CN111667479A - Pattern verification method and device for target image, electronic device and storage medium - Google Patents

Pattern verification method and device for target image, electronic device and storage medium Download PDF

Info

Publication number
CN111667479A
CN111667479A CN202010526093.7A CN202010526093A CN111667479A CN 111667479 A CN111667479 A CN 111667479A CN 202010526093 A CN202010526093 A CN 202010526093A CN 111667479 A CN111667479 A CN 111667479A
Authority
CN
China
Prior art keywords
image
position information
target image
verification
template
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
Application number
CN202010526093.7A
Other languages
Chinese (zh)
Inventor
艾国
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Innovation Qizhi Chengdu Technology Co ltd
Original Assignee
Innovation Qizhi Chengdu Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Innovation Qizhi Chengdu Technology Co ltd filed Critical Innovation Qizhi Chengdu Technology Co ltd
Priority to CN202010526093.7A priority Critical patent/CN111667479A/en
Publication of CN111667479A publication Critical patent/CN111667479A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T7/001—Industrial image inspection using an image reference approach
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformation in the plane of the image
    • G06T3/60—Rotation of a whole image or part thereof
    • 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
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • 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
    • G06V10/24—Aligning, centring, orientation detection or correction of the image
    • G06V10/242—Aligning, centring, orientation detection or correction of the image by image rotation, e.g. by 90 degrees
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30124—Fabrics; Textile; Paper

Abstract

The application provides a pattern verification method and device of a target image, electronic equipment and a computer readable storage medium, wherein the method comprises the following steps: detecting the coordinates of key points in a target image; calculating a rotation matrix according to the key point coordinates and key point coordinates in a preset template image; carrying out rotation transformation on the target image according to the rotation matrix to obtain a corrected image; acquiring a correction sub-image corresponding to the pattern position information from the correction image based on the pattern position information in the template image; and judging whether the corrected subimage is matched with the image to be checked corresponding to the pattern position information in the template image or not, and outputting a checking result. The embodiment of the application is completed by a machine, so that the labor cost is reduced, and the verification efficiency is improved.

