CN111428707B - Method and device for identifying pattern identification code, storage medium and electronic equipment - Google Patents

Method and device for identifying pattern identification code, storage medium and electronic equipment Download PDF

Info

Publication number
CN111428707B
CN111428707B CN202010509898.0A CN202010509898A CN111428707B CN 111428707 B CN111428707 B CN 111428707B CN 202010509898 A CN202010509898 A CN 202010509898A CN 111428707 B CN111428707 B CN 111428707B
Authority
CN
China
Prior art keywords
image
target
pattern
identification code
code
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010509898.0A
Other languages
Chinese (zh)
Other versions
CN111428707A (en
Inventor
杨蒙昭
柴振华
孟欢欢
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.)
Beijing Sankuai Online Technology Co Ltd
Original Assignee
Beijing Sankuai Online 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 Beijing Sankuai Online Technology Co Ltd filed Critical Beijing Sankuai Online Technology Co Ltd
Priority to CN202010509898.0A priority Critical patent/CN111428707B/en
Publication of CN111428707A publication Critical patent/CN111428707A/en
Application granted granted Critical
Publication of CN111428707B publication Critical patent/CN111428707B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/20Image acquisition
    • G06K9/2009Construction of image pick-up using regular bi-dimensional dissection
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/20Image acquisition
    • G06K9/2054Selective acquisition/locating/processing of specific regions, e.g. highlighted text, fiducial marks, predetermined fields, document type identification
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/20Image acquisition
    • G06K9/32Aligning or centering of the image pick-up or image-field
    • G06K9/3216Aligning or centering of the image pick-up or image-field by locating a pattern

Abstract

The disclosure relates to a method and a device for identifying a pattern identification code, a storage medium and an electronic device. The method comprises the following steps: acquiring a first image containing the pattern identification code; acquiring a second image of the pattern identification code from the first image; determining position information of each target corner point in the graphic identification code in the second image, wherein the target corner points comprise each vertex of the graphic identification code and other vertexes of each positioning pattern of the graphic identification code except the vertex of the graphic identification code; and identifying the pattern identification code according to the second image and the position information of each target corner point in the second image. Through the technical scheme, the position of the central point of each positioning pattern can be directly determined according to the position information of the target angular point in the second image, the effective recognition of the pattern recognition code can be guaranteed, and the recognition success rate and the recognition accuracy are improved.

