CN113723399A - License plate image correction method, license plate image correction device and storage medium - Google Patents
License plate image correction method, license plate image correction device and storage medium Download PDFInfo
- Publication number
- CN113723399A CN113723399A CN202110902411.XA CN202110902411A CN113723399A CN 113723399 A CN113723399 A CN 113723399A CN 202110902411 A CN202110902411 A CN 202110902411A CN 113723399 A CN113723399 A CN 113723399A
- Authority
- CN
- China
- Prior art keywords
- license plate
- image
- corrected
- rectangular frame
- points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The application discloses a license plate image correction method, a license plate image correction device and a storage medium, wherein the method comprises the following steps: processing an image to be corrected including a license plate to be processed based on an image segmentation network to obtain a first license plate mask image, wherein the image segmentation network comprises an encoder and a decoder, the encoder is used for encoding the image to be corrected to obtain a feature map, and the decoder is used for decoding the feature map according to the correction reference image size corresponding to the license plate to be processed to obtain the first license plate mask image; calculating corner points of the license plate in the image to be corrected and an external rectangular frame of the license plate based on the first license plate mask image; and based on the external rectangular frame and the angular points, correcting the image of the license plate to obtain a corrected license plate image. Through the mode, the correction effect of the license plate can be improved.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a license plate image correction method, a license plate image correction device and a storage medium.
Background
Due to the influence of factors such as an image shooting angle or a vehicle body posture of a target vehicle hanging a license plate, the obtained license plate always has a certain angle in each degree of freedom of a space, and certain difficulty is caused to a series of subsequent processing such as license plate recognition, license plate classification or tracking and the like. License plate correction techniques can be divided into two major categories: the license plate correction technology based on the traditional image processing method and the license plate correction method based on deep learning have the problems that the influence of noise is large, the correction result of the whole license plate cannot be obtained, or the correction effect is poor.
Disclosure of Invention
The application provides a license plate image correction method, a license plate image correction device and a storage medium, which can improve the correction effect of a license plate.
In order to solve the technical problem, the technical scheme adopted by the application is as follows: a license plate image correction method is provided, and the method comprises the following steps: processing an image to be corrected including a license plate to be processed based on an image segmentation network to obtain a first license plate mask image, wherein the image segmentation network comprises an encoder and a decoder, the encoder is used for encoding the image to be corrected to obtain a feature map, and the decoder is used for decoding the feature map according to the correction reference image size corresponding to the license plate to be processed to obtain the first license plate mask image; calculating corner points of the license plate in the image to be corrected and an external rectangular frame of the license plate based on the first license plate mask image; and based on the external rectangular frame and the angular points, correcting the image of the license plate to obtain a corrected license plate image.
In order to solve the above technical problem, another technical solution adopted by the present application is: the license plate image correction device comprises a memory and a processor which are connected with each other, wherein the memory is used for storing a computer program, and the computer program is used for realizing the license plate image correction method in the technical scheme when being executed by the processor.
In order to solve the above technical problem, another technical solution adopted by the present application is: there is provided a computer-readable storage medium for storing a computer program, which, when executed by a processor, is used to implement the license plate image rectification method of the above technical solution.