Description

Pattern verification method and device for target image, electronic device and storage medium
Technical Field
The present disclosure relates to the field of image processing technologies, and in particular, to a method and an apparatus for pattern verification of a target image, an electronic device, and a computer-readable storage medium.
Background
In the process of detecting ready-made clothes, the patterns on the clothes need to be checked, and the clothes are ensured to be printed with the originally designed patterns at the specified positions. The designs printed on the garment typically include printed designs, iron logos, and the like. At present, the patterns on the clothing are checked manually. This approach is inefficient and costly.
Disclosure of Invention
An embodiment of the present application provides a pattern verification method and apparatus for a target image, an electronic device, and a computer-readable storage medium, so as to solve the problems of high cost and low efficiency in manual pattern verification.
In one aspect, the present application provides a pattern verification method for a target image, including:
detecting the coordinates of key points in a target image;
calculating a rotation matrix according to the key point coordinates and key point coordinates in a preset template image;
carrying out rotation transformation on the target image according to the rotation matrix to obtain a corrected image;
acquiring a correction sub-image corresponding to the pattern position information from the correction image based on the pattern position information in the template image;
and judging whether the corrected subimage is matched with the image to be checked corresponding to the pattern position information in the template image or not, and outputting a checking result.
In one embodiment, the detecting the coordinates of the key points in the target image further includes:
and taking the target image as the input of a trained deep learning model to obtain the key point coordinates of the target image.
In an embodiment, prior to calculating the rotation matrix, the method further comprises:
and searching the template image corresponding to the verification identification based on the verification identification of the target image.
In an embodiment, before searching for the template image corresponding to the verification identifier, the method further includes:
and receiving the verification identification and the template image, and establishing a mapping relation between the verification identification and the template image.
In an embodiment, before the calculating a rotation matrix according to the key point coordinates and key point coordinates in a preset template image, the method further includes:
and taking the template image as the input of a trained deep learning model to obtain the key point coordinates of the template image.
In an embodiment, before the acquiring a corrected sub-image corresponding to the pattern position information from the corrected image based on the pattern position information in the template image, the method further includes:
acquiring pattern position information marked on the template image;
and storing the key point coordinates corresponding to the template image and the pattern position information in a correlation manner.
In an embodiment, the determining whether the correction sub-image matches the image to be verified corresponding to the pattern position information in the template image includes:
calculating the similarity between the correction sub-image and the image to be checked based on a similarity calculation method;
judging whether the similarity is greater than a preset similarity threshold value or not;
if yes, determining that the syndrome image is matched with the image to be checked;
and if not, determining that the syndrome image is not matched with the image to be checked.
In another aspect, the present application further provides a pattern verification apparatus for a target image, including:
the detection module is used for detecting the coordinates of the key points in the target image;
the calculation module is used for calculating a rotation matrix according to the key point coordinates and key point coordinates in a preset template image;
the rotation module is used for performing rotation transformation on the target image according to the rotation matrix to obtain a corrected image;
the acquisition module is used for acquiring a correction sub-image corresponding to the pattern position information from the correction image based on the pattern position information in a preset template image;
and the verification module is used for judging whether the corrected subimage is matched with the image to be verified corresponding to the pattern position information in the template image or not and outputting a verification result.
Further, the present application also provides an electronic device, including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to perform the pattern verification method of the target image.
In addition, the present application also provides a computer-readable storage medium storing a computer program executable by a processor to perform the above-described pattern verification method for a target image.
In the embodiment of the application, a rotation matrix is calculated based on the detected key point coordinates and the key point coordinates in the template image, a correction subimage is obtained from a correction image obtained by rotation after the target image is rotated according to the rotation matrix, and the checking work of the target image is completed by judging whether the correction subimage is matched with an image to be checked in the template image; the whole process is completed by a machine, so that the labor cost is reduced, and the checking efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments of the present application will be briefly described below.
Fig. 1 is a schematic view of an application scenario of a pattern verification method for a target image according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
fig. 3 is a schematic flowchart of a pattern verification method for a target image according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a target image provided in an embodiment of the present application;
FIG. 5 is a schematic diagram of a template image provided in accordance with an embodiment of the present application;
fig. 6 is a block diagram of a pattern verification apparatus for a target image according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
Like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
Fig. 1 is a schematic view of an application scenario of a pattern verification method of an apparatus according to an embodiment of the present application. As shown in fig. 1, the application scenario includes a server 30 and a client 20, where the client 20 may be a camera for collecting a target image and may transmit the target image to the server 30, the server 30 may be a server, a server cluster, or a cloud computing center, and the server 30 may perform a pattern verification service on the target image uploaded by the client 20.
As shown in fig. 2, the present embodiment provides an electronic apparatus 1 including: at least one processor 11 and a memory 12, one processor 11 being exemplified in fig. 2. The processor 11 and the memory 12 are connected by a bus 10, and the memory 12 stores instructions executable by the processor 11, and the instructions are executed by the processor 11, so that the electronic device 1 can execute all or part of the flow of the method in the embodiments described below. In an embodiment, the electronic device 1 may be the server 30.
The Memory 12 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk.
The present application also provides a computer readable storage medium storing a computer program executable by a processor 11 to perform the pattern verification method for a target image provided by the present application.
Referring to fig. 3, a flow chart of a pattern verification method provided in an embodiment of the present application is shown in fig. 4, and the method may include the following steps 310 to 350.
Step 310: and detecting the coordinates of the key points in the target image.
The target image is an image subjected to pattern verification, and an object to be identified exists in the target image. The server may obtain the target image from the client. Such as: the client side is a camera on a production line of a clothing factory, shoots clothes on the production line, and uploads a shot target image to the server side.