Description

Method and device for identifying pattern identification code, storage medium and electronic equipment
Technical Field
The present disclosure relates to the field of image recognition technologies, and in particular, to a method and an apparatus for recognizing a pattern recognition code, a storage medium, and an electronic device.
Background
The pattern recognition code records data information through images which are distributed on a plane according to a certain rule through a specific geometric figure, and common pattern recognition codes comprise two-dimensional codes, bar codes and the like. The pattern identification code is identified, and the information recorded in the pattern identification code can be acquired.
The pattern recognition code has the characteristics of large information capacity and the like, so that the application scene is wide. For example, a code scanning payment scenario, a code scanning cycling scenario, a code scanning login scenario, etc. In the related art, when the pattern recognition code is recognized, the recognition success rate is low, and the recognition accuracy is not high, so that the acquisition of information in the pattern recognition code is influenced.
Disclosure of Invention
The present disclosure provides a method, an apparatus, a storage medium, and an electronic device for recognizing a pattern recognition code, which can ensure effective recognition of the pattern recognition code and improve a recognition success rate and a recognition accuracy.
In order to achieve the above object, in a first aspect, the present disclosure provides a method for identifying a pattern identification code, the method including: acquiring a first image containing the pattern identification code; acquiring a second image of the pattern identification code from the first image; determining position information of each target corner point in the graphic identification code in the second image, wherein the target corner points comprise each vertex of the graphic identification code and other vertexes of each positioning pattern of the graphic identification code except the vertex of the graphic identification code; and identifying the pattern identification code according to the second image and the position information of each target corner point in the second image.
Optionally, the obtaining a second image of the pattern recognition code from the first image includes: detecting the pattern recognition code in the first image to determine a pattern recognition code area in the first image; determining a target area in the first image according to the pattern recognition code area, wherein the target area comprises the pattern recognition code area and is larger than the pattern recognition code area; and performing screenshot operation on the pattern identification code area in the target area to obtain the second image.
Optionally, the determining the position information of each target corner point in the pattern recognition code in the second image includes: and inputting the second image into a corner recognition model, and obtaining the position information of each target corner output by the corner recognition model in the second image.
Optionally, the identifying the pattern identification code according to the second image and the position information of each target corner point in the second image includes: correcting the figure identification code according to the second image and the position information of each target corner point in the second image to obtain a corrected target image of the figure identification code; and identifying the pattern identification code according to the target image and the position information of each target corner point in the target image.
Optionally, the correcting the pattern recognition code includes: determining the positions of the central points of at least two positioning patterns according to the position information of each target corner point in the second image; and rotating the second image according to the determined angle between the connecting line of the central point positions of any two positioning patterns and a preset direction so as to correct the pattern identification code.
Optionally, the correcting the pattern recognition code includes: determining the proportion of the average side length of the positioning pattern to the average side length of the pattern identification code according to the position information of each target corner point in the second image; determining the position information of each target corner point in the target image according to the proportion; and correcting the pattern recognition code through a spline interpolation algorithm according to the position information of each target corner point in the target image.
Optionally, the identifying the pattern identification code according to the target image and the position information of each target corner point in the target image includes: carrying out external expansion processing on the target image; determining the position information of each target corner point in the target image after the external expansion processing according to the position information of each target corner point in the target image; and identifying the pattern identification code according to the target image subjected to the external expansion processing and the position information of each target corner point in the target image subjected to the external expansion processing.
Optionally, the method further comprises: under the condition that the identification result is not obtained, performing up-sampling processing on the target image; and re-identifying the pattern identification code according to the image obtained after the up-sampling processing is carried out on the target image.
In a second aspect, the present disclosure provides an apparatus for recognizing a pattern recognition code, the apparatus comprising: a first acquisition module configured to acquire a first image containing the pattern recognition code; a second obtaining module configured to obtain a second image of the pattern recognition code from the first image; a determining module configured to determine position information of each target corner point in the graphical identification code in the second image, wherein the target corner point comprises each vertex of the graphical identification code and other vertices of each positioning pattern of the graphical identification code except for the vertex of the graphical identification code; and the identification module is configured to identify the pattern identification code according to the second image and the position information of each target corner point in the second image.
Optionally, the second obtaining module includes: a detection sub-module configured to detect a pattern recognition code in the first image to determine a pattern recognition code region in the first image; a first determining submodule configured to determine a target region in the first image according to the pattern recognition code region, wherein the target region includes the pattern recognition code region and is larger than the pattern recognition code region; and the screenshot operation sub-module is configured to perform screenshot operation on the graphic identification code region in the target region to obtain the second image.
Optionally, the determining module is configured to input the second image into a corner recognition model, and obtain position information of the respective target corner outputted by the corner recognition model in the second image.
Optionally, the identification module comprises: the first correction submodule is configured to correct the figure identification code according to the second image and position information of each target corner point in the second image so as to obtain a corrected target image of the figure identification code; and the first identification submodule is configured to identify the pattern identification code according to the target image and the position information of each target corner point in the target image.
Optionally, the first correction submodule includes: a second determining submodule configured to determine center point positions of at least two positioning patterns according to position information of each target corner point in the second image; and the rotation operation sub-module is configured to perform rotation operation on the second image according to an angle between a connecting line of the central point positions of any two positioning patterns determined by the second determination sub-module and a preset direction, so as to correct the pattern identification code.
Optionally, the first correction submodule includes: a third determining submodule configured to determine, according to position information of each target corner point in the second image, a ratio of an average side length of the positioning pattern to an average side length of the pattern identification code; a fourth determining submodule configured to determine position information of each target corner point in the target image according to the proportion; and the second correction submodule is configured to correct the figure identification code through a spline interpolation algorithm according to the position information of each target corner point in the target image.
Optionally, the first identification submodule includes: an external expansion processing sub-module configured to perform external expansion processing on the target image; a fifth determining sub-module, configured to determine, according to the position information of each target corner point in the target image, the position information of each target corner point in the target image after the outward expansion processing; and the second identification submodule is configured to identify the pattern identification code according to the target image subjected to the external expansion processing and the position information of each target corner point in the target image subjected to the external expansion processing.
Optionally, the apparatus further comprises: an up-sampling processing sub-module configured to perform up-sampling processing on the target image if a recognition result is not obtained; and the third identification submodule is configured to re-identify the pattern identification code according to an image obtained after the target image is subjected to the up-sampling processing.
In a third aspect, the present disclosure provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method provided by the first aspect of the present disclosure.