Through the scheme, the beneficial effects of the application are that: inputting an image to be corrected into an image segmentation network to obtain a first license plate mask image, wherein the image to be corrected comprises a license plate to be corrected, the image segmentation network comprises an encoder and a decoder, the encoder encodes the image to be corrected to obtain a feature map, and the decoder decodes the feature map according to the correction reference image size corresponding to the license plate to be corrected to obtain the first license plate mask image; processing the first license plate mask image to obtain corner points of the license plate in the image to be corrected and an external rectangular frame of the license plate; then processing the external rectangular frame and the angular points to realize the correction of the image of the license plate; due to the adoption of the image segmentation network, compared with a correction scheme based on the traditional image processing, the method can effectively resist noise interference; and the corner points and the external rectangular frame of the license plate are obtained by utilizing the first license plate mask image, and then the license plate image is subjected to perspective transformation by utilizing the corner points and the vertexes of the external rectangular frame, so that the image correction is realized, the correction accuracy is higher, the correction effect is better, and the integral correction of the license plate can be realized.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts. Wherein:
fig. 1 is a schematic flowchart illustrating an embodiment of a license plate image rectification method provided in the present application;
FIG. 2(a) is a schematic diagram of an image to be corrected provided by the present application;
FIG. 2(b) is a schematic illustration of a first license plate mask image corresponding to the image to be rectified in FIG. 2 (a);
FIG. 3 is a schematic flowchart illustrating another embodiment of a license plate image rectification method according to the present application;
FIG. 4 is a schematic diagram of a salient object detection network provided herein;
FIG. 5(a) is another schematic diagram of an image to be corrected provided by the present application;
FIG. 5(b) is a schematic view of a second tile mask image corresponding to FIG. 5 (a);
FIG. 5(c) is a schematic diagram of a bounding rectangular frame of the license plate region in FIG. 5 (b);
FIG. 5(d) is a schematic illustration of an intermediate license plate image provided herein;
FIG. 5(e) is a schematic diagram of a rectified license plate image provided herein;
FIG. 6 is a schematic structural diagram of an embodiment of a license plate image rectification device provided in the present application;
FIG. 7 is a schematic structural diagram of an embodiment of a computer-readable storage medium provided in the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a schematic flowchart illustrating an embodiment of a license plate image rectification method provided in the present application, where the method includes:
step 11: and processing the image to be corrected containing the license plate to be processed based on the image segmentation network to obtain a first license plate mask image.
The image to be corrected is an image of a license plate to be processed, which contains deformation such as horizontal inclination, vertical inclination or trapezoidal distortion, and the image to be corrected can be captured by utilizing the camera equipment or can be acquired from an image database; then, inputting an image to be corrected into an image segmentation image, so that an image segmentation network segments the image to be corrected, and a segmentation result (namely a first license plate mask image) is generated; specifically, the first license plate mask image is a binary image, that is, the image segmentation network can divide the input image to be corrected into two types, in this embodiment, the image segmentation network divides the image to be corrected into a region where a license plate is located (that is, a license plate region) and a region where other objects/backgrounds except the license plate are located (that is, a non-license plate region), and finally forms the first license plate mask image.
Furthermore, the image segmentation network comprises an encoder and a decoder, wherein the encoder is used for encoding the image to be corrected to obtain a characteristic diagram; the decoder is used for decoding the characteristic image according to the size of the correction reference image corresponding to the license plate to be processed to obtain a first license plate mask image; specifically, the size of the correction reference image is related to image parameters (such as image quality, image size, image format or whether the background of the license plate to be processed is relatively complex) corresponding to the license plate to be processed in the image to be corrected, and when the image quality is higher or the size of the license plate to be processed is larger, the size of the correction reference image can be smaller; and the size of the first license plate mask image changes following the size of the correction reference image, and when the size of the correction reference image becomes larger, the size of the first license plate mask image becomes larger.
In a specific embodiment, the image segmentation network may be a salient object detection network, and the image to be corrected is sent to the salient object detection network to obtain the first license plate mask image. The saliency target detection is an image segmentation method, and the saliency target detection based on deep learning can be regarded as a special case of image semantic segmentation, and the whole image is segmented into a foreground region and a background region; the structure of the saliency target detection network is approximately the same as that of the image semantic segmentation network, and the saliency target detection network is divided into an encoder and a decoder, wherein the last layer of the decoder is a prediction layer; in the stage of an encoder, the size of the feature map is continuously reduced through the processing of a down-sampling layer; at the decoder stage, the size of the feature map is gradually reduced to the size of the original image (i.e., the input image of the salient object detection network) through the processing of the up-sampling layer.
In the embodiment, the license plate is taken as a foreground target, and the saliency target detection network can extract all pixels in the license plate area to obtain a complete mask of the license plate; for example, as shown in fig. 2(a) -2(b), fig. 2(a) shows an image to be corrected, fig. 2(b) shows a first license plate mask image, the pixel value of the license plate region 21 is 0, and the pixel value of the non-license plate region 22 is 255, it can be understood that the embodiment only takes 0 and 255 as examples, and the pixel value of the first license plate mask image can be set by itself in practical applications.
