CN114529570A - Image segmentation method, image identification method, user certificate subsidizing method and system - Google Patents
Image segmentation method, image identification method, user certificate subsidizing method and system Download PDFInfo
- Publication number
- CN114529570A CN114529570A CN202210158194.2A CN202210158194A CN114529570A CN 114529570 A CN114529570 A CN 114529570A CN 202210158194 A CN202210158194 A CN 202210158194A CN 114529570 A CN114529570 A CN 114529570A
- Authority
- CN
- China
- Prior art keywords
- image
- pattern
- pixel
- gray
- target
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- 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
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
Abstract
The invention provides an image segmentation method, an image identification method, a user certificate subsidizing method and a user certificate subsidizing system, which relate to the field of big data.
Description
Technical Field
The application relates to the technical field of big data, in particular to an image segmentation method, an image identification method, a user certificate subsidizing method and a user certificate subsidizing system.
Background
When a customer encounters the situations of loss, damage and the like of a bank card, the bank card needs to be reprocessed, and the customer needs to take various certificates to a website for handling, but at present, the image identification technology has defects, particularly the fingerprint image identification technology has the defects of low identification accuracy and the like, so that the problems of complex flow, low efficiency and the like exist in the above scenes.
Disclosure of Invention
In order to solve the technical problem, the application provides the following technical scheme:
in a first aspect, the present application provides an image segmentation method, including:
acquiring a gray level image of an image to be segmented; the image to be segmented comprises a target pattern and a background pattern;
and according to the distance information of each pixel point in the gray image and the corresponding zero-value pixel point, combining the gray difference data of each pixel point and the target pattern pixel and the background pattern pixel, and segmenting the gray image to obtain the target pattern.
In some embodiments, the image recognition method further comprises:
generating a set threshold according to the gray data of all pixel points in the gray image;
performing binarization processing on each pixel point of the gray level image according to the set threshold value to obtain a binarized image;
determining pixel point position information corresponding to the target body pixel value in the binary image;
and according to the determined pixel point position information, extracting pixel points at corresponding positions from the gray level image to generate an initial target body pattern.
In some embodiments, the segmenting the grayscale image to obtain the target volume pattern by combining grayscale difference data of each pixel point and a target volume pattern pixel and a background pattern pixel according to the distance information between each pixel point and a corresponding zero-value pixel point includes:
generating a brightness image corresponding to the gray image according to the distance information corresponding to each pixel point and by combining the corresponding relation between the distance information and the brightness value;
marking the contour of the target body by combining the gray difference data of each pixel point and the pattern pixel of the target body and the background pattern pixel according to the brightness image;
and segmenting a target body pattern correspondingly defined by the target body outline from the gray level image.
In some embodiments, the segmenting the grayscale image to obtain the target volume pattern by combining grayscale difference data of each pixel point and a target volume pattern pixel and a background pattern pixel according to the distance information between each pixel point and a corresponding zero-value pixel point includes:
generating a brightness pattern corresponding to the initial target body pattern according to the distance information corresponding to each pixel point in the initial target body pattern and by combining the corresponding relation between the distance information and the brightness value;
according to the brightness pattern, combining the gray difference data marks of each pixel point, the target pattern pixel and the background pattern pixel to obtain an updated target body outline;
segmenting the target volume pattern correspondingly defined by the updated target volume profile from the initial target volume pattern.
In some embodiments, the target is a fingerprint, and the step of segmenting the grayscale image to obtain the target pattern before generating the luminance pattern corresponding to the initial target pattern further includes at least one of the following steps:
based on a fingerprint standard form, removing pixel points with pixel areas smaller than a set value in the gray level image;
based on the USM algorithm, utilizing a convolution kernel to carry out image convolution operation;
and scanning the gray level image point by point based on eight neighborhood chain codes, searching for boundaries, and removing the boundaries lower than the thresholds by utilizing a plurality of thresholds.
In some embodiments, the generating a set threshold according to the gray data of all the pixels in the gray image includes:
obtaining the average gray of a target pixel point and the average gray of a background pixel point according to the gray data of all pixel points in the gray image;
and calculating the inter-class variance according to the ratio of the number of the target pixel points to the number of the gray image pixel points, the average gray level of the target pixel points, the ratio of the number of the background pixel points to the number of the gray image pixel points and the average gray level of the background pixel points to obtain the set threshold.
In some embodiments, said labeling the target volume contour from said luminance image in combination with grayscale difference data for each pixel point and target volume pattern pixels and background pattern pixels comprises
Obtaining the type of each pixel point by combining the gray difference data of each pixel point, the target pattern pixel and the background pattern pixel according to the brightness image, wherein the type of each pixel point comprises the background pixel and the target pixel;
and marking the pixel points corresponding to the target pixels to form the target body outline.
A second aspect provides a method of image recognition, comprising the image segmentation method of any one of the above, and
and identifying the target body pattern segmented by the image segmentation method.
In some embodiments, the identifying the target volume pattern segmented by the image segmentation method includes:
determining a plurality of initial clustering centers according to the gray level image;
executing iteration operation, distributing each pixel point to a corresponding initial clustering center according to the similarity of each pixel point and each initial clustering center to form a plurality of clusters, recalculating the clustering center of each cluster to obtain a corresponding updated clustering center, and redistributing each pixel point to each updated clustering center based on the similarity until each updated clustering center is kept unchanged to obtain a plurality of final clusters;
identifying the target volume pattern from the final plurality of clusters.
In a third aspect, the present application provides a user credential complementing method based on image recognition, including:
acquiring a subsidy request of a user subsidy user certificate and a gray image input by the user; the gray image comprises a target body pattern and a background pattern;
according to the distance information of each pixel point in the target body gray image and the corresponding zero-value pixel point, combining the gray difference data of each pixel point and the target body pattern pixel and the background pattern pixel, and segmenting the target body gray image to obtain a target body pattern;
identifying whether the target volume pattern is a fingerprint pattern;
and if the fingerprint pattern is the reserved fingerprint pattern with the same texture as the fingerprint pattern, allowing the user to make a request.
In a fourth aspect, the present application provides an image segmentation system, comprising:
the image acquisition module is used for acquiring a gray image of an image to be segmented; the image to be segmented comprises a target pattern and a background pattern;
and the image segmentation module is used for segmenting the gray image to obtain a target body pattern by combining the gray difference data of each pixel point and the target body pattern pixel and the background pattern pixel according to the distance information of each pixel point in the gray image and the corresponding zero-value pixel point.
