CN111950659A - Double-layer license plate image processing method and device, electronic equipment and storage medium - Google Patents
Double-layer license plate image processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111950659A CN111950659A CN202010907037.8A CN202010907037A CN111950659A CN 111950659 A CN111950659 A CN 111950659A CN 202010907037 A CN202010907037 A CN 202010907037A CN 111950659 A CN111950659 A CN 111950659A
- Authority
- CN
- China
- Prior art keywords
- license plate
- affine transformation
- image
- layer
- generate
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/625—License plates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Image Analysis (AREA)
Abstract
The application provides a double-layer license plate image processing method, a double-layer license plate image processing device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring an original license plate image, and generating an image training sample; putting the image training sample into a convolutional neural network to obtain standard feature points; performing inclination correction according to the preset boundary characteristic points and the standard characteristic points to generate affine transformation parameters; and cutting the original license plate image according to the affine transformation parameters to generate a target image. The method solves the problems of single source of license plate data, low reliability of calculation results, narrow application range and low precision in the prior art.
Description
Technical Field
The application relates to the field of computer data storage, in particular to a double-layer license plate image processing method and device, electronic equipment and a storage medium.
Background
The existing license plate cutting method generally adopts the following procedures: 1. roughly positioning the license plate by a certain method to obtain the initial position of the license plate; 2. then, Radon (Radon) transformation or horizontal and vertical projection of the regions is used for the initial license plate regions one by one; 3. calculating the approximate horizontal and vertical inclination angles of the license plate according to the calculated characteristic information; 4. performing inclination correction on the initial license plate area through the calculated horizontal and vertical inclination angles; 5. acquiring horizontal and vertical projection views of the license plate after inclination correction; 6. and (4) cutting the license plates one by one through projection.
The existing method has the following defects: 1. the dependence on license plate positioning is large, and the subsequent inclination angle calculation is directly influenced by the positioning accuracy; 2. the inclination angle calculation method depends on a fixed operator, and the calculation result is unreliable under the conditions of fouling, shielding and the like of the license plate; 3. the calculation amount and the memory requirement of the inclination angle calculation method are large, the calculation is carried out region by region, and the inclination angle calculation method is not suitable for the conditions of multiple license plates (bayonets, illegal parking snapshot and the like); 4. the inclination angle calculation method is designed for a single-layer license plate, and has a poor effect on a double-layer license plate; 5. the inclination correction is only rough angle correction, and the removal work of an invalid region cannot be carried out, so that great interference is brought to the subsequent license plate cutting work.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method and an apparatus for processing a double-layer license plate image, an electronic device, and a storage medium, so as to solve technical problems in the prior art.
In a first aspect, an embodiment of the present application provides a method for processing a double-layer license plate image, including: acquiring an original license plate image, and generating an image training sample; putting the image training sample into a convolutional neural network to obtain standard feature points; performing inclination correction according to the preset boundary characteristic points and the standard characteristic points to generate affine transformation parameters; and cutting the original license plate image according to the affine transformation parameters to generate a target image.
In one embodiment, the putting the image training samples into a convolutional neural network to obtain standard feature points includes: randomly generating a plurality of pieces of initial characteristic point information according to the image training sample; and counting the position information of a preset number of initial characteristic points according to the initial characteristic point information to generate standard characteristic points.
In an embodiment, performing tilt correction according to the preset boundary feature points and the standard feature points to generate affine transformation parameters includes: dividing an original license plate image into a first layer of correction area and a second layer of correction area according to preset boundary characteristic points; calculating offset information of the preset boundary characteristic points according to the image training samples and the preset boundary characteristic points; and generating a first affine transformation parameter of the first layer correction area and a second affine transformation parameter of the second layer correction area according to the first layer correction area, the second layer correction area and the offset information.
In an embodiment, the cutting an original license plate image according to affine transformation parameters to generate a target image includes: performing affine transformation inverse operation on the first affine transformation parameters to generate a first corrected image; and performing affine transformation inverse operation on the second affine transformation parameters to generate a second corrected image.
In a second aspect, an embodiment of the present application further provides a double-layer license plate image processing apparatus, including: the sample generation module is used for acquiring an original license plate image and generating an image training sample; the characteristic acquisition module is used for putting the image training sample into a convolutional neural network to acquire standard characteristic points; the affine transformation module is used for performing inclination correction according to the preset boundary characteristic points and the standard characteristic points to generate affine transformation parameters; and the image generation module is used for cutting the original license plate image according to the affine transformation parameters to generate a target image.