In a fourth aspect, the present disclosure provides an electronic device comprising: a memory having a computer program stored thereon; a processor for executing the computer program in the memory to implement the steps of the method provided by the first aspect of the present disclosure.
Through the technical scheme, after the first image containing the pattern identification code is obtained, the second image of the pattern identification code can be obtained from the first image, and identification is carried out according to the second image, so that the problem of low identification success rate caused by direct identification according to the first image under the condition that the proportion of the pattern identification code in the first image is small can be solved. And then, identifying the pattern identification code according to the second image and the position information of each target corner point in the second image. Therefore, when the central point position of each positioning pattern cannot be determined due to the abnormal phenomena of blurring and the like of the pattern identification code, the central point position of each positioning pattern can be directly determined according to the position information of the target angular point in the second image, the pattern identification code can be effectively identified, and the identification success rate and the identification accuracy are improved.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure without limiting the disclosure.
Fig. 1 is a flow chart illustrating a method of pattern recognition code recognition according to an example embodiment.
FIG. 2 is a diagram illustrating a second image of a graphical identification code, according to an example embodiment.
FIG. 3 is a flow chart illustrating a method of obtaining a second image of a pattern recognition code from a first image according to an exemplary embodiment.
FIG. 4 is a schematic diagram illustrating a method of determining a target region in a first image according to an exemplary embodiment.
Fig. 5 is a flowchart illustrating a method for recognizing a pattern recognition code according to a second image and position information of each target corner point in the second image according to an exemplary embodiment.
FIG. 6 is a flow chart illustrating a method of correcting a pattern recognition code according to an example embodiment.
FIG. 7 is a diagram illustrating a pattern recognition code, according to an example embodiment.
FIG. 8 is a diagram illustrating a target image after correction of the graphical identification code shown in FIG. 7, according to an example embodiment.
Fig. 9 is a flow chart illustrating a method of correcting a pattern recognition code according to another exemplary embodiment.
FIG. 10 is a diagram illustrating a graphical identification code, according to another exemplary embodiment.
FIG. 11 is a diagram illustrating a target image after correction of the graphical identification code shown in FIG. 10, according to an example embodiment.
Fig. 12 is a flowchart illustrating a method for recognizing a pattern recognition code according to a target image and position information of each target corner point in the target image according to an exemplary embodiment.
Fig. 13 is a block diagram illustrating an apparatus for recognizing a pattern recognition code according to an exemplary embodiment.
FIG. 14 is a block diagram illustrating an electronic device in accordance with an example embodiment.
Detailed Description
The following detailed description of specific embodiments of the present disclosure is provided in connection with the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present disclosure, are given by way of illustration and explanation only, not limitation.
An application scenario of the present disclosure is first introduced. The method and the device can be applied to any scene needing to identify the graphical identification code, such as code scanning payment, code scanning cycling, code scanning login, code scanning downloading and the like.
Fig. 1 is a flowchart illustrating a method for recognizing a pattern recognition code according to an exemplary embodiment, where the method is applicable to a terminal, such as a terminal device like a smart phone, a tablet computer, a notebook computer, a Personal Computer (PC), and the like. As shown in FIG. 1, the method may include S101-S104.
In S101, a first image including a pattern recognition code is acquired.
The first image may be acquired by an image acquisition device integrated on the terminal. The image capturing device may be any device with image capturing capability, for example, a camera, a video camera, or the like.
In one embodiment, the first image may be an image containing a pattern recognition code pre-stored in the terminal. In another embodiment, the first image may also be an image captured by the image capturing device in real time, for example, an image containing a graphical identification code captured by the image capturing device in real time, or an image frame containing a graphical identification code captured by the image capturing device in real time in a video stream.
In S102, a second image of the pattern recognition code is acquired from the first image.
The first image includes the pattern recognition code and also includes a background part except the pattern recognition code, and particularly, in the case that the proportion of the pattern recognition code in the first image is small, if the first image is directly recognized, the recognition may not be performed, and the recognition success rate is low. Therefore, in the present disclosure, after acquiring the first image, the second image of the pattern recognition code may be acquired from the first image first. For example, a screenshot operation may be performed on the graphical identification code region in the first image to obtain the second image.
In S103, the position information of each target corner point in the pattern recognition code in the second image is determined.
The target corner points may include vertices of the graphics identifier and vertices of the positioning pattern of the graphics identifier other than the vertices of the graphics identifier. The pattern recognition code usually includes a plurality of positioning patterns, and the positioning patterns can be used to determine the size and the position of the pattern recognition code to assist in recognizing the pattern recognition code.
Fig. 2 is a schematic diagram illustrating a second image of a graphical identification code that may include three positioning patterns, positioning pattern 201, positioning pattern 202, and positioning pattern 203, according to an example embodiment. The target corner point may comprise the vertex of the pattern identifier, point A1Point F1Point I1And point M1And the dividing vertex A of the positioning pattern 2011Other vertices than the one, i.e. points B1Point C1And point D1Positioning the dividing vertex F of the pattern 2021Other than the vertex, i.e. point E1Point G1And point H1Positioning the dividing vertex M of the pattern 2031Other than the vertex, i.e. point J1Point K1And point L1. In the pattern recognition code shown in fig. 2, there are 13 target corner points in total.
For example, as shown in fig. 2, taking the direction of one side of the pattern identifier as an x-axis and the direction perpendicular to the x-axis as a y-axis as an example, the position information of each target corner point in the second image may be two-dimensional coordinate information of each target corner point in the second image.
It should be noted that the pattern identification code, the positioning pattern therein, and the positions of the target corner points shown in fig. 2 are only exemplary illustrations and do not limit the embodiments of the disclosure.
In S104, the pattern identification code is identified according to the second image and the position information of each target corner point in the second image.
When the pattern identification code is identified, the position of the central point of each positioning pattern needs to be analyzed first, and if the position of the central point of each positioning pattern is not analyzed, the pattern identification code cannot be identified continuously. In an actual application scenario, the pattern identification code is easily stained, blurred, missing and the like, and if the abnormal phenomena occur, for example, the localized pattern is stained, the position of the center point of each localized pattern may not be resolved, so that the pattern identification code cannot be effectively identified, and the identification success rate is low.
In the present disclosure, when the pattern identification code is identified, the used information includes, in addition to the second image of the pattern identification code, position information of each target corner point in the second image. And according to the position information of each target corner point in the second image, the position of the central point of each positioning pattern can be directly determined. Illustratively, from the target corner point A1、B1、C1、D1The position of the center point of the positioning pattern 201 can be determined according to the position information in the second image, and the target corner point E is used for determining the position of the center point1、F1、G1、H1The position of the center point of the positioning pattern 202 can be determined according to the position information in the second image, and the target corner point J is used for determining the position of the center point1、K1、L1、M1From the position information in the second image, the position of the center point of the positioning pattern 203 can be determined.
Therefore, even if the central point position of each positioning pattern cannot be detected due to the situation that the pattern identification code is fuzzy and the like, the central point position information of each positioning pattern can be directly determined according to the position information of each target angular point in the second image during identification, so that the pattern identification code can be effectively and accurately identified, and the identification success rate is improved.