In certain embodiments, further comprising:
the set threshold generating module is used for generating a set threshold according to the gray data of all pixel points in the gray image;
the binarization processing module is used for carrying out binarization processing on each pixel point of the gray level image according to the set threshold value to obtain a binarization image;
the target position information determining module is used for determining pixel point position information corresponding to the target body pixel value in the binary image;
and the initial target body pattern generating module is used for extracting pixel points at corresponding positions from the gray level image according to the determined pixel point position information to generate an initial target body pattern.
In certain embodiments, the image segmentation module comprises:
the brightness image generating unit generates a brightness image corresponding to the gray image according to the distance information corresponding to each pixel point and by combining the corresponding relation between the distance information and the brightness value;
the contour marking unit is used for marking the contour of the target body by combining the gray difference data of each pixel point, the pattern pixel of the target body and the background pattern pixel according to the brightness image;
and the target body pattern segmentation unit is used for segmenting a target body pattern correspondingly limited by the target body outline from the gray level image.
In certain embodiments, the image segmentation module comprises:
the luminance image generating unit is used for generating a luminance pattern corresponding to the initial target body pattern according to the distance information corresponding to each pixel point in the initial target body pattern and the corresponding relation between the distance information and the luminance value;
the target body contour updating unit is used for obtaining an updated target body contour by combining the gray difference data marks of each pixel point, the target body pattern pixel and the background pattern pixel according to the brightness pattern;
and the target body pattern segmentation unit is used for segmenting the target body pattern correspondingly limited by the updated target body outline from the initial target body pattern.
In certain embodiments, the object is a fingerprint, the image segmentation system further comprising at least one of:
the pixel point removing module is used for removing pixel points with pixel areas smaller than a set value in the gray level image based on a fingerprint standard form;
the convolution module is used for carrying out convolution operation on the image by utilizing a convolution kernel based on a USM algorithm;
and the boundary removing module is used for scanning the gray level image point by point based on eight neighborhood chain codes, searching for boundaries and removing the boundaries lower than the thresholds by utilizing the thresholds.
In some embodiments, the setting threshold generation module comprises:
the average gray level generation unit is used for obtaining the average gray level of the target pixel point and the average gray level of the background pixel point according to the gray level data of all the pixel points in the gray level image;
and the set threshold generating unit is used for calculating the inter-class variance according to the ratio of the number of target pixels to the number of gray image pixels, the average gray of the target pixels, the ratio of the number of background pixels to the number of gray image pixels and the average gray of the background pixels to obtain the set threshold.
In some embodiments, the outline marker unit includes:
the pixel point type determining unit is used for obtaining the type of each pixel point by combining the gray difference data of each pixel point, the target pattern pixel and the background pattern pixel according to the brightness image, wherein the type of each pixel point comprises the background pixel and the target pixel;
and the marking unit is used for marking the pixel points corresponding to the target pixels to form a target body outline.
In a fifth aspect, the present application provides an image recognition system, comprising:
the image acquisition module is used for acquiring a gray image of an image to be segmented; the image to be segmented comprises a target pattern and a background pattern;
the image segmentation module is used for segmenting the gray image to obtain a target body pattern by combining gray difference data of each pixel point and a target body pattern pixel and a background pattern pixel according to the distance information of each pixel point in the gray image and a corresponding zero-value pixel point;
and the image identification module is used for identifying the target body pattern segmented by the image segmentation method.
In a sixth aspect, the present application provides a user credential reprocessing system based on image recognition, including:
the image acquisition module is used for acquiring a subsidy request of a user subsidy user certificate and a gray image input by the user; the gray image comprises a target body pattern and a background pattern;
the image segmentation module is used for segmenting the target body gray level image to obtain a target body pattern by combining gray level difference data of each pixel point and a target body pattern pixel and a background pattern pixel according to the distance information of each pixel point and a corresponding zero-value pixel point in the target body gray level image;
the image identification module is used for identifying whether the target body pattern is a fingerprint pattern;
and if the fingerprint pattern is the reserved fingerprint pattern with the same texture as the fingerprint pattern, allowing the user to make a request.
In a seventh aspect, the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the image segmentation method and the image recognition method when executing the computer program.
In an eighth aspect, the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the image segmentation method and the image recognition method described above.
According to the technical scheme, the image segmentation method, the image identification method, the user certificate subsidizing method and the user certificate subsidizing system are characterized in that the gray image is segmented to obtain the target body pattern by combining the gray difference data of each pixel point and the target body pattern pixel and the background pattern pixel according to the distance information of each pixel point in the gray image and the corresponding zero-value pixel point, the accuracy and the efficiency of image identification are improved, the fingerprint identification and the fingerprint information acquired by card transaction for the first time are matched with the identity of the owner of the identification card for the fingerprint pattern, the user certificate is subsidized conveniently and quickly, the working efficiency of workers is improved, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a picture segmentation method in an embodiment of the present application.
Fig. 2 is a schematic flow chart of image preliminary segmentation in the image segmentation method in the embodiment of the present application.
Fig. 3 is a schematic specific flowchart of step S200 in fig. 1 in this embodiment of the application.
Fig. 4 is a schematic specific flowchart of step S200 in fig. 1 in this embodiment.
Fig. 5 is a schematic flowchart further included in the picture segmentation method in the embodiment of the present application.
Fig. 6 is a flowchart of fingerprint image contour extraction and segmentation in the image segmentation method in the embodiment of the present application.
Fig. 7 is a schematic diagram of eight neighborhood chain codes in the picture segmentation method in the embodiment of the present application.
Fig. 8 is a schematic flowchart of the calculation of the binarization threshold in the image identification method in the embodiment of the application.
Fig. 9 is a flowchart illustrating a picture identification method in an embodiment of the present application.
FIG. 10 is a schematic diagram of an image recognition flow of a K-means algorithm in the image recognition method in the embodiment of the present application.
Fig. 11 is a flowchart illustrating a user credential subsidizing method based on image recognition in an embodiment of the present application.
Fig. 12 is a schematic structural diagram of a picture segmentation system in an embodiment of the present application.