The key points refer to identification points of key portions of the object to be recognized in the target image. In one embodiment, if the object to be recognized is a garment, the key points may include positions of left shoulder, right shoulder, left cuff, right cuff, left bottom, right bottom, and the like. The keypoint coordinates refer to Pixel coordinates (Pixel coordinates) of the keypoint in the image Coordinate system.
In one embodiment, the server may detect the coordinates of the key points in the target image through an image processing technique based on deep learning.
In one embodiment, the server may train the deep learning model through the labeled sample images. Wherein the label of the sample image is a heat map (heatmap) generated based on the coordinates of the key points in the sample image. The heat map is the same size as the sample image, with each pixel point in the heat map corresponding to a pixel point in the sample image. Each heat map corresponds to a key point, the value of the pixel point corresponding to the key point in the heat map is 1, and the values of the pixel points at the other positions are 0.
The deep learning model may be any one of CPN (Cascaded Pyramid Network), HRNet (High Resolution Network), and MSPN (Multi-Stage Network).
And adjusting the network parameters of the deep learning model according to the difference between the heat map calculated by the deep learning model for the sample image and the heat map in the label. This process is repeated until the deep learning model converges.
The server can take the target image as the input of the trained deep learning model to obtain the key point coordinates of the target image.
When the size of the input target image is W × H and K key points need to be detected, the deep learning model may output K heatmaps with the size of W × H. The server can determine the coordinates of each key point through the heat map.
Step 320: and calculating a rotation matrix according to the key point coordinates and the key point coordinates in the preset template image.
The template image refers to an image when the placing position and the posture of the object to be recognized are correct. In an embodiment, before performing step 320, the server may use the template image as an input of the trained deep learning model, so as to obtain the key point coordinates of the template image.
When the object to be recognized in the target image has a deviation or rotation, whether the pattern to be verified exists on the object to be recognized cannot be verified accurately. Therefore, by calculating a rotation matrix for rotating the transformation target image, the position and orientation of the object to be recognized are corrected.
If K key points are preset, the coordinates of the K key points can be respectively expressed as (x)1，y1)、(x2，y2)、(x3，y3)……(xk，yk) (ii) a Key points in template imagesThe coordinates may be expressed as (x'1，y’1)、(x’2，y’2)、(x’3，y’3)……(x’k，y’k)。
Wherein, the key point coordinate (x)i，yi) The corresponding keypoint coordinate in the template image is (x'i，y’i)。
The server side can generate a key point coordinate matrix with the size of 3 x K based on the detected key point coordinates, and the key point coordinate matrix can be expressed as
Figure BDA0002532167920000081
The server generates a template key point coordinate matrix with the size of 3 x K based on the key point coordinates in the template image, and the template key point coordinate matrix can be expressed as
Figure BDA0002532167920000082
The relationship between the keypoint coordinate matrix and the template keypoint coordinate matrix can be represented by the following equation (1):
Figure BDA0002532167920000083
wherein the content of the first and second substances,
Figure BDA0002532167920000084
representing a rotation matrix; theta is the angle by which the target image needs to be rotated, tx is the amount of translation of the target image in the X-axis direction, and ty is the amount of translation of the target image in the Y-axis direction.
The server side can calculate the rotation matrix through the key point coordinate matrix and the template key point coordinate matrix.
Step 330: and carrying out rotation transformation on the target image according to the rotation matrix to obtain a corrected image.
The corrected image refers to an image obtained by rotating and converting a target image, and the placement position and the posture of an object to be recognized in the corrected image are correct. And the rotation transformation of the target image is realized by multiplying the rotation matrix by a matrix formed by coordinates of each pixel point of the target image.
The server side can utilize the rotation matrix to carry out rotation transformation on each pixel point in the target image. The coordinates of any pixel point in the target image can be expressed as (x)a，yb) And representing the pixel points of the a-th row and the b-th column in the target image. The pixel coordinate after the pixel rotation is expressed as (x ') in the current coordinate system'a，y’b). The new pixel coordinates can be calculated by the following formula (2).
Figure BDA0002532167920000091
Wherein the content of the first and second substances,
Figure BDA0002532167920000092
a rotation matrix is represented.
In the image coordinate system, the abscissa or the ordinate of any pixel is an integer. If the calculated coordinates have decimal, the decimal in the coordinates can be adjusted to be an integer, so that the coordinates are adjusted to be the closest pixel point coordinates.
After the pixel point coordinates of all the pixel points after rotation are obtained, the server side can screen out the pixel points in the area where the target image is located, and 0 is filled in other positions in the area where the target image is located, so that a corrected image is obtained. In one embodiment, if the image coordinate system is from the top left of the target image, the coordinates (x) are passed through the bottom right of the target imager，yr) The region in which the target image is located may be determined. After the server side obtains the rotated pixel point coordinates, coordinates (0, 0) at the upper left corner and coordinates (x) at the lower right corner are screened outr，yr) And indicating the pixel points in the rectangular frame, and filling 0 in the pixel point coordinates of the pixel points which do not have the pixel points in the rectangular frame, so that the image in the rectangular frame can be used as a correction image.
Step 340: and acquiring a correction sub-image corresponding to the pattern position information from the correction image based on the pattern position information in the template image.
The pattern position information is a position of the pattern to be checked in the template image, and the pattern position information may be represented by a peripheral rectangular frame of the pattern to be checked, for example, the upper left corner coordinate and the lower right corner coordinate of the peripheral rectangular frame. In one embodiment, the pattern position information may be annotated. The corrected sub-image is a partial image corresponding to pattern position information cut out from the corrected image.
Step 350: and judging whether the corrected subimage is matched with the image to be checked corresponding to the pattern position information in the template image or not, and outputting a checking result.
The image to be checked is an image which contains the pattern to be checked and has the same size as the peripheral rectangular frame indicated by the pattern position information. The pattern to be verified refers to a pattern which needs to be judged whether the target image exists in the pattern verification process. In one embodiment, if the object to be identified is a garment, the pattern to be verified may be a printed pattern or a hot stamp on the garment.
And the verification result represents whether the pattern to be verified exists in the target image. Matching means that the syndrome image and the image to be verified are substantially identical, and in one embodiment, if the similarity between the syndrome image and the image to be verified is greater than a threshold, it can be determined that the two match.
Referring to fig. 4, a schematic diagram of a target image according to an embodiment of the present application is provided. The object to be recognized in the target image 60 in fig. 4 is a garment, and the key points are a, b, c, d, e, and f in the figure.