In an embodiment, the feature obtaining module is further configured to: randomly generating a plurality of pieces of initial characteristic point information according to the image training sample; and counting the position information of a preset number of initial characteristic points according to the initial characteristic point information to generate standard characteristic points.
In one embodiment, the affine transformation module is further configured to: dividing an original license plate image into a first layer of correction area and a second layer of correction area according to preset boundary characteristic points; calculating offset information of the preset boundary characteristic points according to the image training samples and the preset boundary characteristic points; and generating a first affine transformation parameter of the first layer correction area and a second affine transformation parameter of the second layer correction area according to the first layer correction area, the second layer correction area and the offset information.
In one embodiment, the image generation module is further configured to: performing affine transformation inverse operation on the first affine transformation parameters to generate a first corrected image; and performing affine transformation inverse operation on the second affine transformation parameters to generate a second corrected image.
In a third aspect, an embodiment of the present application further provides an electronic device, including: a memory to store a computer program; a processor configured to perform the method of any of the preceding embodiments.
In a fourth aspect, an embodiment of the present application further provides a non-transitory electronic device readable storage medium, including: a program, when executed by an electronic device, causes the electronic device to perform the method of any of the preceding embodiments.
The double-layer license plate image processing method, the double-layer license plate image processing device, the electronic equipment and the storage medium overcome the defects of the conventional method through algorithm optimization, improve the robustness of the license plate inclination correction algorithm, reduce the time consumption and the memory requirement, and simultaneously completely support the inclination correction of the double-layer license plate. Specifically, the following aspects are provided:
1. and obtaining the inclination information of the license plate in a license plate characteristic point positioning mode.
2. Aiming at the problem of inaccurate positioning of the double-layer license plate, the number of the feature points can be increased to 6.
3. And directly decoupling the double-layer license plate into two independent single-layer license plates through the feature points distributed in different ways.
4. The license plate feature point positioning function and the license plate detection are combined into the same full-volume machine network, so that the calculation amount and the memory consumption caused by a single feature point calculation process are avoided.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure;
fig. 2 is a schematic view of an application scene of a double-layer license plate image processing method according to an embodiment of the present application;
fig. 3 is a flowchart of a double-layer license plate image processing method according to an embodiment of the present disclosure;
fig. 4 is a flowchart of another double-layer license plate image processing method according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a double-layer license plate image processing device according to an embodiment of the present disclosure.
Icon: the system comprises an electronic device 1, a bus 10, a processor 11, a memory 12, a user terminal 100, a server 200, a double-layer license plate image processing device 500, an image acquisition module 501, a target detection module 502, a feature acquisition module 503 and a feature matching module 504.
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.
As shown in fig. 1, the present embodiment provides an electronic apparatus 1 including: at least one processor 11 and a memory 12, one processor being exemplified in fig. 1. 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.
In an embodiment, the electronic device 1 may combine the license plate location and the license plate feature point location into the same full-convolution network, calculate the specific position of the feature point in the picture through the offset, input the obtained feature point information and the standard feature point information into the tilt correction algorithm to calculate two sets of affine transformation parameters, and perform affine transformation inverse operation through the two sets of correction parameters, thereby obtaining two sets of independent image information.
Fig. 2 is a schematic view of an application scenario of the double-layer license plate image processing method provided in this embodiment. As shown in fig. 2, the application scenario may include a user terminal 100, and the user terminal 100 may be a smartphone, a tablet computer, or a drone with a photographing function. The user terminal 100 can execute the double-layer license plate image processing method provided by the application, and the calculation efficiency of double-layer license plate image processing is accelerated.
According to the requirement, the application scenario may further include a server 200, and the server 200 may be a server, a server cluster, or a cloud computing center. The server 200 may receive the image uploaded by the user terminal 100, execute the image processing method provided by the present application, and perform segmentation and classification according to the captured image.
Please refer to fig. 3, which is a flowchart illustrating a method for processing a dual-layer license plate image according to an embodiment of the present disclosure, where the method is executed by the electronic device 1 shown in fig. 1 and is used in the interactive scenario shown in fig. 2. The method comprises the following steps:
step 301: and acquiring an original license plate image, and generating an image training sample.