Fig. 13 is a schematic structural diagram of a picture recognition system in an embodiment of the present application.
Fig. 14 is a schematic diagram of an image preliminary segmentation structure of the picture recognition system in the embodiment of the present application.
Fig. 15 is a schematic diagram of a flow of preliminary segmentation of a fingerprint image of a picture recognition system in an embodiment of the present application.
Fig. 16 is a schematic full-flow diagram of a user credential sponsoring system based on image recognition in the embodiment of the present application.
Fig. 17 is a schematic structural diagram of a user credential sponsoring system based on image recognition in the embodiment of the present application.
Fig. 18 is a schematic structural diagram of an electronic device in the embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all 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 application.
The present application relates to the field of big data, and it is understood that the present application is also applicable to other fields, and is not limited thereto.
In order to facilitate and improve the image recognition accuracy, the present application provides an embodiment of an image segmentation method, referring to fig. 1, including:
step S100: acquiring a gray level image of an image to be segmented; the image to be segmented comprises a target pattern and a background pattern;
step S200: and according to the distance information of each pixel point in the gray image and the corresponding zero-value pixel point, combining the gray difference data of each pixel point and the target pattern pixel and the background pattern pixel, and segmenting the gray image to obtain the target pattern.
The application provides an image segmentation method, through according to every pixel point combines with the distance information of the zero value pixel point that corresponds in the grey scale image every pixel point and the grey scale difference data of target body pattern pixel and background pattern pixel, right the grey scale image is cut apart and is obtained the target body pattern, has improved picture identification's exactness and efficiency, to fingerprint pattern with discernment fingerprint and the fingerprint information of handling the card for the first time and gather match the identity of discernment card owner, and convenient and fast subsidies the user certificate, improves staff work efficiency, improves user experience.
The method comprises the steps of obtaining an image to be segmented, preprocessing the image to be segmented by using the pattern to be identified in the image as a target pattern and using the rest as background patterns, and converting the image to be segmented into a gray image; and comprehensively utilizing the distance between each pixel point and the pixel point closest to the zero value and the gray difference between each pixel point and the target and the background to judge the attribute of the pixel point, wherein the attribute comprises the target pixel and the background pixel, so as to realize image segmentation.
In an embodiment of the image segmentation method provided in the present application, a preferred manner of image segmentation is provided, and referring to fig. 2, the image segmentation method further includes:
step S011: generating a set threshold according to the gray data of all pixel points in the gray image;
step S012: performing binarization processing on each pixel point of the gray level image according to the set threshold value to obtain a binarized image;
step S013: determining pixel point position information corresponding to the target body pixel value in the binary image;
step S014: and according to the determined pixel point position information, extracting pixel points at corresponding positions from the gray level image to generate an initial target body pattern.
It will be appreciated that the binarization process may classify the target user context in preparation for subsequent identification of the target volume. In addition, the binarization of the gray level image can adopt a threshold value method, the image is respectively set to two different levels by utilizing the difference between a target and a background in the image, and a proper threshold value is selected to determine whether a certain pixel is the target or the background, so that the binarized image is obtained.
In the embodiment of the invention, the obtained gray level image is subjected to binarization processing by adopting an OTSU algorithm, a threshold value is set, the pixel value of the image is adjusted according to the threshold value, and a condition is provided for searching the pixel point coordinates meeting the condition subsequently; carrying out binarization processing on the gray level image to obtain a binarized image; and comparing the gray value of the pixel point of the gray image with a set threshold value, screening out pixel point coordinates meeting the conditions, and marking on the fingerprint image according to the pixel point coordinates meeting the conditions to obtain an initial target pattern.
As can be seen from the above description, the image segmentation method provided in the embodiment of the present application performs binarization by using an OTSU algorithm, and performs preliminary segmentation on a grayscale image, so as to facilitate subsequent processing of image segmentation.
In some specific embodiments, referring to fig. 3, the segmenting the grayscale image to obtain the target volume pattern according to the distance information between each pixel point and the corresponding zero-valued pixel point and by combining the grayscale difference data between each pixel point and the target volume pattern pixel and the background pattern pixel includes:
step S201: generating a brightness image corresponding to the gray image according to the distance information corresponding to each pixel point and by combining the corresponding relation between the distance information and the brightness value;
step S202: marking the contour of the target body by combining the gray difference data of each pixel point, the pattern pixel of the target body and the background pattern pixel according to the brightness image;
step S203: and segmenting a target body pattern correspondingly defined by the target body outline from the gray level image.
It can be understood that the distance information corresponding to each pixel point refers to a distance from the pixel point in the image to the nearest zero pixel point, that is, the shortest distance of the zero pixel point, the image is binarized firstly, then each pixel is assigned with a distance (Manhattan distance or Euclidean distance) between the nearest background pixel point and the background pixel point, and a distance metric (distance matrix) is obtained, so that the farther the point is from the boundary, the brighter the point is, and the luminance image corresponding to the gray image is obtained; and obtaining a target body contour according to the brightness image and the gray level difference between each pixel point and the target body pattern pixel and the background pattern pixel, and segmenting the target pattern and the background pattern according to the target body contour to obtain a finally segmented target image.
In the embodiment of the invention, the segmentation of the invention can adopt watershed transform, the image is regarded as a topological landform in geodetic science, the gray value of each pixel of each point in the image represents the altitude of the point, each local minimum value and the influence area thereof are called as a catchbasin, and the boundary of the catchbasin forms a watershed. The implementation of the algorithm can be modeled as a flood process, with the lowest points of the image submerged first, and then the water gradually submerged the entire valley. The water level will overflow when it reaches a certain height, at which time dams are built up where the water overflows, and the process is repeated until all points on the entire image are submerged, at which time the series of built dams become watershed separating the basins.
The watershed algorithm of the invention has good response to weak edges and can be used for pertinently matching the aspect of fingerprint identification.
In an embodiment of the image segmentation method provided by the present application, a preferable mode of image segmentation is provided, and referring to fig. 4, the segmenting the grayscale image to obtain the target volume pattern according to the distance information between each pixel point and the corresponding zero-valued pixel point and by combining the grayscale difference data between each pixel point and the target volume pattern pixel and the background pattern pixel includes:
step S204: generating a brightness pattern corresponding to the initial target body pattern according to the distance information corresponding to each pixel point in the initial target body pattern and by combining the corresponding relation between the distance information and the brightness value;
step S205: according to the brightness pattern, combining the gray difference data marks of each pixel point, the target pattern pixel and the background pattern pixel to obtain an updated target body outline;
step S206: segmenting the target volume pattern correspondingly defined by the updated target volume profile from the initial target volume pattern.
