product;
the target printing finished product character checking and analyzing module is used for comparing and analyzing each character subregion in the target printing finished product and a set standard printing finished product to obtain a character content matching index corresponding to each character subregion in the target printing finished product;
the target printing finished product content checking and analyzing module is used for comprehensively analyzing the picture content matching index corresponding to each picture subregion and the character content matching index corresponding to each character subregion in the target printing finished product to obtain a content matching coefficient corresponding to the target printing finished product;
and the target printing finished product content verification display module is used for correspondingly displaying the content matching coefficient corresponding to the target printing finished product.
10. A kind of picture and text printed matter content checks the storage medium, characterized by that: the content verification storage medium of the image-text printed matter is burned with a computer program, and when the computer program runs in a memory of a server, the content verification method of the image-text printed matter of any one of the claims 1-8 is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211221321.5A CN115527067A (en) | 2022-10-08 | 2022-10-08 | Method, system and storage medium for verifying contents of image-text printed matter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211221321.5A CN115527067A (en) | 2022-10-08 | 2022-10-08 | Method, system and storage medium for verifying contents of image-text printed matter |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115527067A true CN115527067A (en) | 2022-12-27 |
Family
ID=84702358
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211221321.5A Withdrawn CN115527067A (en) | 2022-10-08 | 2022-10-08 | Method, system and storage medium for verifying contents of image-text printed matter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115527067A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116728968A (en) * | 2023-06-25 | 2023-09-12 | 深圳市永顺创能技术有限公司 | Intelligent management system for ink supply of printing equipment |
-
2022
- 2022-10-08 CN CN202211221321.5A patent/CN115527067A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116728968A (en) * | 2023-06-25 | 2023-09-12 | 深圳市永顺创能技术有限公司 | Intelligent management system for ink supply of printing equipment |
| CN116728968B (en) * | 2023-06-25 | 2024-03-19 | 深圳市永顺创能技术有限公司 | Intelligent management system for ink supply of printing equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR100658119B1 (en) | Apparatus and Method for Recognizing Character | |
| JP4006224B2 (en) | Image quality determination method, determination device, and determination program | |
| US8494273B2 (en) | Adaptive optical character recognition on a document with distorted characters | |
| CN108229299A (en) | The recognition methods of certificate and device, electronic equipment, computer storage media | |
| CN112446351B (en) | Intelligent identification method for medical bills | |
| JP6773400B2 (en) | A recording medium equipped with a form recognition device, a form recognition system, a form recognition system program, a form recognition system control method, and a form recognition system program. | |
| CN113569863B (en) | Document checking method, system, electronic equipment and storage medium | |
| CN111695555B (en) | Question number-based accurate question framing method, device, equipment and medium | |
| CN115527067A (en) | Method, system and storage medium for verifying contents of image-text printed matter | |
| CN112036295A (en) | Bill image processing method, bill image processing device, storage medium and electronic device | |
| CN108992033B (en) | Grading device, equipment and storage medium for vision test | |
| JP2003109007A (en) | Device, method and program for classifying slip form and image collating device | |
| US11527102B2 (en) | Systems and methods of automated biometric identification reporting | |
| CN111259888A (en) | Image-based information comparison method and device and computer-readable storage medium | |
| US20220188543A1 (en) | Information processing apparatus and non-transitory computer readable medium | |
| CN111612045B (en) | Universal method for acquiring target detection data set | |
| KR100957508B1 (en) | System and method for recognizing optical characters | |
| CN116363668B (en) | Intelligent book checking method and system | |
| CN117475453B (en) | Document detection method and device based on OCR and electronic equipment | |
| CN115631493B (en) | Text region determining method, system and related device | |
| JP7197009B2 (en) | Object management system | |
| JPH09326037A (en) | Pattern forming device and recording medium storing program for pattern generation | |
| CN116778466A (en) | Large-angle license plate recognition method, device, equipment and storage medium | |
| CN112560836A (en) | Component identification method and device and computer readable storage medium | |
| Barros et al. | Interpretability of an Automatic Handwritten Signature Verification Model |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20221227 |
|
| WW01 | Invention patent application withdrawn after publication |