In this step, license plate location and license plate feature point location can be combined into the same full convolution network, offset prediction of a plurality of feature points is added on the basis of original license plate location output, and specific positions of the feature points in the picture are calculated through the offsets.
In an embodiment, the offset prediction of 6 feature points is added on the basis of the original license plate positioning output, namely, four vertices M1, M2, M5 and M6 of the license plate and two endpoints M3 and M4 of a boundary line between two upper and lower lines of characters of a double-layer license plate. Among them, the upper layer divided images are in the frame ranges of M1, M2, M3, and M4, and the lower layer divided images are in the frame ranges of M3, M4, M5, and M6. For example, the first row of the double-layer license plate represents the two characters of the administrative region as "chuan a", the second row is numbered as "12345", and the two characters can be converted into a row of form "chuan a 12345" after being divided and recombined.
Step 302: and putting the image training sample into a convolutional neural network to obtain standard feature points.
In this step, in the generation training stage, a large amount of feature point information is randomly generated to count a set of standard feature point position information, which is referred to as a standard feature point as a reference standard.
Step 303: and performing inclination correction according to the preset boundary characteristic points and the standard characteristic points to generate affine transformation parameters.
In the step, the obtained characteristic point information and the standard characteristic point information are input into a tilt correction algorithm, and the tilt correction algorithm calculates two groups of affine transformation parameters according to the affine transformation principle. First tier license correction parameters from M1 to M4 and second tier license correction parameters from M3 to M6, respectively.
Step 304: and cutting the original license plate image according to the affine transformation parameters to generate a target image.
In the step, two groups of independent image information can be obtained by running affine transformation inverse operation through two groups of correction parameters, wherein the first group is an upper half image of the license plate, and the second group is a lower half image of the license plate. While correcting, the algorithm can also remove invalid license plate information.
After passing through the license plate rectification portion, the double layer license plate has been cut into two separate single layer license plates. And the license plates are aligned in the horizontal direction, so that the cut license plates can be obtained only by calculating one more projection in the vertical direction.
Please refer to fig. 4, which is a flowchart illustrating another method for processing a dual-layer license plate image according to an embodiment of the present disclosure, which can be executed by the electronic device 1 shown in fig. 1 and used in the interactive scenario shown in fig. 2. The method comprises the following steps:
step 401: and acquiring an original license plate image, and generating an image training sample. For details, refer to the description of step 301 in the above embodiment.
Step 402: and randomly generating a plurality of pieces of initial characteristic point information according to the image training sample.
In this step, in the generation training stage, a large amount of feature point information is randomly generated to count a set of standard feature point position information.
Step 403: and counting the position information of a preset number of initial characteristic points according to the initial characteristic point information to generate standard characteristic points.
In this step, a large amount of feature point information is randomly generated to count up a set of standard feature point position information as a reference standard.
Step 404: and dividing the original license plate image into a first layer of correction area and a second layer of correction area according to the preset boundary characteristic points.
In this step, the four vertices M1, M2, M5, M6 of the license plate, and the two endpoints M3, M4 of the boundary line between the upper and lower lines of characters of the double-layer license plate. Wherein, the frame body ranges of M1, M2, M3 and M4 are first layer correction areas, and the frame body ranges of M3, M4, M5 and M6 are second layer correction areas.
Step 405: and calculating offset information of the preset boundary characteristic points according to the image training samples and the preset boundary characteristic points.
In this step, license plate location and license plate feature point location can be combined into the same full convolution network, offset prediction of a plurality of feature points is added on the basis of original license plate location output, and specific positions of the feature points in the picture are calculated through the offsets.
Step 406: and generating a first affine transformation parameter of the first layer correction area and a second affine transformation parameter of the second layer correction area according to the first layer correction area, the second layer correction area and the offset information.
In the step, the obtained feature point information and the standard feature point information are input into a tilt correction algorithm, and the tilt correction algorithm calculates two groups of affine transformation parameters according to the affine transformation principle. Parameters for correcting the first floor license plate of M1 to M4 and the second floor license plate of M3 to M6, respectively.
Step 407: and performing affine transformation inverse operation on the first affine transformation parameters to generate a first corrected image.
Step 408: and performing affine transformation inverse operation on the second affine transformation parameters to generate a second corrected image.
In the step, two groups of independent image information can be obtained by performing affine transformation inverse operation on two groups of correction parameters, wherein the first group is the upper half part image of the license plate, and the second group is the lower half part image of the license plate. While correcting, the algorithm can also remove invalid license plate information.