Referring to fig. 5, a schematic diagram of a template image according to an embodiment of the present application is provided. The template image 70 in fig. 5 is the template image corresponding to the target image 60 in fig. 4, and the key points in the template image are a ', b', c ', d', e ', f' in the figure. Within the dashed box 71 is the image to be verified in the template image, and the flower font "SPORTS" is the pattern to be verified.
In the pattern verification process, the server detects the coordinates of the key points (a, b, c, d, e, f) in the target image 60, calculates a rotation matrix based on the coordinates of the key points (a ', b', c ', d', e ', f') of the template image 70, and performs rotation transformation on the target image 60, so as to transform the target image 60 into a standard position corresponding to the template image, and obtain a corrected image. Thereafter, a correction sub-image (i.e., an image within the dashed-line frame 61) can be extracted from the target image 60 based on the pattern position information in the preset template image. Then, whether the image to be checked (i.e. the image in the dashed line frame 71) in the preset template image is consistent with the corrected sub-image (i.e. the image in the dashed line frame 61) is judged, and if so, the garment can be considered to be printed with a correct pattern or a hot mark.
In an embodiment, the server may cut the image to be checked from the template image based on the pattern position information, and calculate the similarity between the corrected sub-image and the image to be checked by a similarity calculation method. The Similarity calculation method may be any one of SSIM (Structural Similarity Index) algorithm, PSNR (Peak Signal to noise Ratio) algorithm, MSE (mean square error), and the like.
And the server side judges whether the calculated similarity is greater than a preset similarity threshold value. The similarity threshold may be an empirical value for determining whether the correction sub-image is sufficiently similar to the image to be checked.
On one hand, if the similarity is larger than the similarity threshold, the correction sub-image is matched with the image to be checked. At this time, the pattern to be verified exists in the target image.
On the other hand, if the similarity is smaller than the similarity threshold, the corrected sub-image is determined not to be matched with the image to be checked. At this time, the pattern to be verified does not exist in the target image.
The server can output the verification result.
In one embodiment, it is assumed that the server performs pattern verification on different types of target images (e.g., different brands of clothes), and in this case, the template images corresponding to the different types of target images are different. Such as: and if the object in the target image is the clothes, the server side checks the hot stamping pattern on the clothes. Different template images exist for different brands, different styles and different sizes of clothing.
In an embodiment, in the pre-configuration stage, the server may receive the verification identifier and the template image, and establish a mapping relationship between the verification identifier and the template image. The verification marks are used for distinguishing the types of the template images, and one verification mark can correspond to a certain size of one style of a brand. For example, the verification identifier may be xx brand lady short sleeve M code. The verification mark can be a group of data, and different numbers or letter combinations are used for representing different brands and different styles of clothes. Such as: when the server checks the patterns on the clothes, the clothes with different brands, different styles and different sizes can have corresponding template images respectively, and the check identification and the corresponding template images are stored in the server in advance.
The server may save the mapping relationship in the template image table. The template image table comprises a plurality of template image table entries, and each template image table entry comprises a mapping relation between the verification identifier and the template image. The server may generate a template image entry for the mapping relationship and store the template image entry in the template image table.
When pattern verification is carried out on different types of target images, the server side can obtain verification marks of the target images, and therefore template images corresponding to the verification marks are searched.
The server can search the template image table based on the verification identifier of the target image, and determine the template image corresponding to the verification identifier based on the searched template image table entry.
The above step 320 is performed according to the searched template image.
In an embodiment, before performing step 320, the server may obtain pattern position information labeled on the template image, and store the key point coordinates and the pattern position information corresponding to the template image in an associated manner. For example, if there are multiple template images, the key point coordinates and pattern position information may be stored in the template image entry corresponding to the template image.
The server side can subsequently calculate a rotation matrix through the stored key point coordinates, and obtain a correction sub-image and an image to be checked based on the stored pattern position information.
Fig. 6 is a block diagram of a pattern verification apparatus for a target image according to an embodiment of the present invention. As shown in fig. 6, the apparatus may include: the device comprises a detection module 610, a calculation module 620, a rotation module 630, an acquisition module 640 and a verification module 650.
And the detecting module 610 is used for detecting the coordinates of the key points in the target image.
And a calculating module 620, configured to calculate a rotation matrix according to the key point coordinates and key point coordinates in a preset template image.
And a rotation module 630, configured to perform rotation transformation on the target image according to the rotation matrix, so as to obtain a corrected image.
An obtaining module 640, configured to obtain, based on the pattern position information in the template image, a corrected sub-image corresponding to the pattern position information from the corrected image.
And the verification module 650 is configured to determine whether the corrected sub-image matches the to-be-verified image corresponding to the pattern position information in the template image, and output a verification result.
In an embodiment, the detecting module 610 is further configured to:
and taking the target image as the input of a trained deep learning model to obtain the key point coordinates of the target image.
In an embodiment, the calculation module 620 is further configured to:
and searching the template image corresponding to the verification identification based on the verification identification of the target image.
In an embodiment, the calculation module 620 is further configured to:
and receiving the verification identification and the template image, and establishing a mapping relation between the verification identification and the template image.
In an embodiment, the calculation module 620 is further configured to:
and taking the template image as the input of a trained deep learning model to obtain the key point coordinates of the template image.
In an embodiment, the calculation module 620 is further configured to:
acquiring pattern position information marked on the template image;
and storing the key point coordinates corresponding to the template image and the pattern position information in a correlation manner.
In one embodiment, the verification module 650 is further configured to:
calculating the similarity between the correction sub-image and the image to be checked based on a similarity calculation method;
judging whether the similarity is greater than a preset similarity threshold value or not;
if yes, determining that the syndrome image is matched with the image to be checked;
and if not, determining that the syndrome image is not matched with the image to be checked.
The implementation processes of the functions and actions of the modules in the device are specifically described in the implementation processes of the corresponding steps in the pattern verification method for the target image, and are not described herein again.
In the embodiments provided in the present application, the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

