A sled number plate recognition method and system, computer device and storage medium

Abstract

The application is suitable for the technical field of image processing, and provides a slide number plate recognition method, system, computer device and storage medium, acquires a number plate image; carries out preprocessing on the number in the number plate image, then segments the preprocessed number plate image to obtain a number region image with the smallest area that can be recognized; sequentially recognizes the number region image and outputs a recognition result; in the positioning of the number plate, the difference between the brightness of the number and the brightness of the bottom plate is used to accurately position the position of the number plate; in actual use, the acquisition efficiency of high-quality license plate information is significantly improved, and the threshold of image recognition is reduced. In the segmentation of the number plate, the error of subsequent segmentation is reduced through number preprocessing, the recognition area is reduced, the recognition workload is reduced, and the recognition speed and accuracy are improved.

Description

Technical Field

[0001] This invention belongs to the field of image processing technology, and in particular relates to a skid license plate recognition method, system, computer equipment, and storage medium. Background Technology

[0002] With the development of science and technology and the continuous improvement of people's living standards, automobiles have entered thousands of households. Automobile production is a complex assembly line industrial chain, which includes the combination of various parts. Simply put, it includes four major steps: stamping, welding, painting and final assembly. Each step requires continuous and accurate processing on the assembly line, which puts forward high requirements for processing.

[0003] Throughout the entire automobile production line, the manufacturing process of each car relies on a rolling skid, which acts as a support to hold the car's chassis in place. To better distinguish the uniqueness of each car, a number plate is fixed to the edge of each rolling skid. This number plate consists of numbers that determine the car's model, paint color, and other industrial design elements. Therefore, accurately identifying the numbers on the number plates greatly reduces the rework rate in automobile manufacturing and minimizes factory losses.

[0004] However, the movement of the rolling skid often uses a trigger-based mode. When it moves to a certain production workshop, the trigger sensor stops it in a certain area, after which the robot arm or worker will perform the corresponding automotive process. Due to the weight of the vehicle body and the control precision issues when the trigger sensor is activated, the position where the skid stops will vary each time. Since the camera position is fixed, the different positions of the skid and the different angles when the license plate is installed pose a significant challenge to license plate recognition.

[0005] Current recognition methods often use industrial cameras to capture images of the character portions of chip boxes. After obtaining the original image, the image is binarized, the image resolution is changed to adapt to the display, and dilation and erosion are performed. After preprocessing, the characters are recognized using a pre-trained YAML file, and the recognition results are controlled.

[0006] Although it can perform recognition, the requirements for the images to be recognized are quite demanding. It requires good image acquisition conditions and high image quality, resulting in an unsatisfactory actual recognition success rate. Summary of the Invention

[0007] The purpose of this invention is to provide a skid license plate recognition method, which aims to solve the technical problems existing in the prior art as identified in the background art.

[0008] This invention is implemented as follows: acquiring a license plate image;

[0009] The numbers in the license plate image are preprocessed, and then the preprocessed license plate image is segmented to obtain the smallest recognizable number region image.

[0010] The number area image is sequentially identified, and the identification results are output.

[0011] For example, the step of acquiring the license plate image specifically includes:

[0012] Image acquisition equipment captures images of license plates with skids;

[0013] Location processing is performed on images containing skid license plate information;

[0014] For example, the step of locating the image containing the skid license plate information specifically includes:

[0015] The images containing the skid license plate information are captured through a traversal process using a set acquisition window.

[0016] Images whose bright-to-dark ratio conforms to a preset range are selected from the images collected through traversal, forming the first image set;

[0017] The image with the highest number of bright spots in the first image set is identified as the license plate image to be identified.

[0018] For example, the step of preprocessing the numbers in the license plate image specifically includes:

[0019] First, the image of the license plate to be identified is subjected to median filtering to obtain the median-filtered image;

[0020] Finally, the median-filtered image is subjected to morphological processing to obtain the closed image.

[0021] For example, the subsequent segmentation of the preprocessed license plate image to obtain a number region image with the smallest identifiable area specifically includes:

[0022] The edge information of the closed image is extracted and its bounding rectangle is extracted. Rectangles that meet the set conditions are selected to obtain a set of rectangles.

[0023] Extract the bounding rectangles of the corresponding number from the set of rectangles;

[0024] For example, the step of extracting the bounding rectangle of the corresponding number from the rectangle set specifically includes:

[0025] Calculate the center point of all rectangles in the rectangle set to obtain the rectangle center point set. Sort the rectangle center points in the rectangle center point set and the rectangles in the rectangle set in order.