In one embodiment, after passing through the license plate rectification portion, the double layer license plate has been cut into two separate single layer license plates. And the license plate information is aligned in the horizontal direction, so that the completely cut license plate information can be obtained only by calculating one more projection in the vertical direction.
Please refer to fig. 5, which is a block diagram of an embodiment of the present application, and further provides a double-layer license plate image processing apparatus 500, which can be executed by the electronic device 1 shown in fig. 1 and used in the interactive scenario shown in fig. 2, so as to combine license plate positioning and license plate feature point positioning into a same full-convolution network, calculate a specific position of a feature point in a picture through an offset, input obtained feature point information and standard feature point information into a tilt correction algorithm to calculate two sets of affine transformation parameters, and perform an affine transformation inverse operation through the two sets of correction parameters, thereby obtaining two sets of independent image information. The double-deck license plate image processing apparatus 500 includes: a sample generation module 501, a feature acquisition module 502, an affine transformation module 503, and an image generation module 504. The specific principle relationship is as follows:
the sample generating module 501 is configured to obtain an original license plate image and generate an image training sample. Please refer to the description of step 301 in the above embodiments.
And the feature obtaining module 502 is configured to put the image training samples into a convolutional neural network to obtain standard feature points. Please refer to the description of step 302 in the above embodiment.
In an embodiment, the feature obtaining module 502 is further configured to: randomly generating a plurality of pieces of initial characteristic point information according to the image training sample; and counting the position information of a preset number of initial characteristic points according to the initial characteristic point information to generate standard characteristic points. Please refer to the description of steps 401 and 402 in the above embodiments.
And the affine transformation module 503 is configured to perform tilt correction according to the preset boundary feature points and the standard feature points, and generate affine transformation parameters. Please refer to the description of step 303 in the above embodiments.
In an embodiment, the affine transformation module 503 is further configured to: dividing an original license plate image into a first layer of correction area and a second layer of correction area according to preset boundary characteristic points; calculating offset information of the preset boundary characteristic points according to the image training samples and the preset boundary characteristic points; and generating a first affine transformation parameter of the first layer correction area and a second affine transformation parameter of the second layer correction area according to the first layer correction area, the second layer correction area and the offset information. Please refer to the description of steps 403-406 in the above embodiment.
And the image generation module 504 is configured to cut the original license plate image according to the affine transformation parameters to generate a target image. Please refer to the description of step 304 in the above embodiment.
In one embodiment, the image generation module 504 is further configured to: performing affine transformation inverse operation on the first affine transformation parameters to generate a first corrected image; and performing affine transformation inverse operation on the second affine transformation parameters to generate a second corrected image. Please refer to the description of steps 407 and 408 in the above embodiment.
The double-layer license plate image processing method, the double-layer license plate image processing device, the electronic equipment and the storage medium overcome the defects of the conventional method through algorithm optimization, improve the robustness of the license plate inclination correction algorithm, reduce the time consumption and the memory requirement, and simultaneously completely support the inclination correction of the double-layer license plate. Specifically, the following aspects are provided:
1. and obtaining the inclination information of the license plate in a license plate characteristic point positioning mode.
2. Aiming at the problem of inaccurate positioning of the double-layer license plate, the number of the feature points can be increased to 6.
3. And directly decoupling the double-layer license plate into two independent single-layer license plates through the feature points distributed in different ways.
4. The license plate feature point positioning function and the license plate detection are combined into the same full-volume machine network, so that the calculation amount and the memory consumption caused by a single feature point calculation process are avoided.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
In addition, units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
Furthermore, the 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.
It should be noted that the functions, if implemented in the form of software functional modules and sold or used as independent products, 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: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A double-layer license plate image processing method is characterized by comprising the following steps:
acquiring an original license plate image, and generating an image training sample;
putting the image training sample into a convolutional neural network to obtain standard feature points;
performing inclination correction according to preset boundary characteristic points and the standard characteristic points to generate affine transformation parameters;
and cutting the original license plate image according to the affine transformation parameters to generate a target image.
2. The method of claim 1, wherein the projecting the image training samples into a convolutional neural network to obtain standard feature points comprises:
randomly generating a plurality of pieces of initial characteristic point information according to the image training samples;
and counting the position information of the initial characteristic points in a preset quantity according to the initial characteristic point information to generate the standard characteristic points.