It can be understood that the image segmentation is performed twice on the basis of performing primary segmentation on the binary image by using an OTSU algorithm, and the target pattern after twice segmentation is clearer and more accurate than the target pattern after once segmentation.
In an embodiment of the image segmentation method provided by the present application, a preferable way of extracting a fingerprint image is provided, referring to fig. 5, where the target is a fingerprint, and the segmenting the grayscale image to obtain a target pattern according to distance information between each pixel point and a corresponding zero-valued pixel point and by combining grayscale difference data between each pixel point and a target pattern pixel and a background pattern pixel includes:
step S301: based on a fingerprint standard form, removing pixel points with the pixel area smaller than a set value in the gray level image;
step S302: utilizing a convolution kernel to carry out image convolution operation based on a USM algorithm;
step S303: and scanning the gray level image point by point based on eight neighborhood chain codes, searching for boundaries, and removing the boundaries lower than the thresholds by utilizing a plurality of thresholds.
It can be understood that when the image to be segmented is a fingerprint image, the fingerprint image needs to be processed and then watershed segmented, referring to fig. 6, morphological operation is firstly adopted, and multiple morphological processing is carried out, so that an area with a very small pixel area in the image is eliminated; and then, scanning the fingerprint image point by adopting eight neighborhood chain codes, searching for a boundary, eliminating invalid contour information by using multiple thresholds, and then tracking the fingerprint contour to form a marked image.
In the embodiment of the invention, the images containing the fingerprints are collected and screened out, and the USM algorithm is adopted to check the image convolution by utilizing the convolution, so that the edge enhancement of the fingerprint image is realized; a common algorithm for realizing sharpening by image convolution processing is called an Unshiharpen Mask method, and the sharpening method is that Gaussian blur is firstly carried out on an original image, then the original image is subtracted by an image obtained by multiplying a coefficient by the Gaussian blur, and then a value Scale is adjusted to be within an RGB pixel value range of 0-255. The USM sharpening-based method can remove some fine interference details and noise, and is more real and credible than an image sharpening result obtained by directly using a convolution sharpening operator.
In the embodiment of the invention, through morphological operation, a specific logical operation is carried out on the region corresponding to the binary image at each pixel position, and the result of the logical operation is a response pixel of the output image.
In the embodiment of the invention, the chain code is an important feature at the later stage of image extraction, namely, pattern identification, for example, the feature of the chain code is used for carrying out digital identification or character identification, and the extraction of the chain code can acquire a boundary sequence which is difficult to acquire by means of a boundary tracking algorithm.
In some specific embodiments, referring to fig. 8, the generating a set threshold according to the gray data of all the pixels in the gray image includes:
step S207: obtaining the average gray of a target pixel point and the average gray of a background pixel point according to the gray data of all pixel points in the gray image;
step S208: and calculating the inter-class variance according to the ratio of the number of the target pixel points to the number of the gray image pixel points, the average gray level of the target pixel points, the ratio of the number of the background pixel points to the number of the gray image pixel points and the average gray level of the background pixel points to obtain the set threshold.
In some embodiments, let p be the grayscale image f (x)1The number of the pixel points of the foreground accounts for the proportion value of the sample image, and the average gray level is m1；p2Setting the average gray level as m for the proportion of the number of background pixels in the whole sample image2，
Is the between-class variance; then initializing each variable; then traversing each pixel point, and calculating each value of the foreground part and the background part, including the total number of the pixel points, the total gray sum of the pixel points, the average gray and the proportion of partial pixel points; finally by the formula
Calculating the between-class variance
I.e. the threshold of the OTSU algorithm.
In some embodiments, said labeling the target volume contour from said luminance image in combination with grayscale difference data for each pixel point and target volume pattern pixels and background pattern pixels comprises:
obtaining the type of each pixel point by combining the gray difference data of each pixel point, the target pattern pixel and the background pattern pixel according to the brightness image, wherein the types of the pixel points comprise the background pixel and the target pixel;
and marking the pixel points corresponding to the target pixels to form the target body outline.
In the present embodiment, the first and second electrodes are,
the present application further provides an image recognition method, referring to fig. 9, including:
step S100: acquiring a gray level image of an image to be segmented; the image to be segmented comprises a target pattern and a background pattern;
step S200: according to the distance information of each pixel point in the gray image and the corresponding zero-value pixel point, combining the gray difference data of each pixel point and the target pattern pixel and the background pattern pixel, and segmenting the gray image to obtain a target pattern;
step S300: and identifying the target body pattern segmented by the image segmentation method.
It can be understood that the invention divides the gray image to obtain the target volume pattern by combining the gray difference data of each pixel point and the target volume pattern pixel and the background pattern pixel according to the distance information of each pixel point and the corresponding zero-value pixel point in the gray image, thereby improving the accuracy and efficiency of image recognition.
In some specific embodiments, referring to fig. 10, the identifying the target volume pattern segmented by the image segmentation method includes:
step S401: determining a plurality of initial clustering centers according to the gray level image;
step S402: executing iteration operation, distributing each pixel point to a corresponding initial clustering center according to the similarity of each pixel point and each initial clustering center to form a plurality of clusters, recalculating the clustering center of each cluster to obtain a corresponding updated clustering center, and redistributing each pixel point to each updated clustering center based on the similarity until each updated clustering center is kept unchanged to obtain a plurality of final clusters;
step S403: identifying the target volume pattern from the final plurality of clusters.
It can be understood that, in the embodiment of the present invention, the fingerprint identification is performed by using a K-means algorithm, and the steps include:
step 1: acquiring the number of required images, screening out images containing fingerprints, and processing the current image by adopting a contrast-limiting self-adaptive histogram equalization algorithm;
and 2, step: adopting a horizontal windowing binarization algorithm to the image obtained in the step 1, binarizing the image, and highlighting fingerprint features in the background;
and step 3: the image is segmented by adopting a K-means algorithm, the number of K values of a central point is estimated through a binarization threshold value, and the position of a clustering center is determined according to an image gray value statistical histogram;
(1) giving k initial clustering centers;
(2) and (3) repeating: redistributing each data object to k clustering centers to form k clusters, and recalculating the clustering center of each cluster;
(3) until the cluster center is no longer changed.