In other embodiments, after an image to be corrected captured by the image capturing device is acquired, preprocessing (such as scaling, cropping, filtering, or image enhancement) may be performed on the image to be corrected, so as to improve the quality of the image or reduce the amount of data that needs to be processed.
Step 12: and calculating the corner points of the license plate in the image to be corrected and the external rectangular frame of the license plate based on the first license plate mask image.
After the first license plate mask image is obtained, license plate image correction post-processing can be carried out; specifically, the first license plate mask image is processed to obtain the outline (i.e. license plate outline) of the area (i.e. license plate area) where the license plate is located in the first license plate mask image, wherein the outline is a pixel point on the outermost edge of the license plate area; then, calculating a circumscribed rectangular frame of the license plate area in the first license plate mask image; and then, four angular points (namely, an upper left angular point, a lower left angular point, an upper right angular point and a lower right angular point of the license plate) of the license plate are calculated by utilizing the license plate outline and the external rectangular frame.
Further, when the size of the first license plate mask image is the same as that of the image to be recognized, the license plate area in the first license plate mask image is the area where the license plate in the image to be recognized is located; when the size of the first license plate mask image is different from that of the image to be recognized, the license plate area in the first license plate mask image can be zoomed according to the size ratio of the first license plate mask image to the image to be recognized, so that the area where the license plate is located in the image to be corrected is obtained.
Step 13: and based on the external rectangular frame and the angular points, correcting the image of the license plate to obtain a corrected license plate image.
After the corner points of the license plate and the external rectangular frame of the license plate in the image to be corrected are obtained, the image where the license plate is located (recorded as the license plate image) can be corrected by adopting a common algorithm (for example, through perspective transformation).
The correction method provided by the embodiment extracts the license plate position and the license plate boundary through the image segmentation network, is simple to implement, greatly reduces processing steps, enhances the resistance to noise, and can process various license plates with stronger universality compared with the scheme provided by the embodiment which can only process blue license plates in order to prevent noise interference in the related art. In addition, the scheme provided by the embodiment can be used for independently processing the license plate to obtain the corrected license plate image, the subsequent recognition network is not relied on, so that the corrected license plate is more flexible to use, the image segmentation network directly outputs the pixel level mask of the license plate instead of indirectly correcting through the recognition effect, the correction accuracy is higher, and the correction effect is better; in addition, the method can effectively solve the problem of large angle of the license plate, and is beneficial to assisting subsequent tasks of further license plate identification, classification or tracking and the like.
Referring to fig. 3, fig. 3 is a schematic flowchart illustrating another embodiment of a license plate image rectification method provided in the present application, the method including:
step 31: and processing the image to be corrected containing the license plate to be processed based on the image segmentation network to obtain a first license plate mask image.
The image segmentation network comprises an encoder and a decoder, the feature map needs to be restored to the size of an original image at the decoder stage, and since semantic segmentation is a pixel-level classification, and the shape of an object to be predicted has uncertainty, in order to accurately obtain the boundary of the object, prediction has to be performed on the feature map in proportion to the size of the original image, so that the calculation amount is huge and the time consumption is high; based on the embodiment, improvement is carried out, the characteristics of the license plate target are fully considered in the designed network structure, and the calculated amount is reduced.
In the embodiment, the inclined license plate is a quadrangle, if the inclined license plate is subjected to downsampling, the slopes of four sides of the inclined license plate are kept unchanged, the core parameters of license plate image correction are not influenced, but the maximum precision loss value caused by downsampling N times of an original feature map is +/-N pixels, so that the time consumption can be reduced by proper downsampling, and the subsequent correction is not influenced; therefore, the feature map is restored to a certain size in the decoder, for example: and the size of the feature graph is reduced to one fourth of the size of the original graph, so that time consumption and precision can be considered.