Through the technical scheme, after the first image containing the pattern identification code is obtained, the second image of the pattern identification code can be obtained from the first image, and identification is carried out according to the second image, so that the problem of low identification success rate caused by direct identification according to the first image under the condition that the proportion of the pattern identification code in the first image is small can be solved. And then, identifying the pattern identification code according to the second image and the position information of each target corner point in the second image. Therefore, when the central point position of each positioning pattern cannot be determined due to the abnormal phenomena of blurring and the like of the pattern identification code, the central point position of each positioning pattern can be directly determined according to the position information of the target angular point in the second image, the pattern identification code can be effectively identified, and the identification success rate and the identification accuracy are improved.
FIG. 3 is a flow chart illustrating a method of obtaining a second image of a pattern recognition code from a first image according to an exemplary embodiment. As shown in FIG. 3, the step S102 may include steps S301 to S303.
In S301, the pattern recognition code in the first image is detected to determine a pattern recognition code region in the first image.
In the step, the first image is detected by any pattern recognition code detection method in the related technology to determine the pattern recognition code area. For example, a plurality of positioning patterns may be detected first, and the pattern identification code region may be determined by the plurality of positioning patterns.
In S302, a target region in the first image is determined based on the pattern recognition code region.
In practical application, when a user scans a code, the user may be far away from the pattern recognition code, so that the pattern recognition code may occupy a smaller proportion of the first image acquired by the image acquisition device. In the case that the code occupation ratio is small, if the screenshot operation is directly performed on the pattern recognition code region in the first image after the pattern recognition code region is determined in S301, the edge portion of the pattern recognition code may not be included in the second image, so that the obtained pattern recognition code in the second image is not complete enough.
In the present disclosure, after the pattern recognition code region in the first image is determined, a target region in the first image may be determined according to the pattern recognition code region, and the target region may include the pattern recognition code region and be larger than the pattern recognition code region. And then, intercepting the graph identification code area from the target area to obtain a second image, thus reducing the cutting range and ensuring the integrity of the graph identification code in the obtained second image.
An exemplary embodiment of determining a target region in a first image is described below. FIG. 4 is a schematic diagram illustrating a method of determining a target region in a first image according to an exemplary embodiment. As shown in fig. 4, the image 400 is a first image including a pattern recognition code, and the region 401 is a pattern recognition code region in the first image determined in S301. Then, the region 401 may be expanded outward, for example, the periphery of the region 401 may be expanded outward by a preset distance to obtain the region 402. Wherein the extended preset distance may be preset, and the disclosure is not particularly limited.
In one embodiment, the region 402 may be directly used as the target region. In another embodiment, the region 402 may be further adjusted to determine the target region. The normal pattern recognition code area is usually square, and when a user scans a code, the pattern recognition code area in the first image may not be square due to the shooting position, the shooting angle and the like, so that resolution adjustment needs to be additionally performed on the image intercepted with the pattern recognition code, so that the second image is square, and the pattern recognition code can be normally recognized.
In order to avoid the distortion phenomenon of the image after resolution adjustment and to adapt to the square shape of the second image to the maximum extent, the region 402 may be expanded to adjust to a square region by taking the center position of the region 402 as a reference, so as to obtain a region 403, and the region 403 may be used as a target region in the first image in the present disclosure. The image of the pattern recognition code is intercepted from the square area 403, so that the image distortion phenomenon after resolution adjustment can be avoided to the greatest extent.
It should be noted that the process of determining the target area shown in fig. 4 is only an exemplary illustration and does not limit the embodiments of the present disclosure, and the target area only includes the pattern recognition code area and is larger than the pattern recognition code area.
In S303, a screenshot operation is performed on the pattern recognition code region in the target region to obtain a second image.
The image identification code area is intercepted from the target area, compared with the method that the image identification code area is directly intercepted from the whole first image, the cutting range can be reduced, the screenshot operation is more accurate, the image identification code in the obtained second image is more complete, the image identification code is identified according to the second image subsequently, and the identification success rate can be improved.
Through the technical scheme, the target area is an area which comprises the pattern identification code in the first image and is larger than the pattern identification code, and the screenshot operation is carried out on the pattern identification code area from the target area, so that the clipping range can be shortened, and the problem that the pattern identification code obtained by directly carrying out screenshot from the whole first image is incomplete is solved.
In this disclosure, the determining, in S103, the position information of each target corner point in the pattern identification code in the second image may include: and inputting the second image into the corner recognition model, and obtaining the position information of each target corner output by the corner recognition model in the second image.
Wherein the corner point identification model may be pre-trained. The corner point identification model can be obtained by training a neural network model by taking an image of the graphic identification code as a model input parameter and taking position information of each target corner point of the graphic identification code in the image as a model output parameter. In the method, the second image of the pattern identification code is directly input into the corner identification model, so that the position information of each target corner outputted by the corner identification model in the second image can be obtained, the target corners in the pattern identification code do not need to be detected one by one, the detection time of the target corners can be shortened, and the identification efficiency of the pattern identification code is improved.
In an actual application scene, due to different code scanning angles of users, the figure identification code in the first image may have a rotation phenomenon of different degrees, and if the figure identification code is attached to the surface of an uneven object, the figure identification code in the first image may have a deformation phenomenon, so that the figure identification code is not easily identified or is easily identified by mistake. In the present disclosure, in order to improve the recognition success rate and the recognition accuracy of the pattern recognition code, the pattern recognition code may be corrected, and then the corrected pattern recognition code may be recognized.
Fig. 5 is a flowchart illustrating a method for recognizing a pattern recognition code according to a second image and position information of each target corner point in the second image, where, as shown in fig. 5, S104 may include S501 and S502.
In S501, the pattern recognition code is corrected according to the second image and the position information of each target corner point in the second image, so as to obtain a target image of the corrected pattern recognition code.
In S502, the pattern identification code is identified according to the target image and the position information of each target corner point in the target image.
After the pattern recognition code is corrected, the pattern recognition code can be more easily recognized, and the situation of false recognition can be effectively avoided. The pattern recognition code is recognized according to the target image of the corrected pattern recognition code and the position information of each target corner point in the target image, and compared with the mode that the pattern recognition code is recognized directly according to the second image, the recognition success rate and the recognition accuracy can be improved. The position information of each target corner point in the target image may be two-dimensional coordinate information of each target corner point in the target image.
If the pattern recognition code is attached to a relatively flat surface of an object, the pattern recognition code generally does not deform, and in this case, the rotation phenomenon of the pattern recognition code needs to be corrected. In one embodiment, an exemplary embodiment of correcting the pattern recognition code may be as shown in fig. 6, including S601 and S602.
In S601, the positions of the center points of at least two positioning patterns are determined according to the position information of each target corner point in the second image.
FIG. 7 is a diagram illustrating a pattern recognition code, according to an example embodiment. As shown in fig. 7, the figure identification code has a rotation phenomenon, and the figure identification code may include three positioning patterns, which are a positioning pattern 701, a positioning pattern 702, and a positioning pattern 703, respectively, and includes a target corner point a2、B2、C2、D2、E2、F2、G2、H2、I2、J2、K2、L2And M2. The step isIn the step, the central point positions of any two positioning patterns may be determined, and the present disclosure does not specifically limit any two positioning patterns, for example, the positioning patterns 701 and 703 may be used, or the central point positions of the three positioning patterns may also be determined.
