License plate auxiliary identification method and system for smart checkpoint

Abstract

The invention relates to the technical field of traffic control, in particular to a license plate auxiliary recognition method and system for an intelligent checkpoint, and the method comprises the steps: enabling a to-be-processed character to be matched with a preset character library, and obtaining a matched character; and then, according to the shape features of the matched characters, growing is carried out on the surrounding area, and a complete target character is obtained. The license plate auxiliary recognition method can cope with the conditions of shielding, fouling and the like of license plate characters, and improves the accuracy of character recognition. Through an accurate license plate auxiliary identification result, the intelligent checkpoint can accurately and automatically record and trigger corresponding traffic control measures such as fine and score deduction for illegal vehicles; the intelligent checkpoint can accurately analyze traffic data in real time through an accurate license plate auxiliary recognition result, provides timely and accurate information support for a traffic management department, and helps the traffic management department to quickly make a decision, optimize traffic flow and improve road traffic efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic control, and in particular to a license plate auxiliary recognition method and system for a smart card slot. Background Art

[0002] In scenarios such as traffic control, urban security monitoring, parking lot management, as well as in complex scenarios such as smart construction sites and smart gas stations, smart checkpoints can be set up at important traffic intersections or sections. Smart checkpoints are a collection of intelligent devices used to monitor and manage traffic flow. Through the set up smart checkpoints, not only can the basic vehicle traffic record function be realized, but it can also be combined with license plate recognition technology to use the results of license plate recognition to provide richer services and applications.

[0003] However, when smart checkpoints are combined with license plate recognition technology, license plate recognition will be affected by environmental conditions, license plate style, equipment hardware performance and other factors, reducing the accuracy of license plate recognition results. When smart checkpoints use license plate recognition results with reduced accuracy for traffic control, they will erroneously report illegal vehicles or allow illegal vehicles to pass, resulting in more traffic management errors; the traffic flow data counted by smart checkpoints will be inaccurate, which will in turn affect the reliability of traffic flow analysis, traffic planning and scheduling decisions; traffic management measures (such as travel restrictions, bans during special periods, etc.) will not be implemented properly, and traffic flow cannot be effectively controlled, which will worsen traffic congestion; for vehicles that require special attention (such as dangerous goods transport vehicles, stolen vehicles, etc.), if smart checkpoints cannot correctly identify these high-risk vehicles, these may be missed, increasing the risk to public safety.

[0004] Therefore, how to improve the accuracy of traffic control by smart checkpoints is an urgent problem that needs to be solved. Summary of the invention

[0005] In order to solve the technical problem of how to improve the accuracy of traffic control by smart checkpoints, the purpose of the present invention is to provide a license plate auxiliary recognition method and system for smart checkpoints. The technical solutions adopted are as follows: The present application provides a method for assisting license plate recognition of a smart card slot, the method comprising: Obtain the front image of the vehicle captured by the smart camera; Performing contour detection on the front image of the vehicle, and obtaining a license plate image according to the result of the contour detection, wherein the license plate image includes a plurality of characters to be processed; For any of the characters to be processed, the character to be processed is matched with a preset character library to obtain a matching character, and region growth is performed around the character to be processed according to shape features of the matching character to obtain a target character; The target character is verified according to the matching character, and when the verification result meets the preset verification condition, the target character is used as the result of the license plate auxiliary recognition, and traffic control is performed according to the result of the license plate auxiliary recognition.

[0006] In some embodiments, after obtaining the license plate image, the following steps are performed: When the license plate image is in color, grayscale processing is performed on the license plate image to obtain a grayscale image corresponding to the license plate image; Performing dilation processing on the grayscale image by using a preset structural element to obtain a grayscale image after dilation processing; Performing an erosion process on the grayscale image after the dilation process by using the preset structural element to obtain an eroded grayscale image; The grayscale image after the corrosion process is subjected to threshold segmentation process to obtain a binary license plate image, and the binary license plate image is used to match with the preset character library.

[0007] In some embodiments, matching the character to be processed with a preset character library to obtain a matching character includes: Determining a preset character library corresponding to the character to be processed according to the position of the character to be processed, and calculating the matching degree between the character to be processed and a plurality of reference characters in the preset character library; The matching character is determined from the plurality of reference characters according to the matching degree.