3. The method according to claim 2, wherein the performing the tilt correction according to the preset boundary feature points and the standard feature points to generate affine transformation parameters comprises:
dividing the original license plate image into a first layer of correction area and a second layer of correction area according to the preset boundary characteristic points;
calculating offset information of the preset boundary feature points according to the image training samples and the preset boundary feature points;
and generating a first affine transformation parameter of the first layer correction area and a second affine transformation parameter of the second layer correction area according to the first layer correction area, the second layer correction area and the offset information.
4. The method of claim 3, wherein the cutting the original license plate image according to the affine transformation parameters to generate a target image comprises:
performing affine transformation inverse operation on the first affine transformation parameters to generate a first corrected image;
and performing affine transformation inverse operation on the second affine transformation parameters to generate a second corrected image.
5. A double-deck license plate image processing apparatus, comprising:
the sample generation module is used for acquiring an original license plate image and generating an image training sample;
the characteristic acquisition module is used for putting the image training sample into a convolutional neural network to acquire standard characteristic points;
the affine transformation module is used for carrying out inclination correction according to the preset boundary characteristic points and the standard characteristic points to generate affine transformation parameters;
and the image generation module is used for cutting the original license plate image according to the affine transformation parameters to generate a target image.
6. The apparatus of claim 5, wherein the feature acquisition module is further configured to:
randomly generating a plurality of pieces of initial characteristic point information according to the image training samples;
and counting the position information of the initial characteristic points in a preset quantity according to the initial characteristic point information to generate the standard characteristic points.
7. The apparatus of claim 6, wherein the affine transformation module is further configured to:
dividing the original license plate image into a first layer of correction area and a second layer of correction area according to the preset boundary characteristic points;
calculating offset information of the preset boundary feature points according to the image training samples and the preset boundary feature points;
and generating a first affine transformation parameter of the first layer correction area and a second affine transformation parameter of the second layer correction area according to the first layer correction area, the second layer correction area and the offset information.
8. The apparatus of claim 7, wherein the image generation module is further configured to:
performing affine transformation inverse operation on the first affine transformation parameters to generate a first corrected image;
and performing affine transformation inverse operation on the second affine transformation parameters to generate a second corrected image.
9. An electronic device, comprising:
a memory to store a computer program;
a processor to perform the method of any one of claims 1 to 4.
10. A non-transitory electronic device readable storage medium, comprising: program which, when run by an electronic device, causes the electronic device to perform the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010907037.8A CN111950659B (en) | 2020-09-01 | 2020-09-01 | Double-layer license plate image processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010907037.8A CN111950659B (en) | 2020-09-01 | 2020-09-01 | Double-layer license plate image processing method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111950659A true CN111950659A (en) | 2020-11-17 |
| CN111950659B CN111950659B (en) | 2022-12-09 |
Family
ID=73367966
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010907037.8A Active CN111950659B (en) | 2020-09-01 | 2020-09-01 | Double-layer license plate image processing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111950659B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105528605A (en) * | 2014-09-28 | 2016-04-27 | 江苏省兴泽实业发展有限公司 | Double-layer license plate character segmentation method based on projection and recognition |
| CN107679531A (en) * | 2017-06-23 | 2018-02-09 | 平安科技（深圳）有限公司 | Licence plate recognition method, device, equipment and storage medium based on deep learning |
| WO2018090771A1 (en) * | 2016-11-16 | 2018-05-24 | 杭州海康威视数字技术股份有限公司 | Vehicle license plate recognition method and apparatus |
| CN109447117A (en) * | 2018-09-25 | 2019-03-08 | 平安科技（深圳）有限公司 | The double-deck licence plate recognition method, device, computer equipment and storage medium |