Illustratively, it can be based on the target corner point A2、B2、C2、D2The position information in the second image determines the position of the center point of the positioning pattern 701, i.e. the position information of the point N in the second image. According to the target corner E2、F2、G2And H2The position information in the second image determines the position of the center point of the positioning pattern 702, i.e. the position information of the point P in the second image. According to the target corner J2、K2、L2、M2The position information in the second image determines the position of the center point of the positioning pattern 703, i.e., the position information of the point Q in the second image.
In S602, the second image is rotated according to the angle between the connection line of the center point positions of any two positioning patterns and the preset direction, so as to correct the pattern recognition code.
If the center point positions of the two positioning patterns are determined in S601, the center point positions of the two positioning patterns may be used, and if the center point positions of the three positioning patterns are determined in S601, the center point positions of any two positioning patterns of the three positioning patterns may be used.
In an embodiment, as shown in fig. 7, for example, a rotation matrix is constructed according to an angle θ between a connection line of a center point position point N of the positioning pattern 701 and a center point position point Q of the positioning pattern 703 and a preset direction, and for each pixel point in the second image, a rotation operation is performed through the rotation matrix, so that the pattern identifier can be subjected to rotation correction. The preset direction may be a horizontal direction, a vertical direction, or any other direction, and fig. 7 only illustrates the preset direction as a horizontal square, but does not limit the embodiments of the present disclosure.
FIG. 8 is a diagram illustrating a target image after correction of the graphical identification code shown in FIG. 7, according to an example embodiment. After the pattern recognition code is corrected, the pattern recognition code may be corrected back to a normal angle, as shown in fig. 8. The pattern recognition code is recognized according to the target image shown in fig. 8, so that the recognition success rate and the recognition accuracy can be improved.
If the pattern recognition code is attached to the surface of an uneven object, for example, the surface of a cylindrical bottle body or an easily deformable packaging bag, the pattern recognition code is easy to deform along with the uneven object, and is not easy to recognize. In another embodiment, an exemplary embodiment of correcting the pattern recognition code may include steps S901 to S903 as shown in fig. 9.
In S901, a ratio of an average side length of the positioning pattern to an average side length of the pattern identification code is determined according to position information of each target corner point in the second image.
FIG. 10 is a diagram illustrating a graphical identification code, according to another exemplary embodiment. As shown in fig. 10, the pattern recognition code is deformed. The pattern identification code comprises a positioning pattern 1001, a positioning pattern 1002 and a positioning pattern 1003, and also comprises a target corner point A3、B3、C3、D3、E3、F3、G3、H3、I3、J3、K3、L3And M3. In this step, the average side length of the positioning pattern and the average side length of the pattern identification code can be determined according to the position information of each target corner point in the second image. Illustratively, from the target corner point A3And a target corner point B3Can determine the side length A of the positioning pattern 10013B3Length of (d). The other respective side lengths may be determined in a similar manner to that described above.
For example, the average side length of the positioning pattern may be determined by the following formula (1):
l f =(l AB +l BC +l CD +l DA +l EF +l FG +l GH +l HE +l JK +l KL +l LM +l MJ )/12(1)
wherein the content of the first and second substances,l f indicating the average side length of the positioning pattern,l AB represents the side length A3B3The length of (a) of (b),l BC represents the side length B3C3The length of (a) of (b),l CD represents the side length C3D3The length of (a) of (b),l DA represents the side length A3D3The length of (a) of (b),l EF represents the side length E3F3The length of (a) of (b),l FG represents the side length F3G3The length of (a) of (b),l GH represents the side length G3H3The length of (a) of (b),l HE represents the side length H3E3The length of (a) of (b),l JK represents the side length J3K3The length of (a) of (b),l KL represents the side length K3L3The length of (a) of (b),l LM represents the side length L3M3The length of (a) of (b),l MJ represents the side length M3J3Length of (d).
For example, the average side length of the pattern recognition code may be determined by the following formula (2):
l side =((l DA +l DJ +l MJ )+(l AB +l BE +l EF )+(l FG +l GI )+(l IL +l LM ))/4 (2)
wherein the content of the first and second substances,l side representing the average side length of the pattern identification code,l DJ represents the side length D3J3The length of (a) of (b),l BE to representSide length B3E3The length of (a) of (b),l GI represents the side length G3I3The length of (a) of (b),l IL represents the side length I3L3Length of (d).
The ratio of the average side length of the positioning pattern to the average side length of the pattern identification code can be determined by the following formula (3)p:
p=l f /l side (3)
In S902, the position information of each target corner in the target image is determined according to the scale.
FIG. 11 is a diagram illustrating a target image after correction of the graphical identification code shown in FIG. 10, according to an example embodiment. Illustratively, the size of the target image may be predetermined, for example, the resolution of the target image may be set to 250 × 250. And determining the position information of each target angular point in the target image according to the proportion of the average side length of the positioning pattern to the average side length of the pattern identification code and the side length of the target image.
It should be noted that when the pattern recognition code is at a normal angle, each positioning pattern is generally located at the upper left corner, the upper right corner and the lower left corner of the pattern recognition code, and the pattern recognition code shown in fig. 10 not only has a deformation phenomenon, but also has a rotation phenomenon, and when the deformation correction is performed on the pattern recognition code, the rotation correction can be completed at the same time. When the position information of each target corner point in the target image is determined, the graphic identification code can be corrected to a normal angle, namely, the positioning patterns are respectively positioned at the upper left corner, the upper right corner and the lower left corner of the graphic identification code.
In S903, the pattern recognition code is corrected by a spline interpolation algorithm according to the position information of each target corner in the target image.
According to the position information of each target corner point in the target image, the corresponding relation between each pixel point in the second image and the target image can be determined through a spline difference algorithm, the corresponding relation can represent the mapping relation between each pixel point from the second image to the target image, the pixel points in the second image are mapped into the target image according to the corresponding relation of each pixel point, the figure identification code can be corrected, and the target image of the corrected figure identification code is obtained.
Therefore, the pattern identification code is corrected through the spline difference algorithm, and the deformed pattern identification code can be effectively corrected, so that the recognition success rate and the recognition accuracy of the pattern identification code are improved.
When the pattern recognition code is recognized, it is usually necessary to detect the region where the positioning pattern is located, and the boundary of the positioning pattern is generally black and is located at the edge of the image of the pattern recognition code, which is not easy to detect. In order to solve the problem, in the present disclosure, an exemplary embodiment of identifying the pattern identification code according to the target image and the position information of each target corner point in the target image in S502 may be as shown in fig. 12, and includes S1201 to S1203.
In S1201, the target image is subjected to the expansion processing.
In order to accurately detect the boundary of the positioning pattern, in an embodiment, the target image may be subjected to an outward expansion process to increase a white area around the target image. After the white areas are added to the periphery of the target image, the black boundary of the positioning pattern can be more easily identified, so that the position of the positioning pattern can be quickly detected according to the black boundary of the positioning pattern. The size of the target image subjected to the dilation process, that is, the size of the increased white area, is not particularly limited in this disclosure.
In S1202, the position information of each target corner point in the target image after the outward expansion processing is determined according to the position information of each target corner point in the target image.
In S1203, the pattern identification code is identified according to the target image after the extension processing and the position information of each target corner point in the target image after the extension processing.
And determining the position information of each target corner point in the target image after the external expansion processing according to the position information of the target corner point in the target image and the size of the external expansion processing of the target image. The boundary of the positioning pattern can be accurately detected by identifying according to the target image after the external expansion processing, so that the position of the positioning pattern is accurately determined, and the effective identification of the pattern identification code is further ensured.
In the technical scheme, after the target image is subjected to the outer expansion processing, the position of the positioning pattern of the pattern identification code can be accurately detected when the pattern identification code is identified, so that the accurate identification of the pattern identification code is ensured.