And 4, step 4: and (4) clustering each pixel point by using an initial clustering center, continuously iterating and replacing the clustering center in the step (3) until iteration is stopped, and realizing image classification according to a clustering result.
In a specific embodiment, the image recognition method further includes: the target pattern is enhanced using the CLAHE algorithm. The CLAHE algorithm is adopted for the input image, the image contrast is enhanced, and the details are highlighted;
in the examples of the present invention, there are 3 most obvious features in CLAHE: (1) dividing a small interval in an original image, and then carrying out histogram equalization processing on the small interval; (2) carrying out contrast limitation on the image to reduce the noise enhancement in the AHE; (3) the operation efficiency is further improved by the difference operation. The specific process of histogram equalization is as follows:
(1) determining the gray level of an original image;
(2) calculating the distribution probability of the original histogram;
(3) calculating a histogram probability accumulated value;
(4) and calculating the pixel mapping relation, wherein ss (i) is the gray level in the equalized image corresponding to the ith gray level.
ss(i)＝int{[max(pix)-min(pix)]sk+0.5}
From the above description, it can be known that the image recognition method provided by the present application can adopt the CLAHE algorithm and the OTSU algorithm in the image segmentation method of the present invention to perform image preprocessing, so as to further enhance local detail features and avoid noise amplification, use the watershed transform algorithm to segment an image to be determined, and then use the K-means algorithm to classify the segmented image, so as to accurately obtain a target image, thereby accurately recognizing the image.
Based on the convenience of fast and convenient reimbursement of the bank card, improvement of the working efficiency of bank workers and improvement of user experience, the application provides an embodiment of a user certificate reimbursement method based on image recognition, which is shown in fig. 11 and includes:
step S501: acquiring a subsidy request of a user subsidy user certificate and a gray image input by the user; the gray image comprises a target body pattern and a background pattern;
step S502: according to the distance information of each pixel point in the target body gray image and the corresponding zero-value pixel point, combining the gray difference data of each pixel point and the target body pattern pixel and the background pattern pixel, and segmenting the target body gray image to obtain a target body pattern;
step S503: identifying whether the target volume pattern is a fingerprint pattern;
step S504: and if the fingerprint pattern is the reserved fingerprint pattern with the same texture as the fingerprint pattern, allowing the user to make a request.
The method comprises the steps of obtaining an image to be segmented, preprocessing the image to be segmented by using the pattern to be identified in the image as a target pattern and using the rest as background patterns, and converting the image to be segmented into a gray image; comprehensively utilizing the distance between each pixel point and the pixel point closest to the zero value and the gray level difference between each pixel point and the target and the background to judge the attribute of the pixel point, wherein the attribute comprises the target pixel and the background pixel, so as to realize image segmentation; then the fingerprint is identified, so that the identification fingerprint and the fingerprint information acquired by card transaction for the first time are matched with the identity of the card owner, the user certificate is conveniently and quickly repaired, the working efficiency of workers is improved, and the user experience is improved.
In some embodiments, the user credential reprocessing method based on image recognition provided by the application may use a CLAHE algorithm and an OTSU algorithm to perform image preprocessing, so as to further enhance local detail features and avoid noise amplification, use a watershed transform algorithm to segment an image to be determined, and use a K-means algorithm to classify fingerprint segmentation images, which is not described in detail herein.
In terms of software, in order to solve the problem of low accuracy of image recognition at present, referring to fig. 12, the present application provides an image segmentation system, including:
the image acquisition module 11 is used for acquiring a gray image of an image to be segmented; the image to be segmented comprises a target pattern and a background pattern;
and the image segmentation module 12 is configured to segment the grayscale image to obtain a target volume pattern according to distance information between each pixel point in the grayscale image and a corresponding zero-value pixel point, and by combining grayscale difference data between each pixel point and a target volume pattern pixel and a background pattern pixel.
The image to be segmented is preprocessed by the image acquisition module, and the image to be segmented is converted into a gray scale image, wherein the pattern to be identified in the image is a target pattern, and the rest of the patterns are background patterns; the image segmentation module comprehensively utilizes the distance between each pixel point and the pixel point closest to the zero value and the gray difference between each pixel point and the target and the background to judge the attribute of the pixel point, wherein the attribute comprises the target pixel and the background pixel, so that the image segmentation is realized.
Based on the same inventive concept, in some embodiments, the method further comprises:
the set threshold generating module is used for generating a set threshold according to the gray data of all pixel points in the gray image;
the binarization processing module is used for carrying out binarization processing on each pixel point of the gray level image according to the set threshold value to obtain a binarization image;
the target position information determining module is used for determining pixel point position information corresponding to the target body pixel value in the binary image;
and the initial target body pattern generating module is used for extracting pixel points at corresponding positions from the gray level image according to the determined pixel point position information to generate an initial target body pattern.
Based on the same inventive concept, in some embodiments, the image segmentation module includes:
the brightness image generating unit generates a brightness image corresponding to the gray image according to the distance information corresponding to each pixel point and by combining the corresponding relation between the distance information and the brightness value;
the contour marking unit is used for marking the contour of the target body by combining the gray difference data of each pixel point, the pattern pixel of the target body and the background pattern pixel according to the brightness image;
and the target body pattern segmentation unit is used for segmenting a target body pattern correspondingly limited by the target body outline from the gray level image.
Based on the same inventive concept, in some embodiments, the image segmentation module includes:
the luminance image generating unit is used for generating a luminance pattern corresponding to the initial target body pattern according to the distance information corresponding to each pixel point in the initial target body pattern and the corresponding relation between the distance information and the luminance value;
the target body contour updating unit is used for obtaining an updated target body contour by combining the gray difference data marks of each pixel point, the target body pattern pixel and the background pattern pixel according to the brightness pattern;
and the target body pattern segmentation unit is used for segmenting the target body pattern correspondingly limited by the updated target body outline from the initial target body pattern.