| CN109766805A (en) * | 2018-12-28 | 2019-05-17 | 安徽清新互联信息科技有限公司 | A kind of double-deck license plate character recognition method based on deep learning |
| CN110059683A (en) * | 2019-04-15 | 2019-07-26 | 广州广电银通金融电子科技有限公司 | A kind of license plate sloped antidote of wide-angle based on end-to-end neural network |
| US20190251369A1 (en) * | 2018-02-11 | 2019-08-15 | Ilya Popov | License plate detection and recognition system |
| CN110163199A (en) * | 2018-09-30 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Licence plate recognition method, license plate recognition device, car license recognition equipment and medium |
| CN110728283A (en) * | 2019-10-11 | 2020-01-24 | 高新兴科技集团股份有限公司 | License plate type identification method and device |
-
2020
- 2020-09-01 CN CN202010907037.8A patent/CN111950659B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105528605A (en) * | 2014-09-28 | 2016-04-27 | 江苏省兴泽实业发展有限公司 | Double-layer license plate character segmentation method based on projection and recognition |
| WO2018090771A1 (en) * | 2016-11-16 | 2018-05-24 | 杭州海康威视数字技术股份有限公司 | Vehicle license plate recognition method and apparatus |
| CN107679531A (en) * | 2017-06-23 | 2018-02-09 | 平安科技（深圳）有限公司 | Licence plate recognition method, device, equipment and storage medium based on deep learning |
| US20190251369A1 (en) * | 2018-02-11 | 2019-08-15 | Ilya Popov | License plate detection and recognition system |
| CN109447117A (en) * | 2018-09-25 | 2019-03-08 | 平安科技（深圳）有限公司 | The double-deck licence plate recognition method, device, computer equipment and storage medium |
| CN110163199A (en) * | 2018-09-30 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Licence plate recognition method, license plate recognition device, car license recognition equipment and medium |
| CN109766805A (en) * | 2018-12-28 | 2019-05-17 | 安徽清新互联信息科技有限公司 | A kind of double-deck license plate character recognition method based on deep learning |
| CN110059683A (en) * | 2019-04-15 | 2019-07-26 | 广州广电银通金融电子科技有限公司 | A kind of license plate sloped antidote of wide-angle based on end-to-end neural network |
| CN110728283A (en) * | 2019-10-11 | 2020-01-24 | 高新兴科技集团股份有限公司 | License plate type identification method and device |
Non-Patent Citations (2)
| Title |
|---|
| WANWEI WANG等: "A Light CNN for End-to-End Car License Plates Detection and Recognition", 《IEEE ACCESS》 * |
| 裴明涛 等: "基于多尺度模板匹配和部件模型的车牌字符分割方法", 《北京理工大学学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111950659B (en) | 2022-12-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112771573B (en) | Depth estimation method and device based on speckle images and face recognition system | |
| CN109784250B (en) | Positioning method and device of automatic guide trolley | |
| US20180253852A1 (en) | Method and device for locating image edge in natural background | |
| CN111325798B (en) | Camera model correction method, device, AR implementation equipment and readable storage medium | |
| CN109461133B (en) | Bridge bolt falling detection method and terminal equipment | |
| CN109934873B (en) | Method, device and equipment for acquiring marked image | |
| CN111161348B (en) | Object pose estimation method, device and equipment based on monocular camera | |
| WO2022147655A1 (en) | Positioning method and apparatus, spatial information acquisition method and apparatus, and photographing device | |
| KR102421604B1 (en) | Image processing methods, devices and electronic devices | |
| CN111950659B (en) | Double-layer license plate image processing method and device, electronic equipment and storage medium | |
| CN116977671A (en) | Target tracking method, device, equipment and storage medium based on image space positioning | |
| CN111369531A (en) | Image definition grading method, equipment and storage device | |
| CN110660091A (en) | Image registration processing method and device and photographing correction operation system | |
| CN116012242A (en) | Camera distortion correction effect evaluation method, device, medium and equipment | |
| CN116993654A (en) | Camera module defect detection method, device, equipment, storage medium and product | |
| CN111238369B (en) | Method, system and equipment for measuring volume of double rectangular objects | |
| CN114723883A (en) | Three-dimensional scene reconstruction method, device, equipment and storage medium | |
| CN113840135A (en) | Color cast detection method, device, equipment and storage medium | |
| CN111833441A (en) | Face three-dimensional reconstruction method and device based on multi-camera system | |
| CN111633337A (en) | Reflection eliminating method and device for laser welding seam measurement | |
| CN112967398B (en) | Three-dimensional data reconstruction method and device and electronic equipment | |
| CN117593547A (en) | Commodity area detection method, commodity area detection device, terminal equipment and medium | |
| JP2017010555A (en) | Image processing method and image processing apparatus | |
| CN116416147A (en) | Image processing method, electronic device, and computer-readable medium | |
| CN116883385A (en) | Method and device for evaluating quality of infrared face image |
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 |