Claims (10)

1. A method for pattern verification of a target image, comprising:
detecting the coordinates of key points in a target image;
calculating a rotation matrix according to the key point coordinates and key point coordinates in a preset template image;
carrying out rotation transformation on the target image according to the rotation matrix to obtain a corrected image;
acquiring a correction sub-image corresponding to the pattern position information from the correction image based on the pattern position information in the template image;
and judging whether the corrected subimage is matched with the image to be checked corresponding to the pattern position information in the template image or not, and outputting a checking result.
2. The method of claim 1, wherein the detecting of keypoint coordinates in the target image further comprises:
and taking the target image as the input of a trained deep learning model to obtain the key point coordinates of the target image.
3. The method of claim 1, wherein prior to computing the rotation matrix, the method further comprises:
and searching the template image corresponding to the verification identification based on the verification identification of the target image.
4. The method of claim 3, wherein before searching for the template image corresponding to the verification identifier, the method further comprises:
and receiving the verification identification and the template image, and establishing a mapping relation between the verification identification and the template image.
5. The method of claim 1, wherein prior to said computing a rotation matrix from said keypoint coordinates and keypoint coordinates in a preset template image, the method further comprises:
and taking the template image as the input of a trained deep learning model to obtain the key point coordinates of the template image.
6. The method according to claim 1, wherein before the obtaining of the corrected sub-image corresponding to the pattern position information from the corrected image based on the pattern position information in the template image, the method further comprises:
acquiring pattern position information marked on the template image;
and storing the key point coordinates corresponding to the template image and the pattern position information in a correlation manner.
7. The method according to claim 1, wherein the determining whether the correction sub-image matches the image to be verified corresponding to the pattern position information in the template image comprises:
calculating the similarity between the correction sub-image and the image to be checked based on a similarity calculation method;
judging whether the similarity is greater than a preset similarity threshold value or not;
if yes, determining that the syndrome image is matched with the image to be checked;
and if not, determining that the syndrome image is not matched with the image to be checked.
8. A pattern verification apparatus for a target image, comprising:
the detection module is used for detecting the coordinates of the key points in the target image;
the calculation module is used for calculating a rotation matrix according to the key point coordinates and key point coordinates in a preset template image;
the rotation module is used for performing rotation transformation on the target image according to the rotation matrix to obtain a corrected image;
the acquisition module is used for acquiring a correction sub-image corresponding to the pattern position information from the correction image based on the pattern position information in a preset template image;
and the verification module is used for judging whether the corrected subimage is matched with the image to be verified corresponding to the pattern position information in the template image or not and outputting a verification result.
9. An electronic device, characterized in that the electronic device comprises:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to perform the method of pattern verification of a target image of any one of claims 1-7.
10. A computer-readable storage medium, characterized in that the storage medium stores a computer program executable by a processor to perform the method of pattern verification of an object image according to any one of claims 1 to 7.
CN202010526093.7A 2020-06-10 2020-06-10 Pattern verification method and device for target image, electronic device and storage medium Pending CN111667479A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010526093.7A CN111667479A (en) 2020-06-10 2020-06-10 Pattern verification method and device for target image, electronic device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010526093.7A CN111667479A (en) 2020-06-10 2020-06-10 Pattern verification method and device for target image, electronic device and storage medium