Based on the same inventive concept, in some embodiments, the object is a fingerprint, and the image segmentation system further comprises at least one of the following modules:
the pixel point removing module is used for removing pixel points with the pixel area smaller than a set value in the gray level image based on the fingerprint standard form;
the convolution module is used for utilizing a convolution kernel to carry out image convolution operation based on the USM algorithm;
and the boundary removing module is used for scanning the gray level image point by point based on eight neighborhood chain codes, searching for boundaries and removing the boundaries lower than the thresholds by utilizing the thresholds.
Based on the same inventive concept, in some embodiments, the setting threshold generating module includes:
the average gray level generation unit is used for obtaining the average gray level of the target pixel point and the average gray level of the background pixel point according to the gray level data of all the pixel points in the gray level image;
and the set threshold generating unit is used for calculating the inter-class variance according to the ratio of the number of target pixels to the number of gray image pixels, the average gray of the target pixels, the ratio of the number of background pixels to the number of gray image pixels and the average gray of the background pixels to obtain the set threshold.
Based on the same inventive concept, in some embodiments, the outline marking unit includes:
the pixel point type determining unit is used for obtaining the type of each pixel point by combining the gray difference data of each pixel point, the target pattern pixel and the background pattern pixel according to the brightness image, wherein the type of each pixel point comprises the background pixel and the target pixel;
and the marking unit is used for marking the pixel points corresponding to the target pixels to form a target body outline.
The present application provides an image recognition system, see fig. 13, comprising:
the image acquisition module 21 is used for acquiring a gray image of an image to be segmented; the image to be segmented comprises a target pattern and a background pattern;
the image segmentation module 22 is configured to segment the grayscale image to obtain a target volume pattern according to distance information between each pixel point in the grayscale image and a corresponding zero-value pixel point, and by combining grayscale difference data between each pixel point and a target volume pattern pixel and a background pattern pixel;
and the image identification module 23 is used for identifying the target body pattern divided by the image division method.
It can be understood that, the image acquisition module acquires an image to be segmented, the pattern to be identified in the image is a target pattern, the rest are background patterns, the image to be segmented is preprocessed, and the image to be segmented is converted into a gray scale image; the image segmentation module comprehensively utilizes the distance between each pixel point and the pixel point closest to the zero value and the gray difference between each pixel point and the target and the background to judge the attribute of the pixel point, wherein the attribute comprises the target pixel and the background pixel, so that the image segmentation is realized; and the image identification module identifies the segmented target body pattern by adopting a K-means algorithm.
In some specific embodiments, referring to fig. 14, the image recognition system further comprises:
the threshold calculation module 25 generates a set threshold according to the gray data of all the pixel points in the gray image;
a binarization processing module 26, configured to perform binarization processing on the grayscale image according to the set threshold value to obtain a binarized image;
an object extraction module 27, which extracts the contour pattern of the object in the gray level image according to the binary image;
and the initial segmentation module 28 is used for screening the outline pattern according to the set threshold value to obtain an initial target body pattern.
It can be understood that the gray level image obtained by the threshold value calculation module is subjected to binarization processing by adopting an OTSU algorithm, a threshold value is set, and the pixel value of the image is adjusted according to the threshold value, so as to provide conditions for subsequently searching pixel point coordinates meeting the conditions; the binarization processing module is used for carrying out binarization processing on the gray level image to obtain a binarization image; the target body extraction module compares the gray value of the gray image pixel with a set threshold value, screens out pixel point coordinates meeting conditions, marks the pixel point coordinates meeting the conditions on the fingerprint image, and the initial segmentation module segments the pixel point coordinates according to the marks to obtain an initial target pattern, wherein the fingerprint image is taken as an example, and the image processing flow is shown in fig. 15.
The present application provides a bank card reissuing system based on image recognition, as shown in fig. 17, including:
the image acquisition module 31 is used for acquiring a subsidy request of a user subsidy user certificate and a gray image input by the user; the gray image comprises a target body pattern and a background pattern;
the image segmentation module 32 is used for segmenting the target body gray level image to obtain a target body pattern according to the distance information between each pixel point in the target body gray level image and the corresponding zero-value pixel point and by combining the gray level difference data between each pixel point and the target body pattern pixel and the background pattern pixel;
an image recognition module 33 for recognizing whether the target pattern is a fingerprint pattern;
and if the reserved fingerprint pattern with the same grain as the fingerprint pattern exists in the database, the permission module 34 permits the user to make a request.
The image to be segmented is preprocessed by the image acquisition module, and the image to be segmented is converted into a gray scale image, wherein the pattern to be identified in the image is a target pattern, and the rest of the patterns are background patterns; the image segmentation module comprehensively utilizes the distance between each pixel point and the pixel point closest to the zero value and the gray difference between each pixel point and the target and the background to judge the attribute of the pixel point, wherein the attribute comprises the target pixel and the background pixel, so that the image segmentation is realized; the image recognition module adopts a K-means algorithm to recognize fingerprints, and fast matching is carried out from a fingerprint library, so that identity of a user can be fast verified, and user certificates including but not limited to savings cards and credit cards can be complemented.
From the above description, it can be seen that the image recognition-based user certificate reprocessing system provided by the application, as shown in fig. 16, performs image preprocessing by reading a client fingerprint and adopting the CLAHE algorithm and the OTSU algorithm, so that local detail features are further enhanced, noise amplification is avoided, a watershed transform algorithm is used to segment an image to be determined, and then a K-means algorithm is used to classify the fingerprint segmented image, so that the recognition fingerprint and fingerprint information acquired by card handling for the first time are matched with the identity of a card owner, the user certificate is reprocessed conveniently and quickly, the working efficiency of workers is improved, and the user experience is improved.
In terms of hardware, in order to solve the problem of low accuracy of the existing image recognition, the present application provides an embodiment of an electronic device for implementing all or part of the contents in the image segmentation method, where the electronic device specifically includes the following contents:
fig. 18 is a schematic block diagram of a system configuration of an electronic device 9600 according to an embodiment of the present application. As shown in fig. 18, the electronic device 9600 can include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. Notably, this fig. 18 is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.
In one embodiment, the image recognition function may be integrated into the central processor. Wherein the central processor may be configured to control:
step S100: acquiring a gray level image of an image to be segmented; the image to be segmented comprises a target pattern and a background pattern;
step S200: and according to the distance information of each pixel point in the gray image and the corresponding zero-value pixel point, combining the gray difference data of each pixel point and the target pattern pixel and the background pattern pixel, and segmenting the gray image to obtain the target pattern.