In a specific embodiment, as shown in fig. 4, the image 41 to be corrected is input into a saliency target detection network (not identified in the figure) that includes a residual block 42, a maximum pooling layer 43, a processing layer 44, and an upsampling layer 45, the processing layer 44 includes a convolution layer, a Batch Normalization layer (BN), and an activation layer (not identified in the figure), and the activation function of the activation layer may use a modified Linear Units (ReLU); after being processed by the saliency-object detection network, the first license plate mask image 46 is output, and it can be seen that the size of the first license plate mask image 46 is smaller than that of the image 41 to be corrected.
Step 32: and adjusting the size of the first license plate mask image to the size of the image to be corrected to obtain a second license plate mask image.
After the first license plate mask image is acquired, the size of the first license plate mask image can be adjusted, so that the size of the generated second license plate mask image is equal to the size of the image to be corrected. For example, as shown in FIG. 4, the first license plate mask image 46 is enlarged to obtain a second license plate mask image 47.
Step 33: and acquiring the outline of the license plate area in the second license plate mask image.
The second license plate mask image comprises a license plate region, the license plate region in the second license plate mask image is the same as the license plate region where the license plate in the image to be corrected is located, the second license plate mask image is a binary image, and the binary image is subjected to contour extraction processing to obtain the contour of the license plate region; for example, the contour may be acquired by performing edge detection processing on the second signboard mask image; or because the binary image only has two pixel values, a pixel threshold (for example, 255) can be set, whether the gray difference value between a certain pixel point and a circle of surrounding pixel points is greater than or equal to the pixel threshold is compared, if yes, the pixel point is a pixel point on the contour, so that which pixel points in all pixel points in the license plate area are the pixel points on the contour are judged, and all the screened pixel points form the contour.
Step 34: based on the contour, corner points and a circumscribed rectangle frame are determined.
The outline comprises a plurality of pixel points, the abscissa of the upper left corner of the circumscribed rectangular frame is the minimum of the abscissas in all the pixel points, and the height and the width of the circumscribed rectangular frame can be determined based on the coordinate values of the pixel points, so that the position of the circumscribed rectangular frame is determined; specifically, the maximum value of the abscissa in all the pixel points and the minimum value of the abscissa in all the pixel points can be obtained, and the maximum value of the abscissa and the minimum value of the abscissa are subtracted to obtain the height of the circumscribed rectangular frame; and obtaining the maximum value of the vertical coordinates in all the pixel points and the minimum value of the vertical coordinates in all the pixel points, and subtracting the maximum value of the vertical coordinates from the minimum value of the vertical coordinates to obtain the width of the external rectangular frame.
Because the acquired second license plate mask image is at a pixel level, the outline of the second license plate mask image is not necessarily quadrilateral, and four corners of the outline are not necessarily right angles, the outline of the second license plate mask image and an external rectangular frame are adopted to determine the corner points of the license plate area in the embodiment; specifically, after the position of the external rectangular frame is obtained, the distance between each vertex of the external rectangular frame and all pixel points in the license plate area is calculated; selecting the pixel points closest to each vertex as the corners, wherein the corners of the license plate region correspond to the vertices of the external rectangular frame one by one, namely, for each vertex of the external rectangular frame, circularly traversing all the pixel points on the outline to obtain the pixel points closest to the vertex, wherein the pixel points are the original corners of the license plate before correction, and the four vertices of the external rectangular frame are the corrected target corners.
It is understood that the four corner points of the license plate region can also be obtained by other methods, such as: and calculating four edges of the license plate region, and then calculating intersection points of the four edges, wherein the corner points of the license plate region are the intersection points.
Step 35: and cutting out an image corresponding to the circumscribed rectangular frame from the image to be corrected to obtain a middle license plate image.
The position of a license plate area in the second license plate mask image is the same as that of a license plate area in the image to be corrected, and the position of a circumscribed rectangular frame of the license plate area in the second license plate mask image is the same as that of the circumscribed rectangular frame of the license plate area in the image to be corrected; and after the position of the external rectangular frame in the second license plate mask image is obtained, recording the position of the image to be corrected, which is the same as the position of the external rectangular frame, as the external license plate position, and cutting the image to be corrected along the external license plate position to obtain an intermediate license plate image.