Further, since the pattern recognition code itself may have an abnormal phenomenon such as blurring or staining, even if the target image obtained by correcting the pattern recognition code is recognized, the recognition result may not be obtained. In order to further improve the recognition success rate, the recognition method of the pattern recognition code provided by the present disclosure may further include:
under the condition that the identification result is not obtained, performing up-sampling processing on the target image;
and re-identifying the pattern identification code according to the image obtained after the up-sampling processing is carried out on the target image.
After the target image is identified, if the identification result is not obtained, the characteristic pattern identification code may appear phenomena such as blurring and fouling. According to the method and the device, the target image of the pattern identification code can be subjected to upsampling processing, new pixels can be inserted among pixel points by adopting a proper interpolation algorithm on the basis of the original image pixels, and the definition of the target image can be effectively enhanced. And re-identifying the pattern identification code according to the image obtained after the target image is subjected to the up-sampling treatment, so that the identification success rate can be further improved.
Based on the same inventive concept, the present disclosure further provides an apparatus for recognizing a pattern recognition code, and fig. 13 is a block diagram of an apparatus for recognizing a pattern recognition code according to an exemplary embodiment, as shown in fig. 13, the apparatus 1300 may include:
a first obtaining module 1301 configured to obtain a first image including the pattern recognition code; a second obtaining module 1302 configured to obtain a second image of the pattern recognition code from the first image; a determining module 1303, configured to determine position information of each target corner point in the graphical identification code in the second image, where the target corner point includes each vertex of the graphical identification code and other vertices of each positioning pattern of the graphical identification code except for the vertex of the graphical identification code; an identifying module 1304 configured to identify the pattern identification code according to the second image and the position information of each target corner point in the second image.
Through the technical scheme, after the first image containing the pattern identification code is obtained, the second image of the pattern identification code can be obtained from the first image, and identification is carried out according to the second image, so that the problem of low identification success rate caused by direct identification according to the first image under the condition that the proportion of the pattern identification code in the first image is small can be solved. And then, identifying the pattern identification code according to the second image and the position information of each target corner point in the second image. Therefore, when the central point position of each positioning pattern cannot be determined due to the abnormal phenomena of blurring and the like of the pattern identification code, the central point position of each positioning pattern can be directly determined according to the position information of the target angular point in the second image, the pattern identification code can be effectively identified, and the identification success rate and the identification accuracy are improved.
Optionally, the second obtaining module 1302 may include: a detection sub-module configured to detect a pattern recognition code in the first image to determine a pattern recognition code region in the first image; a first determining submodule configured to determine a target region in the first image according to the pattern recognition code region, wherein the target region includes the pattern recognition code region and is larger than the pattern recognition code region; and the screenshot operation sub-module is configured to perform screenshot operation on the graphic identification code region in the target region to obtain the second image.
Optionally, the determining module 1303 is configured to input the second image into a corner recognition model, and obtain position information of each target corner in the second image output by the corner recognition model.
Optionally, the identifying module 1304 may include: the first correction submodule is configured to correct the figure identification code according to the second image and position information of each target corner point in the second image so as to obtain a corrected target image of the figure identification code; and the first identification submodule is configured to identify the pattern identification code according to the target image and the position information of each target corner point in the target image.
Optionally, the first correction submodule includes: a second determining submodule configured to determine center point positions of at least two positioning patterns according to position information of each target corner point in the second image; and the rotation operation sub-module is configured to perform rotation operation on the second image according to an angle between a connecting line of the central point positions of any two positioning patterns determined by the second determination sub-module and a preset direction, so as to correct the pattern identification code.
Optionally, the first correction submodule includes: a third determining submodule configured to determine, according to position information of each target corner point in the second image, a ratio of an average side length of the positioning pattern to an average side length of the pattern identification code; a fourth determining submodule configured to determine position information of each target corner point in the target image according to the proportion; and the second correction submodule is configured to correct the figure identification code through a spline interpolation algorithm according to the position information of each target corner point in the target image.
Optionally, the first identification submodule includes: an external expansion processing sub-module configured to perform external expansion processing on the target image; a fifth determining sub-module, configured to determine, according to the position information of each target corner point in the target image, the position information of each target corner point in the target image after the outward expansion processing; and the second identification submodule is configured to identify the pattern identification code according to the target image subjected to the external expansion processing and the position information of each target corner point in the target image subjected to the external expansion processing.
Optionally, the apparatus 1300 may further include: an up-sampling processing sub-module configured to perform up-sampling processing on the target image if a recognition result is not obtained; and the third identification submodule is configured to re-identify the pattern identification code according to an image obtained after the target image is subjected to the up-sampling processing.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 14 is a block diagram illustrating an electronic device 1400 in accordance with an example embodiment. As shown in fig. 14, the electronic device 1400 may include: a processor 1401, and a memory 1402. The electronic device 1400 may also include one or more of a multimedia component 1403, an input/output (I/O) interface 1404, and a communication component 1405.
The processor 1401 is configured to control the overall operation of the electronic device 1400, so as to complete all or part of the steps in the above-mentioned method for recognizing the pattern recognition code. The memory 1402 is used to store various types of data to support operation of the electronic device 1400, such as instructions for any application or method operating on the electronic device 1400 and application-related data, such as contact data, messaging, pictures, audio, video, and the like. The Memory 1402 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. Multimedia components 1403 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 1402 or transmitted through the communication component 1405. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 1404 provides an interface between the processor 1401 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 1405 is used for wired or wireless communication between the electronic device 1400 and other devices. Wireless Communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, which is not limited herein. The corresponding communication component 1405 may therefore include: Wi-Fi module, Bluetooth module, NFC module, etc.
In an exemplary embodiment, the electronic Device 1400 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for executing the above-mentioned pattern recognition code recognition method.
In another exemplary embodiment, there is also provided a computer readable storage medium including program instructions, which when executed by a processor, implement the steps of the above-described pattern recognition code recognition method. For example, the computer readable storage medium may be the memory 1402 described above including program instructions that are executable by the processor 1401 of the electronic device 1400 to perform the pattern recognition code recognition method described above.
In another exemplary embodiment, a computer program product is also provided, which contains a computer program executable by a programmable device, the computer program having code portions for performing the above-mentioned method of pattern recognition code recognition when executed by the programmable device.
The preferred embodiments of the present disclosure are described in detail with reference to the accompanying drawings, however, the present disclosure is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present disclosure within the technical idea of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.
It should be noted that, in the foregoing embodiments, various features described in the above embodiments may be combined in any suitable manner, and in order to avoid unnecessary repetition, various combinations that are possible in the present disclosure are not described again.
In addition, any combination of various embodiments of the present disclosure may be made, and the same should be considered as the disclosure of the present disclosure, as long as it does not depart from the spirit of the present disclosure.