The method comprises the steps of obtaining an image to be segmented, preprocessing the image to be segmented by using the pattern to be identified in the image as a target pattern and using the rest as background patterns, and converting the image to be segmented into a gray image; and comprehensively utilizing the distance between each pixel point and the pixel point closest to the zero value and the gray difference between each pixel point and the target and the background to judge the attribute of the pixel point, wherein the attribute comprises the target pixel and the background pixel, so as to realize image segmentation.
In another embodiment, the image recognition system may be configured separately from the central processor 9100, for example, the image recognition system may be configured as a chip connected to the central processor 9100, and the image recognition function is realized by the control of the central processor.
As shown in fig. 18, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is noted that the electronic device 9600 also does not necessarily include all of the components shown in fig. 18; further, the electronic device 9600 may further include a component not shown in fig. 18, and reference may be made to the related art.
As shown in fig. 18, a central processor 9100, sometimes referred to as a controller or operational control, can include a microprocessor or other processor device and/or logic device, which central processor 9100 receives input and controls the operation of the various components of the electronic device 9600.
The memory 9140 can be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 9100 can execute the program stored in the memory 9140 to realize information storage or processing, or the like.
The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. Power supply 9170 is used to provide power to electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, an LCD display, but is not limited thereto.
The memory 9140 can be a solid state memory, e.g., Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 9140 could also be some other type of device. Memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 being used for storing application programs and function programs or for executing a flow of operations of the electronic device 9600 by the central processor 9100.
The memory 9140 can also include a data store 9143, the data store 9143 being used to store data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. The driver storage portion 9144 of the memory 9140 may include various drivers for the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, contact book applications, etc.).
The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. The communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in the case of a conventional mobile communication terminal.
Embodiments of the present application further provide a computer-readable storage medium capable of implementing all steps in the image recognition method in the foregoing embodiments, where the computer-readable storage medium stores thereon a computer program, and when the computer program is executed by a processor, the computer program implements all steps of the image recognition method in the foregoing embodiments, where the execution subject is a server or a client, for example, when the processor executes the computer program, the processor implements the following steps:
step S100: acquiring a gray level image of an image to be segmented; the image to be segmented comprises a target pattern and a background pattern;
step S200: and according to the distance information of each pixel point in the gray image and the corresponding zero-value pixel point, combining the gray difference data of each pixel point and the target pattern pixel and the background pattern pixel, and segmenting the gray image to obtain the target pattern.
The method comprises the steps of obtaining an image to be segmented, preprocessing the image to be segmented by using the pattern to be identified in the image as a target pattern and using the rest as background patterns, and converting the image to be segmented into a gray image; and comprehensively utilizing the distance between each pixel point and the pixel point closest to the zero value and the gray difference between each pixel point and the target and the background to judge the attribute of the pixel point, wherein the attribute comprises the target pixel and the background pixel, so as to realize image segmentation.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principle and the embodiment of the present invention are explained by applying the specific embodiment in the present invention, and the above description of the embodiment is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (15)
1. An image segmentation method, comprising:
acquiring a gray level image of an image to be segmented; the image to be segmented comprises a target pattern and a background pattern;
and according to the distance information of each pixel point in the gray image and the corresponding zero-value pixel point, combining the gray difference data of each pixel point and the target pattern pixel and the background pattern pixel, and segmenting the gray image to obtain the target pattern.
2. The image segmentation method according to claim 1, wherein the image recognition method further comprises:
generating a set threshold according to the gray data of all pixel points in the gray image;
performing binarization processing on each pixel point of the gray level image according to the set threshold value to obtain a binarized image;
determining pixel point position information corresponding to the target body pixel value in the binary image;
and according to the determined pixel point position information, extracting pixel points at corresponding positions from the gray level image to generate an initial target body pattern.
3. The image segmentation method according to claim 1, wherein the segmenting the grayscale image into the target volume pattern according to the distance information between each pixel point and the corresponding zero-valued pixel point and by combining grayscale difference data between each pixel point and the target volume pattern pixel and the background pattern pixel comprises:
generating a brightness image corresponding to the gray image according to the distance information corresponding to each pixel point and by combining the corresponding relation between the distance information and the brightness value;
marking the contour of the target body by combining the gray difference data of each pixel point and the pattern pixel of the target body and the background pattern pixel according to the brightness image;
and segmenting a target body pattern correspondingly defined by the target body outline from the gray level image.
4. The image segmentation method according to claim 2, wherein the segmenting the grayscale image into the target volume pattern according to the distance information between each pixel point and the corresponding zero-valued pixel point and by combining grayscale difference data between each pixel point and the target volume pattern pixel and the background pattern pixel comprises:
generating a brightness pattern corresponding to the initial target body pattern according to the distance information corresponding to each pixel point in the initial target body pattern and by combining the corresponding relation between the distance information and the brightness value;
according to the brightness pattern, combining the gray difference data marks of each pixel point, the target pattern pixel and the background pattern pixel to obtain an updated target body outline;
segmenting the target volume pattern correspondingly defined by the updated target volume profile from the initial target volume pattern.
5. The image segmentation method according to claim 4, wherein the target is a fingerprint, and the step of segmenting the gray-scale image into the target pattern is performed before generating the luminance pattern corresponding to the initial target pattern, further comprises at least one of the following steps:
based on a fingerprint standard form, removing pixel points with pixel areas smaller than a set value in the gray level image;
utilizing a convolution kernel to carry out image convolution operation based on a USM algorithm;
and scanning the gray level image point by point based on eight neighborhood chain codes, searching for boundaries, and removing the boundaries lower than the thresholds by utilizing a plurality of thresholds.
6. The image segmentation method according to claim 2, wherein the generating a set threshold value according to the gray data of all the pixels in the gray image comprises:
obtaining the average gray of a target pixel point and the average gray of a background pixel point according to the gray data of all pixel points in the gray image;
and calculating the inter-class variance according to the ratio of the number of the target pixel points to the number of the gray image pixel points, the average gray level of the target pixel points, the ratio of the number of the background pixel points to the number of the gray image pixel points and the average gray level of the background pixel points to obtain the set threshold.