[0026] Set each center point in the set of center points of rectangles as a reference point, and then iterate through each center point in the set of rectangles using the center points set as reference points.

[0027] Obtain the corresponding number of target center points;

[0028] For example, the step of extracting the bounding rectangle of the corresponding number from the set of rectangles further includes:

[0029] The area difference between the rectangle corresponding to the target center point and the rectangles in the rectangle set is calculated sequentially.

[0030] Export the rectangles with the smallest area difference corresponding to the target center point in sequence;

[0031] For example, the step of sequentially recognizing the number area image and outputting the recognition result specifically involves:

[0032] Import the exported rectangle into the recognition network to identify the license plate number and output the recognition result.

[0033] A skid-mounted license plate recognition system includes:

[0034] The image acquisition module is used to acquire images containing skid license plate information;

[0035] The processing module performs positioning processing on the image containing the skid license plate information, performs noise reduction processing on the image obtained from the positioning processing, and then segments the noise-reduced image to sequentially export the corresponding number of recognizable smallest area number region images.

[0036] The recognition module sequentially recognizes the number area image and outputs the license plate information to the receiving end.

[0037] The beneficial effects of the embodiments of the present invention are:

[0038] 1. In terms of license plate positioning, the difference between the brightness of the numbers and the brightness of the background plate is used to accurately locate the position of the license plate. In actual use, this has significantly improved the efficiency of obtaining high-quality license plate information and lowered the threshold for image recognition.

[0039] 2. In the segmentation of license plates, number preprocessing reduces the error of subsequent segmentation, shrinks the recognition area, reduces the workload of recognition, and improves the speed and accuracy of recognition. Attached Figure Description

[0040] Figure 1 A flowchart illustrating a skid-mounted license plate recognition method provided in an embodiment of the present invention;

[0041] Figure 2A timing diagram of a skid license plate recognition method provided in an embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram of a skid-mounted license plate recognition system provided in an embodiment of the present invention;

[0043] Figure 4 This is an internal structure diagram of the processing module provided in an embodiment of the present invention;

[0044] Figure 5 An actual field acquisition image provided for an embodiment of the present invention;

[0045] Figure 6 This is another actual field-collected image provided for an embodiment of the present invention;

[0046] Figure 7 A segmentation image of a license plate image is provided for one embodiment. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0048] It is understood that the terms "first," "second," etc., used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are used only to distinguish one element from another. For example, without departing from the scope of this application, a first script may be referred to as a second script, and similarly, a second script may be referred to as a first script.

[0049] Figure 1 A flowchart of a skid-mounted license plate recognition method provided in an embodiment of the present invention is shown below. Figure 1 As shown, it includes:

[0050] The image acquisition device captures images containing license plate information; performs positioning processing on the images containing license plate information; performs traversal image acquisition on the images containing license plate information through a set acquisition window; obtains images from the traversed images whose bright-dark point ratio meets a preset range to form a first image set; identifies the image with the most bright spots in the first image set as the license plate image to be identified; performs median filtering on the license plate image to be identified to obtain a median-filtered image; then performs morphological processing on the median-filtered image to obtain a closing operation image; extracts the edge information of the closing operation image and performs... The process involves extracting bounding rectangles, filtering out rectangles that meet set criteria, and extracting bounding rectangles corresponding to the number of license plate numbers from this set. The center points of all rectangles in the set are calculated to obtain a set of center points. The center points and rectangles in this set are then sorted sequentially. Each center point in the set is set as a reference point, and this reference point is used to iterate through each center point in the set. This yields a corresponding number of target center points. The area difference between the rectangles corresponding to these target center points and the rectangles in the set is calculated sequentially. The rectangles with the smallest area difference corresponding to the target center points are then exported. Finally, the exported rectangles are imported into a recognition network for identification, and the license plate recognition results are output.

[0051] like Figure 2 As shown, a method with Figure 1 The timing diagram shown illustrates a skid-mounted license plate recognition method, which specifically includes the following steps:

[0052] Obtain license plate image;

[0053] The numbers in the license plate image are preprocessed, and then the preprocessed license plate image is segmented to obtain the smallest recognizable number region image.

[0054] The number area image is sequentially identified, and the identification results are output.