Step 36: and establishing a coordinate system by taking the upper left corner of the middle license plate image as a coordinate origin, and respectively calculating coordinate values of the corner points and the vertexes of the external rectangular frame in the coordinate system.
And after the middle license plate image is obtained, calculating new coordinates of the license plate area in the middle license plate image and new coordinates of the circumscribed rectangular frame. For example, if the upper left corner position of the external rectangular frame in the image to be corrected is (M1, N1), and the height and width of the external rectangular frame are a and b, respectively, the upper left corner position of the external rectangular frame in the middle license plate image is (1, 1), the upper right corner position is (1, b), the lower left corner position is (a, 1), and the lower right corner position is (a, b).
Step 37: and generating a corrected license plate image based on the coordinate values of the vertexes, the coordinate values of the angular points and the middle license plate image.
Firstly, calculating a transformation matrix by using the coordinate values of the angular points and the coordinate values of the vertexes; and then, carrying out perspective transformation on the image of the license plate in the middle license plate image by using the transformation matrix to obtain the corrected license plate image. It is understood that the calculation method of the transformation matrix and the perspective transformation is the same as that in the prior art, and will not be described herein.
In the embodiment, the license plate is corrected through perspective transformation, and compared with a correction scheme based on traditional image processing, the post-processing scheme designed by the embodiment can accurately extract the original corner points of the license plate and the target corner points of the license plate by means of the license plate mask obtained through saliency target detection, neglects noise interference, and has higher correction accuracy.
In a specific embodiment, the image to be corrected shown in fig. 5(a) is processed by the above-mentioned saliency target detection network to obtain a second license plate mask image; then, obtaining the outline of the second license plate mask image to obtain an outline frame shown in fig. 5(c), and obtaining an extreme value of the second license plate mask image in the horizontal and vertical directions to obtain a circumscribed rectangular frame of the license plate by using the extreme value, as shown in fig. 5 (b); cutting out the license plate from the image to be corrected according to the circumscribed rectangular frame of the license plate to obtain a middle license plate image, as shown in fig. 5 (d); then, according to the original angular point and the target angular point of the license plate, a transformation matrix of perspective transformation can be obtained; the original license plate is subjected to perspective transformation according to the transformation matrix to obtain a corrected license plate image, as shown in fig. 5 (e).
In the embodiment, a significant target detection network is combined with a license plate image correction post-processing method to correct the license plate, significant target detection is used as the license plate extraction method to accurately extract each pixel point belonging to the license plate, and then the post-processing method can accurately obtain four corner points of the license plate and correct the four corner points through perspective transformation; because the license plate mask is extracted by adopting the method for detecting the salient object, compared with the traditional method for extracting the boundary angular points of the license plate, the method is more accurate, can resist the influence of noise, and is suitable for correcting various license plate images; the improved saliency target detection network can reduce the license plate to a certain proportion of the original characteristic diagram in the decoding stage, and then the license plate image can be corrected, so that the correction effect and the time consumption are both considered; in addition, the scheme provided by the embodiment can directly correct the license plate image, does not need to depend on a license plate recognition network, can obtain an independent license plate image correction result, and has a good correction effect and good use flexibility after the license plate image correction.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an embodiment of a license plate image rectification device provided in the present application, in which the license plate image rectification device 60 includes a memory 61 and a processor 62 connected to each other, the memory 61 is used for storing a computer program, and the computer program is used for implementing the license plate image rectification method in the foregoing embodiment when being executed by the processor 62.
The license plate image correction device provided by the embodiment combines the saliency target detection and the correction post-processing, and the license plate image correction post-processing can effectively analyze the license plate mask provided by the saliency target detection network, realize the license plate image correction and simultaneously output the license plate position and the correction result.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an embodiment of a computer-readable storage medium 70 provided in the present application, where the computer-readable storage medium 70 is used for storing a computer program 71, and the computer program 71 is used for implementing the license plate image rectification method in the foregoing embodiment when being executed by a processor.
The computer readable storage medium 70 may be a server, a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes.