[0008] In some embodiments, calculating the degree of matching between the character to be processed and a plurality of reference characters in the preset character library includes: Performing corner point detection on the character to be processed to obtain a first corner point set corresponding to the character to be processed; Performing corner point detection on each of the reference characters to obtain a second corner point set corresponding to each of the reference characters; Mapping the positions of corner points in the first corner point set to the second corner point set, and determining corner points in the second corner point set that meet a preset distance threshold around the mapped positions; The matching degree between the character to be processed and each of the reference characters is obtained according to the number of corner points in the second corner point set that meet a preset distance threshold around the mapped position.

[0009] In some embodiments, performing region growing around the character to be processed according to the shape feature of the matching character includes: When a first corner point in the first corner point set is positionally mapped to the second corner point set, if there are corner points around that meet a preset distance threshold, the first corner point is used as a seed point; Setting a gray value difference threshold when filling pixels around the seed point, and setting a region growth direction according to a stroke feature corresponding to the position of the seed point in the matching character; For any of the seed points, region growing is performed around the seed point according to the gray value difference threshold and the region growing direction.

[0010] In some embodiments, performing region growing around the seed point according to the gray value difference threshold and the region growing direction includes: According to the gray value difference threshold, a plurality of pixel points are determined from around the seed point to obtain an area to be filled; Performing grayscale filling on the pixel points in the area to be filled, and connecting the seed point with the pixel points after grayscale filling to obtain a growth vector; Determining the growth possibility according to the angle between the growth direction of the region and the growth vector; The growth possibility is compared with a preset growth possibility threshold, and the region growing process is controlled according to the comparison result.

[0011] In some embodiments, controlling the region growing process according to the comparison result includes: When the comparison result shows that the growth possibility is greater than or equal to the preset growth possibility threshold, the pixel point after grayscale filling is used as a new seed point, and regional growth is performed around the new seed point according to the grayscale value difference threshold; When the comparison result is that the growth possibility is less than the preset growth possibility threshold, the region growing around the seed point is stopped.

[0012] In some embodiments, after performing region growing around the new seed point, the method further includes: Based on a new character region obtained by performing region growth around the new seed point, a plurality of edge vectors are established along the region growth direction for edge pixel points of the new character region, and the angle change difference between each two adjacent edge vectors is calculated; According to the angle change difference, the probability of the character pixel point corresponding to the edge pixel point is obtained; Determine the lateral distance between the spaced edge pixel points along the region growth direction; The process of the region growth is controlled by combining the possible degree of the character pixel points and the lateral distance.

[0013] In some embodiments, the preset verification condition includes a preset character inflection point matching degree threshold, and the target character is verified according to the matching character, and when the result of the verification meets the preset verification condition, the target character is used as the result of the license plate auxiliary recognition, including: Comparing the inflection point of the matching character with the inflection point of the target character to obtain the degree of coincidence of the inflection points of the characters; When the degree of matching of the inflection points of the characters is greater than or equal to the preset threshold value of the degree of matching of the inflection points of the characters, it is determined that the target character is the result of the auxiliary license plate recognition.

[0014] The present application also provides a smart card slot license plate auxiliary recognition system, the system comprising: An image acquisition module, used to acquire the front image of the vehicle captured by the smart camera; A contour detection module, used to perform contour detection on the front image of the vehicle, and obtain a license plate image according to the result of the contour detection, wherein the license plate image includes a plurality of characters to be processed; A region growing module, for matching any of the characters to be processed with a preset character library to obtain a matching character, and performing region growing around the character to be processed according to shape features of the matching character to obtain a target character; The character verification module is used to verify the target character according to the matching character, and when the verification result meets the preset verification condition, the target character is used as the result of the license plate auxiliary recognition, and traffic control is performed according to the result of the license plate auxiliary recognition.