7. The image segmentation method according to claim 3 or 4, wherein the labeling of the target volume contour according to the luminance image by combining the gray scale difference data of each pixel point with the target volume pattern pixel and the background pattern pixel comprises:
obtaining the type of each pixel point by combining the gray difference data of each pixel point, the target pattern pixel and the background pattern pixel according to the brightness image, wherein the types of the pixel points comprise the background pixel and the target pixel;
and marking the pixel points corresponding to the target pixels to form the target body outline.
8. An image recognition method, comprising the image segmentation method according to any one of claims 1 to 7, and
and identifying the target body pattern segmented by the image segmentation method.
9. The image recognition method according to claim 8, wherein the recognizing the target volume pattern divided by the image division method includes:
determining a plurality of initial clustering centers according to the gray level image;
executing iteration operation, distributing each pixel point to a corresponding initial clustering center according to the similarity of each pixel point and each initial clustering center to form a plurality of clusters, recalculating the clustering center of each cluster to obtain a corresponding updated clustering center, and redistributing each pixel point to each updated clustering center based on the similarity until each updated clustering center is kept unchanged to obtain a plurality of final clusters;
identifying the target volume pattern from the final plurality of clusters.
10. A user certificate reprocessing method based on image recognition is characterized by comprising the following steps:
acquiring a subsidy request of a user subsidy user certificate and a gray image input by the user; the gray image comprises a target body pattern and a background pattern;
according to the distance information of each pixel point in the target body gray image and the corresponding zero-value pixel point, combining the gray difference data of each pixel point and the target body pattern pixel and the background pattern pixel, and segmenting the target body gray image to obtain a target body pattern;
identifying whether the target volume pattern is a fingerprint pattern;
and if the fingerprint pattern is the reserved fingerprint pattern with the same texture as the fingerprint pattern, allowing the user to make a request.
11. An image segmentation system, comprising:
the image acquisition module is used for acquiring a gray image of an image to be segmented; the image to be segmented comprises a target pattern and a background pattern;
and the image segmentation module is used for segmenting the gray image to obtain a target body pattern by combining the gray difference data of each pixel point and the target body pattern pixel and the background pattern pixel according to the distance information of each pixel point in the gray image and the corresponding zero-value pixel point.
12. An image recognition system, comprising:
the image acquisition module is used for acquiring a gray image of an image to be segmented; the image to be segmented comprises a target pattern and a background pattern;
the image segmentation module is used for segmenting the gray image to obtain a target body pattern by combining gray difference data of each pixel point and a target body pattern pixel and a background pattern pixel according to the distance information of each pixel point in the gray image and a corresponding zero-value pixel point;
and the image identification module is used for identifying the target body pattern segmented by the image segmentation method.
13. A user credential reprocessing system based on image recognition, comprising:
the image acquisition module is used for acquiring a subsidy request of a user subsidy user certificate and a gray image input by the user; the gray image comprises a target body pattern and a background pattern;
the image segmentation module is used for segmenting the target body gray image to obtain a target body pattern by combining gray difference data of each pixel point and a target body pattern pixel and a background pattern pixel according to distance information of each pixel point in the target body gray image and a corresponding zero-value pixel point;
the image identification module is used for identifying whether the target body pattern is a fingerprint pattern;
and if the reserved fingerprint pattern with the same grain as the fingerprint pattern exists in the database, the permission module permits the user to make a request.
14. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 10 when executing the program.
15. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210158194.2A CN114529570A (en) | 2022-02-21 | 2022-02-21 | Image segmentation method, image identification method, user certificate subsidizing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210158194.2A CN114529570A (en) | 2022-02-21 | 2022-02-21 | Image segmentation method, image identification method, user certificate subsidizing method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114529570A true CN114529570A (en) | 2022-05-24 |
Family
ID=81625786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210158194.2A Pending CN114529570A (en) | 2022-02-21 | 2022-02-21 | Image segmentation method, image identification method, user certificate subsidizing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114529570A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115564689A (en) * | 2022-10-08 | 2023-01-03 | 上海宇勘科技有限公司 | Artificial intelligence image processing method and system based on block processing technology |
-
2022
- 2022-02-21 CN CN202210158194.2A patent/CN114529570A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115564689A (en) * | 2022-10-08 | 2023-01-03 | 上海宇勘科技有限公司 | Artificial intelligence image processing method and system based on block processing technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110414507B (en) | License plate recognition method and device, computer equipment and storage medium | |
| US9971929B2 (en) | Fingerprint classification system and method using regular expression machines | |
| CN109859227B (en) | Method and device for detecting flip image, computer equipment and storage medium | |
| CN110838126B (en) | Cell image segmentation method, cell image segmentation device, computer equipment and storage medium | |
| CN109492642B (en) | License plate recognition method, license plate recognition device, computer equipment and storage medium | |
| CN109241973B (en) | Full-automatic soft segmentation method for characters under texture background | |
| CN108197644A (en) | A kind of image-recognizing method and device | |
| CN111986183B (en) | Chromosome scattered image automatic segmentation and identification system and device | |
| CN116403094B (en) | Embedded image recognition method and system | |
| CN110503682B (en) | Rectangular control identification method and device, terminal and storage medium | |
| US20170178341A1 (en) | Single Parameter Segmentation of Images | |
| CN113177899A (en) | Method for correcting text tilt of medical photocopy, electronic device and readable storage medium | |
| CN112419207A (en) | Image correction method, device and system | |
| CN114298985B (en) | Defect detection method, device, equipment and storage medium | |
| CN114529570A (en) | Image segmentation method, image identification method, user certificate subsidizing method and system | |
| CN117115117B (en) | Pathological image recognition method based on small sample, electronic equipment and storage medium | |
| CN112258532B (en) | Positioning and segmentation method for callus in ultrasonic image | |
| Chen et al. | Image segmentation based on mathematical morphological operator | |
| CN111898408B (en) | Quick face recognition method and device | |
| CN111199228B (en) | License plate positioning method and device | |
| CN112818983A (en) | Method for judging character inversion by using picture acquaintance | |
| CN111986176B (en) | Crack image identification method, system, terminal and readable storage medium | |
| CN112183229B (en) | Word lattice extraction method and device of operation paper image based on calculation dynamic parameters | |
| CN111753723B (en) | Fingerprint identification method and device based on density calibration | |
| CN114241463A (en) | Signature verification method and device, computer equipment and storage medium |
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 |