Claims (9)

1. A method for identifying a pattern identification code, the method comprising:
acquiring a first image containing the pattern identification code;
acquiring a second image of the pattern identification code from the first image;
determining position information of each target corner point in the graphic identification code in the second image, wherein the target corner points comprise each vertex of the graphic identification code and other vertexes of each positioning pattern of the graphic identification code except the vertex of the graphic identification code;
identifying the pattern identification code according to the second image and the position information of each target corner point in the second image;
the acquiring the second image of the pattern recognition code from the first image comprises:
detecting the pattern recognition code in the first image to determine a pattern recognition code area in the first image;
determining a target area in the first image according to the pattern recognition code area, wherein the target area comprises the pattern recognition code area and is larger than the pattern recognition code area;
performing screenshot operation on the graphic identification code area in the target area to obtain the second image;
wherein the determining a target region in the first image according to the pattern recognition code region comprises:
extending the periphery of the pattern identification code region outwards by a preset distance to obtain an extended region;
carrying out external expansion on the expanded region to adjust the expanded region into a square region, and taking the square region as the target region;
the identifying the pattern identification code according to the second image and the position information of each target corner point in the second image comprises:
correcting the figure identification code according to the second image and the position information of each target corner point in the second image to obtain a corrected target image of the figure identification code;
and identifying the pattern identification code according to the target image and the position information of each target corner point in the target image.
2. The method according to claim 1, wherein the determining the position information of each target corner point in the pattern recognition code in the second image comprises:
and inputting the second image into a corner recognition model, and obtaining the position information of each target corner output by the corner recognition model in the second image.
3. The method of claim 1, wherein said correcting said pattern identification code comprises:
determining the positions of the central points of at least two positioning patterns according to the position information of each target corner point in the second image;
and rotating the second image according to the determined angle between the connecting line of the central point positions of any two positioning patterns and a preset direction so as to correct the pattern identification code.
4. The method of claim 1, wherein said correcting said pattern identification code comprises:
determining the proportion of the average side length of the positioning pattern to the average side length of the pattern identification code according to the position information of each target corner point in the second image;
determining the position information of each target corner point in the target image according to the proportion;
and correcting the pattern recognition code through a spline interpolation algorithm according to the position information of each target corner point in the target image.
5. The method according to claim 1, wherein the identifying the pattern recognition code according to the target image and the position information of each target corner point in the target image comprises:
carrying out external expansion processing on the target image;
determining the position information of each target corner point in the target image after the external expansion processing according to the position information of each target corner point in the target image;
and identifying the pattern identification code according to the target image subjected to the external expansion processing and the position information of each target corner point in the target image subjected to the external expansion processing.
6. The method of claim 1, further comprising:
under the condition that the identification result is not obtained, performing up-sampling processing on the target image;
and re-identifying the pattern identification code according to the image obtained after the up-sampling processing is carried out on the target image.
7. An apparatus for recognizing a pattern recognition code, the apparatus comprising:
a first acquisition module configured to acquire a first image containing the pattern recognition code;
a second obtaining module configured to obtain a second image of the pattern recognition code from the first image;
a determining module configured to determine position information of each target corner point in the graphical identification code in the second image, wherein the target corner point comprises each vertex of the graphical identification code and other vertices of each positioning pattern of the graphical identification code except for the vertex of the graphical identification code;
the identification module is configured to identify the pattern identification code according to the second image and the position information of each target corner point in the second image;
the second acquisition module includes:
a detection sub-module configured to detect a pattern recognition code in the first image to determine a pattern recognition code region in the first image;
a first determining submodule configured to determine a target region in the first image according to the pattern recognition code region, wherein the target region includes the pattern recognition code region and is larger than the pattern recognition code region;
a screenshot operation sub-module configured to perform a screenshot operation on the pattern recognition code region in the target region to obtain the second image;
the first determining submodule is configured to expand the periphery of the pattern recognition code region outwards by a preset distance to obtain an expanded region; carrying out external expansion on the expanded region to adjust the expanded region into a square region, and taking the square region as the target region;
the identification module comprises: the first correction submodule is configured to correct the figure identification code according to the second image and position information of each target corner point in the second image so as to obtain a corrected target image of the figure identification code; and the first identification submodule is configured to identify the pattern identification code according to the target image and the position information of each target corner point in the target image.
8. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
9. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory to carry out the steps of the method of any one of claims 1 to 6.
CN202010509898.0A 2020-06-08 2020-06-08 Method and device for identifying pattern identification code, storage medium and electronic equipment Active CN111428707B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010509898.0A CN111428707B (en) 2020-06-08 2020-06-08 Method and device for identifying pattern identification code, storage medium and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010509898.0A CN111428707B (en) 2020-06-08 2020-06-08 Method and device for identifying pattern identification code, storage medium and electronic equipment