[0055] In one embodiment, Figure 3 A skid-mounted license plate recognition system is shown. The system includes an image acquisition module, a processing module, and a recognition module, wherein:

[0056] The image acquisition module can be a camera, CCTV camera, or similar device, used to acquire images containing skid license plate information, such as... Figure 5 , Figure 6 The image shown;

[0057] The processing module can be a server, desktop computer, mobile computer, etc. It performs location processing on the image containing the license plate information, denoises the resulting image, segments the denoised image, and sequentially exports a corresponding number of the smallest identifiable number region images. Figure 7 The image shown;

[0058] The recognition module can be a mobile device with a camera or a remote host connected to the camera. It sequentially recognizes the number area image and outputs the license plate information to the receiving end.

[0059] Figure 4 An internal structural diagram of a processing module in one embodiment is shown. The processing module can be a computer device, which includes a processor, memory, network interface, input device, and display screen connected via a system bus. The memory includes non-volatile storage media and internal memory. The non-volatile storage media of the computer device stores an operating system and may also store a computer program. When executed by the processor, this computer program enables the processor to implement a skid-mounted license plate recognition method. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to implement a skid-mounted license plate recognition method. The display screen of the computer device can be a liquid crystal display (LCD) or an e-ink display. The input device of the computer device can be a touch layer covering the display screen, or buttons, a trackball, or a touchpad located on the casing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0060] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0061] In one embodiment, a computer device is provided, the computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: acquiring a license plate image; preprocessing the numbers in the license plate image, and then segmenting the preprocessed license plate image to obtain a number region image with the smallest identifiable area; sequentially identifying the number region image and outputting the identification result.

[0062] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the processor performs the following steps: acquiring a license plate image; preprocessing the numbers in the license plate image, and then segmenting the preprocessed license plate image to obtain a number region image with the smallest identifiable area; sequentially identifying the number region image and outputting the identification result.

[0063] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0064] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a non-volatile...

[0065] The program, when executed, may include the processes described in the five embodiments above, as contained in the volatile computer-readable storage medium. Any references to memory, storage, databases, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory...

[0066] This may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0067] 5. The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0068] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0069] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for identifying license plate numbers using a skid, characterized in that, The method includes: Acquiring a license plate image; specifically, this step includes: capturing an image of a skid-mounted license plate with an image acquisition device; performing positioning processing on the image containing the skid-mounted license plate information; specifically, this step of performing positioning processing on the image containing the skid-mounted license plate information includes: performing traversal image acquisition on the image containing the skid-mounted license plate information through a set acquisition window; selecting images from the traversally acquired images whose bright-dark point ratio meets a preset range to form a first image set; identifying the image with the most bright points in the first image set as the license plate image to be identified; The license plate image is preprocessed, and then the preprocessed license plate image is segmented to obtain a number region image with the smallest identifiable area. This segmentation specifically includes: extracting edge information from the closed-loop image and extracting its bounding rectangles, filtering out rectangles that meet set conditions to obtain a rectangle set; extracting the corresponding number of bounding rectangles for each number from the rectangle set; calculating the center points of all rectangles in the rectangle set to obtain a rectangle center point set; sorting the center points and rectangles in the rectangle center point set in order; setting each center point in the rectangle center point set as a reference point; iterating through each center point in the rectangle set using the reference points to obtain the corresponding number of target center points; and extracting the corresponding number of bounding rectangles for each number from the rectangle set. This step also includes: calculating the area difference between the rectangle corresponding to the target center point and the rectangles in the rectangle set; exporting the rectangles with the smallest area difference corresponding to the target center point; and then importing the exported rectangles into a recognition network for recognition, outputting the license plate recognition result. The number area image is sequentially identified, and the identification results are output.

2. The method according to claim 1, characterized in that, The step of preprocessing the numbers in the license plate image specifically includes: First, the image of the license plate to be identified is subjected to median filtering to obtain the median-filtered image; Finally, the median-filtered image is subjected to morphological processing to obtain the closed image.

3. A skid plate recognition system, used to implement the skid plate recognition method according to any one of claims 1 to 2, characterized in that, include: The image acquisition module is used to acquire images containing skid license plate information; The processing module performs positioning processing on the image containing the skid license plate information, performs noise reduction processing on the image obtained from the positioning processing, and then segments the noise-reduced image to sequentially export the corresponding number of recognizable smallest area number region images. The recognition module sequentially recognizes the number area image and outputs the license plate information to the receiving end.

4. A computer device, characterized in that, The system includes a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the skid license plate recognition method according to any one of claims 1 to 2.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, causes the processor to perform the steps of the skid license plate recognition method according to any one of claims 1 to 2.

Images