Publications (1)

Publication Number Publication Date
CN111667479A true CN111667479A (en) 2020-09-15

Family

ID=72386739

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010526093.7A Pending CN111667479A (en) 2020-06-10 2020-06-10 Pattern verification method and device for target image, electronic device and storage medium

Country Status (1)

Country Link
CN (1) CN111667479A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112464952A (en) * 2020-11-25 2021-03-09 创新奇智(南京)科技有限公司 Image alignment method and image matching identification method
CN112801976A (en) * 2021-01-28 2021-05-14 河南省四合印务有限公司 Detection system and method for correcting binding mispasting of books and periodicals and computer device
CN113111880A (en) * 2021-05-12 2021-07-13 中国平安人寿保险股份有限公司 Certificate image correction method and device, electronic equipment and storage medium
CN114723517A (en) * 2022-03-18 2022-07-08 唯品会(广州)软件有限公司 Virtual fitting method, device and storage medium
CN116229437A (en) * 2023-03-14 2023-06-06 北京道达天际科技股份有限公司 Remote sensing image rotation target detection method

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6863218B2 (en) * 2002-07-18 2005-03-08 Sharp Kabushiki Kaisha Two-dimensional code reading apparatus, two-dimensional code reading process, two-dimensional code reading program and recording medium for said program, portable terminal and digital camera
KR20090071738A (en) * 2007-12-28 2009-07-02 주식회사 하이닉스반도체 Method for verifying patterns by using multi - layout data
CN106327483A (en) * 2016-08-12 2017-01-11 广州视源电子科技股份有限公司 Detection equipment logo attaching method, system and device
US20180046882A1 (en) * 2014-11-03 2018-02-15 Terrence A. CARROLL Textile matching using color and pattern recognition and methods of use
CN109214324A (en) * 2018-08-27 2019-01-15 曜科智能科技（上海）有限公司 Most face image output method and output system based on polyphaser array
CN109389038A (en) * 2018-09-04 2019-02-26 阿里巴巴集团控股有限公司 A kind of detection method of information, device and equipment
WO2020077822A1 (en) * 2018-10-17 2020-04-23 深圳壹账通智能科技有限公司 Image feature configuration and verification method and apparatus, computer device and medium