In the several embodiments provided in the present application, it should be understood that the disclosed method and apparatus may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of modules or units is merely a logical division, and an actual implementation may have another division, 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.
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 embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings, or which are directly or indirectly applied to other related technical fields, are intended to be included within the scope of the present application.
Claims (10)
1. A license plate image correction method is characterized by comprising the following steps:
processing an image to be corrected including a license plate to be processed based on an image segmentation network to obtain a first license plate mask image, wherein the image segmentation network comprises an encoder and a decoder, the encoder is used for encoding the image to be corrected to obtain a feature map, and the decoder is used for decoding the feature map according to the correction reference image size corresponding to the license plate to be processed to obtain the first license plate mask image;
calculating corner points of the license plate in the image to be corrected and a circumscribed rectangular frame of the license plate based on the first license plate mask image;
and correcting the image of the license plate based on the external rectangular frame and the angular points to obtain a corrected license plate image.
2. The license plate image rectification method of claim 1, wherein the size of the first license plate mask image is smaller than the size of the image to be rectified, and the step of calculating corner points of the license plate in the image to be rectified and a circumscribed rectangular frame of the license plate based on the first license plate mask image comprises:
adjusting the size of the first license plate mask image to the size of the image to be corrected to obtain a second license plate mask image;
acquiring the outline of a license plate region in the second license plate mask image, wherein the license plate region in the second license plate mask image is the same as the region where the license plate in the image to be corrected is located;
and determining the corner points and the circumscribed rectangle frame based on the outline.
3. The license plate image rectification method of claim 2, wherein the outline includes a plurality of pixel points, the abscissa of the upper left corner of the circumscribed rectangle frame is the minimum of the abscissas of all the pixel points, and the step of determining the corner points and the circumscribed rectangle frame based on the outline includes:
and determining the height and the width of the circumscribed rectangular frame based on the coordinate values of the pixel points.
4. The license plate image rectification method of claim 3, wherein the step of determining the height and width of the circumscribed rectangle based on the coordinate values of the pixel points comprises:
obtaining the maximum value of the abscissa in all the pixel points and the minimum value of the abscissa in all the pixel points, and subtracting the maximum value of the abscissa from the minimum value of the abscissa to obtain the height of the circumscribed rectangular frame;
and obtaining the maximum value of the vertical coordinates in all the pixel points and the minimum value of the vertical coordinates in all the pixel points, and subtracting the maximum value of the vertical coordinates from the minimum value of the vertical coordinates to obtain the width of the external rectangular frame.
5. The license plate image rectification method of claim 2, wherein the step of determining the corner points and the circumscribed rectangle frame based on the contour further comprises:
calculating the distance between each vertex of the circumscribed rectangular frame and all pixel points in the license plate area;
and selecting the pixel point closest to the vertex as the angular point.
6. The license plate image correction method according to claim 1, wherein the step of correcting the image of the license plate based on the circumscribed rectangle and the corner points to obtain a corrected license plate image comprises:
cutting out an image corresponding to the circumscribed rectangular frame from the image to be corrected to obtain a middle license plate image;
establishing a coordinate system by taking the upper left corner of the middle license plate image as a coordinate origin, and respectively calculating coordinate values of the corner and the vertex of the circumscribed rectangular frame in the coordinate system;
and generating the corrected license plate image based on the coordinate values of the vertexes, the coordinate values of the angular points and the middle license plate image.
7. The license plate image rectification method of claim 6, wherein the step of generating the rectified license plate image based on the coordinate values of the vertices, the coordinate values of the corners, and the intermediate license plate image comprises:
calculating a transformation matrix by using the coordinate values of the angular points and the coordinate values of the vertexes;
and carrying out perspective transformation on the image of the license plate in the middle license plate image by using the transformation matrix to obtain the corrected license plate image.
8. The license plate image rectification method of claim 2, wherein the second license plate mask image is a binary image, and the step of obtaining the contour of the license plate region in the second license plate mask image further comprises:
and carrying out contour extraction processing on the binary image to obtain the contour.