Publications (2)

Publication Number Publication Date
CN111428707A CN111428707A (en) 2020-07-17
CN111428707B true CN111428707B (en) 2020-11-10

Family

ID=71551437

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010509898.0A Active CN111428707B (en) 2020-06-08 2020-06-08 Method and device for identifying pattern identification code, storage medium and electronic equipment

Country Status (1)

Country Link
CN (1) CN111428707B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101059834A (en) * 2007-05-31 2007-10-24 中国农业大学 QR two-dimensional bar code recognition method based on pickup head for chatting
CN103258344A (en) * 2013-04-10 2013-08-21 山东华戎信息产业有限公司 Method for automatically extracting texture in plant three-dimensional reconstruction
CN104008359A (en) * 2014-04-18 2014-08-27 杭州晟元芯片技术有限公司 Accurate grid sampling method used for recognizing QR code
CN104346597A (en) * 2014-10-29 2015-02-11 中山大学 QR (quick response) code detection and correction extraction method and IP (intellectual property) core
CN105138945A (en) * 2015-09-25 2015-12-09 三明学院 Identification method of two-dimensional code on surface of rebar
US20160358318A1 (en) * 2015-01-29 2016-12-08 Boe Technology Group Co., Ltd. Image correction method, image correction apparatus and video system
CN106485182A (en) * 2016-06-27 2017-03-08 中国计量大学 A kind of fuzzy Q R code restored method based on affine transformation
CN110046529A (en) * 2018-12-11 2019-07-23 阿里巴巴集团控股有限公司 Two-dimensional code identification method, device and equipment
CN111104813A (en) * 2019-12-16 2020-05-05 北京达佳互联信息技术有限公司 Two-dimensional code image key point detection method and device, electronic equipment and storage medium

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104573601A (en) * 2013-10-28 2015-04-29 江苏联海通信技术有限公司 Recognition system for DPM two-dimension code of device in complex environment
CN105701434A (en) * 2015-12-30 2016-06-22 广州卓德信息科技有限公司 Image correction method for two-dimensional code distorted image
JP2019095953A (en) * 2017-11-21 2019-06-20 小林クリエイト株式会社 Two-dimensional code for preventing forgery of printed matter and printed matter having two-dimensional code
CN109993018A (en) * 2019-04-04 2019-07-09 哈尔滨理工大学 It is a kind of based on the two dimensional code identifying system of Zynq heterogeneous platform and recognition methods
CN110879593A (en) * 2019-11-11 2020-03-13 江苏理工学院 Positioning method, reading method, positioning system and positioning device
CN111163343A (en) * 2020-01-20 2020-05-15 海信视像科技股份有限公司 Method for recognizing pattern recognition code and display device

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101059834A (en) * 2007-05-31 2007-10-24 中国农业大学 QR two-dimensional bar code recognition method based on pickup head for chatting
CN103258344A (en) * 2013-04-10 2013-08-21 山东华戎信息产业有限公司 Method for automatically extracting texture in plant three-dimensional reconstruction
CN104008359A (en) * 2014-04-18 2014-08-27 杭州晟元芯片技术有限公司 Accurate grid sampling method used for recognizing QR code
CN104346597A (en) * 2014-10-29 2015-02-11 中山大学 QR (quick response) code detection and correction extraction method and IP (intellectual property) core
US20160358318A1 (en) * 2015-01-29 2016-12-08 Boe Technology Group Co., Ltd. Image correction method, image correction apparatus and video system
CN105138945A (en) * 2015-09-25 2015-12-09 三明学院 Identification method of two-dimensional code on surface of rebar
CN106485182A (en) * 2016-06-27 2017-03-08 中国计量大学 A kind of fuzzy Q R code restored method based on affine transformation
CN110046529A (en) * 2018-12-11 2019-07-23 阿里巴巴集团控股有限公司 Two-dimensional code identification method, device and equipment
CN111104813A (en) * 2019-12-16 2020-05-05 北京达佳互联信息技术有限公司 Two-dimensional code image key point detection method and device, electronic equipment and storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
《数字图象处理之二维码图像提取算法(九)二维码位置探测图案进行精确定位》;Snail_Walker;《CSDN》;20141212;第3页第2段、第二幅图 *

Also Published As

Publication number Publication date
CN111428707A (en) 2020-07-17

Similar Documents

Publication Publication Date Title
US9946954B2 (en) Determining distance between an object and a capture device based on captured image data
US9697416B2 (en) Object detection using cascaded convolutional neural networks
US10699134B2 (en) Method, apparatus, storage medium and device for modeling lane line identification, and method, apparatus, storage medium and device for identifying lane line
US10664919B2 (en) Systems and methods for mobile image capture and processing
CN106651955B (en) Method and device for positioning target object in picture
KR102126300B1 (en) Method and apparatus for generating an all-in-focus image
EP2921997B1 (en) Two-dimensional code
US9519968B2 (en) Calibrating visual sensors using homography operators
CN107220578B (en) Two-dimensional code scanning and identifying method and device, mobile terminal and storage medium
US8803918B2 (en) Methods and apparatus for calibrating focused plenoptic camera data
US7342572B2 (en) System and method for transforming an ordinary computer monitor into a touch screen
US7606439B2 (en) Method for extracting raw data from an image resulting from a camera shot
US8600167B2 (en) System for capturing a document in an image signal
US20170124386A1 (en) Method, device and computer-readable medium for region recognition
JP2017520050A (en) Local adaptive histogram flattening
US9275281B2 (en) Mobile image capture, processing, and electronic form generation
US20140240467A1 (en) Image processing method and apparatus for elimination of depth artifacts
US9305360B2 (en) Method and apparatus for image enhancement and edge verification using at least one additional image
KR101613637B1 (en) Method, device, program and storage medium for detecting straight line
KR20150116833A (en) Image processor with edge-preserving noise suppression functionality
JP2019523500A (en) Method and system for recognizing position information of two-dimensional code
US8897598B1 (en) Mosaicing documents for translation using video streams
US10679363B2 (en) Image noise reduction
EP2974261A2 (en) Systems and methods for classifying objects in digital images captured using mobile devices
US8411962B1 (en) Robust image alignment using block sums

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
GR01 Patent grant
GR01 Patent grant