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6863218B2 (en) * 2002-07-18 2005-03-08 Sharp Kabushiki Kaisha Two-dimensional code reading apparatus, two-dimensional code reading process, two-dimensional code reading program and recording medium for said program, portable terminal and digital camera
KR20090071738A (en) * 2007-12-28 2009-07-02 주식회사 하이닉스반도체 Method for verifying patterns by using multi - layout data
US20180046882A1 (en) * 2014-11-03 2018-02-15 Terrence A. CARROLL Textile matching using color and pattern recognition and methods of use
CN106327483A (en) * 2016-08-12 2017-01-11 广州视源电子科技股份有限公司 Detection equipment logo attaching method, system and device
CN109214324A (en) * 2018-08-27 2019-01-15 曜科智能科技（上海）有限公司 Most face image output method and output system based on polyphaser array
CN109389038A (en) * 2018-09-04 2019-02-26 阿里巴巴集团控股有限公司 A kind of detection method of information, device and equipment
WO2020077822A1 (en) * 2018-10-17 2020-04-23 深圳壹账通智能科技有限公司 Image feature configuration and verification method and apparatus, computer device and medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
QINGHE ZHENG: "《An End-to-End Image Retrieval System Based on Gravitational Field Deep Learning 》" *
付卓君: "《人证核验系统设计与实现》" *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112464952A (en) * 2020-11-25 2021-03-09 创新奇智(南京)科技有限公司 Image alignment method and image matching identification method
CN112801976A (en) * 2021-01-28 2021-05-14 河南省四合印务有限公司 Detection system and method for correcting binding mispasting of books and periodicals and computer device
CN113111880A (en) * 2021-05-12 2021-07-13 中国平安人寿保险股份有限公司 Certificate image correction method and device, electronic equipment and storage medium
CN113111880B (en) * 2021-05-12 2023-10-17 中国平安人寿保险股份有限公司 Certificate image correction method, device, electronic equipment and storage medium
CN114723517A (en) * 2022-03-18 2022-07-08 唯品会(广州)软件有限公司 Virtual fitting method, device and storage medium
CN116229437A (en) * 2023-03-14 2023-06-06 北京道达天际科技股份有限公司 Remote sensing image rotation target detection method

Similar Documents

Publication Publication Date Title
CN111667479A (en) Pattern verification method and device for target image, electronic device and storage medium
CN111680688B (en) Character recognition method and device, electronic equipment and storage medium
CN111474184B (en) AOI character defect detection method and device based on industrial machine vision
CN104584073B (en) Object detector and object identification method
CN108520254B (en) Text detection method and device based on formatted image and related equipment
CN104584071B (en) Object detector, object identification method
CN110546651B (en) Method, system and computer readable medium for identifying objects
WO2017193596A1 (en) Image matching method and system for printed circuit board
JP6810392B2 (en) Individual identification device
KR101656941B1 (en) Method, server and computer program for improving 2d code recognition ratio
CN107862319B (en) Heterogeneous high-light optical image matching error eliminating method based on neighborhood voting
CN112613506A (en) Method and device for recognizing text in image, computer equipment and storage medium
CN111325104A (en) Text recognition method, device and storage medium
CN108763575B (en) Image control point automatic selection method based on image control point database
CN113903024A (en) Handwritten bill numerical value information identification method, system, medium and device
CN114694161A (en) Text recognition method and equipment for specific format certificate and storage medium
KR20140093407A (en) Recognition device, vehicle model recognition apparatus and method
CN110955603B (en) Automated testing method, apparatus, electronic device and computer readable storage medium
CN112580499A (en) Text recognition method, device, equipment and storage medium
CN112084804A (en) Working method for intelligently acquiring complementary pixels aiming at information-missing bar codes
CN110660091A (en) Image registration processing method and device and photographing correction operation system
JP2015007919A (en) Program, apparatus, and method of realizing high accuracy geometric inspection for images different in point of view
CN108304838B (en) Picture information identification method and terminal
WO2017179728A1 (en) Image recognition device, image recognition method, and image recognition program
CN115116073A (en) Washing label identification method and device, storage medium and electronic device

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