9. A license plate image rectification apparatus comprising a memory and a processor connected to each other, wherein the memory is configured to store a computer program, and the computer program is configured to implement the license plate image rectification method according to any one of claims 1 to 8 when executed by the processor.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, is configured to implement the license plate image rectification method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110902411.XA CN113723399A (en) | 2021-08-06 | 2021-08-06 | License plate image correction method, license plate image correction device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110902411.XA CN113723399A (en) | 2021-08-06 | 2021-08-06 | License plate image correction method, license plate image correction device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113723399A true CN113723399A (en) | 2021-11-30 |
Family
ID=78675080
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110902411.XA Pending CN113723399A (en) | 2021-08-06 | 2021-08-06 | License plate image correction method, license plate image correction device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113723399A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114332447A (en) * | 2022-03-14 | 2022-04-12 | 浙江大华技术股份有限公司 | License plate correction method, license plate correction device and computer readable storage medium |
| CN115937003A (en) * | 2022-11-02 | 2023-04-07 | 深圳市新良田科技股份有限公司 | Image processing method, image processing device, terminal equipment and readable storage medium |
| CN116030047A (en) * | 2023-03-24 | 2023-04-28 | 四川中星电子有限责任公司 | Method for identifying mask qualification in capacitor process |
-
2021
- 2021-08-06 CN CN202110902411.XA patent/CN113723399A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114332447A (en) * | 2022-03-14 | 2022-04-12 | 浙江大华技术股份有限公司 | License plate correction method, license plate correction device and computer readable storage medium |
| CN114332447B (en) * | 2022-03-14 | 2022-08-09 | 浙江大华技术股份有限公司 | License plate correction method, license plate correction device and computer readable storage medium |
| CN115937003A (en) * | 2022-11-02 | 2023-04-07 | 深圳市新良田科技股份有限公司 | Image processing method, image processing device, terminal equipment and readable storage medium |
| CN116030047A (en) * | 2023-03-24 | 2023-04-28 | 四川中星电子有限责任公司 | Method for identifying mask qualification in capacitor process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110414507B (en) | License plate recognition method and device, computer equipment and storage medium | |
| EP1693783B1 (en) | Fast method of object detection by statistical template matching | |
| CN113723399A (en) | License plate image correction method, license plate image correction device and storage medium | |
| CN109978839B (en) | Method for detecting wafer low-texture defects | |
| US8401333B2 (en) | Image processing method and apparatus for multi-resolution feature based image registration | |
| CN111583097A (en) | Image processing method, image processing device, electronic equipment and computer readable storage medium | |
| CN114529459B (en) | Method, system and medium for enhancing image edge | |
| CN111914698B (en) | Human body segmentation method, segmentation system, electronic equipment and storage medium in image | |
| JP2009020613A (en) | Image processing program, image processing method, and image processor | |
| CN112800964A (en) | Remote sensing image target detection method and system based on multi-module fusion | |
| CN111680690B (en) | Character recognition method and device | |
| CN110580680A (en) | face super-resolution method and device based on combined learning | |
| CN111353961A (en) | Document curved surface correction method and device | |
| CN114049499A (en) | Target object detection method, apparatus and storage medium for continuous contour | |
| CN115331245A (en) | Table structure identification method based on image instance segmentation | |
| CN111209908B (en) | Method, device, storage medium and computer equipment for updating annotation frame | |
| CN116052152A (en) | License plate recognition system based on contour detection and deep neural network | |
| Zhou et al. | Fast and resource-efficient hardware implementation of modified line segment detector | |
| CN114674826A (en) | Visual detection method and detection system based on cloth | |
| CN112733855B (en) | Table structuring method, table recovering device and device with storage function | |
| Fang et al. | 1-D barcode localization in complex background | |
| CN113542868A (en) | Video key frame selection method and device, electronic equipment and storage medium | |
| CN109785367B (en) | Method and device for filtering foreign points in three-dimensional model tracking | |
| CN113228105A (en) | Image processing method and device and electronic equipment | |
| CN112418210B (en) | Intelligent classification method for tower inspection information |
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 |