[0015] The present invention has the following beneficial effects: First, obtain the front image of the vehicle collected by the smart card port; then, perform contour detection on the front image of the vehicle, and obtain a license plate image based on the result of the contour detection, wherein the license plate image includes a plurality of characters to be processed; then, for any of the characters to be processed, match the characters to be processed with a preset character library to obtain a matching character, and perform region growth around the characters to be processed based on the shape characteristics of the matching characters to obtain a target character; finally, verify the target character based on the matching characters, and when the result of the verification meets the preset verification conditions, use the target character as the result of license plate auxiliary recognition, and perform traffic control based on the result of the license plate auxiliary recognition. In the present application, the characters to be processed are matched with a preset character library to obtain matching characters; then, based on the shape characteristics of the matching characters, the surrounding area is grown to obtain a complete target character. The license plate auxiliary recognition method can cope with situations such as occlusion and contamination of license plate characters, and improve the accuracy of character recognition. Through accurate license plate auxiliary recognition results, the smart toll gate can accurately record and trigger corresponding traffic control measures such as fines and point deductions for illegal vehicles; the smart toll gate can accurately analyze traffic data in real time through accurate license plate auxiliary recognition results, and provide timely and accurate information support for traffic management departments, which helps traffic management departments make decisions quickly, optimize traffic flow, and improve road traffic efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A schematic diagram of an implementation environment of a smart card slot license plate auxiliary recognition method provided by an embodiment of the present invention; Figure 2 A flowchart of a method for assisting license plate recognition of a smart card slot provided by an embodiment of the present invention; Figure 3 A schematic diagram of a binary license plate image provided by an embodiment of the present invention; Figure 4 A schematic diagram of the structure of a smart card slot license plate auxiliary recognition system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a smart card port license plate auxiliary recognition method and system proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0019] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0021] The specific scheme of the license plate auxiliary recognition method and system of the smart card port provided by the present invention is described in detail below with reference to the accompanying drawings.

[0022] See also Figure 1 , Figure 1 The following is a schematic diagram of an implementation environment of a smart card slot license plate auxiliary recognition method provided by an embodiment of the present invention. Figure 1As shown, the implementation environment includes a license plate auxiliary recognition terminal 101 and an image acquisition terminal 102. The license plate auxiliary recognition terminal 101 may be a terminal device equipped with a license plate auxiliary recognition system, including but not limited to a laptop computer, tablet computer, handheld computer, PAD (tablet computer), desktop computer, etc. with local computing capabilities; the license plate auxiliary recognition system may be implemented in the form of a target client, and the target client may be a client that supports license plate auxiliary recognition of a smart card port, such as a video client, an instant messaging client, a browser client, etc.; the license plate auxiliary recognition terminal 101 may, but is not limited to, communicate with the image acquisition terminal 102 through a network, and the above network may include but is not limited to: a wired network, a wireless network, wherein the wired network includes: a local area network, a metropolitan area network, and a wide area network, and the wireless network includes: Bluetooth, WIFI (Wireless Fidelity, a technology that allows electronic devices to connect to a wireless local area network) and other networks that implement wireless communication. The above license plate auxiliary recognition terminal 101 may, but is not limited to, include a human-computer interaction screen, a processor, and a memory. The above human-computer interaction screen may, but is not limited to, be used to display the front image of the vehicle and the result of the license plate auxiliary recognition. The above processor may be used, but is not limited to, to respond to human-computer interaction operations, execute corresponding operations, or generate corresponding instructions.

[0023] As an optional method, the image acquisition terminal 102 is set at the smart checkpoint. When the vehicle passes through the smart checkpoint, the front image of the vehicle can be collected by the image acquisition terminal 102. The image acquisition terminal 102 may include, for example: an infrared camera, which is suitable for nighttime or low-light environments, and can provide clear images at nighttime or under low-light conditions, enhancing the system's all-weather working ability; an ordinary camera, which is the most basic image acquisition device, suitable for most conventional scenes, captures light through an optical lens, and converts the light into an electrical signal, which is then converted into a digital image by an image sensor; a panoramic camera, which is used to provide a wide range of vision, and is suitable for scenes that need to cover a wider area.

[0024] As an optional method, the license plate auxiliary recognition terminal 101 can also be a server, which can be a single server, a server cluster composed of multiple servers, or a cloud server. The above is only an example, and this embodiment does not make any limitation to this.

[0025] As an optional method, the following steps of the license plate auxiliary recognition method of the smart card port can be performed on the license plate auxiliary recognition terminal 101: Obtain the front image of the vehicle captured by the smart camera; Performing contour detection on the front image of the vehicle, and obtaining a license plate image according to the result of the contour detection, wherein the license plate image includes a plurality of characters to be processed; For any of the characters to be processed, the character to be processed is matched with a preset character library to obtain a matching character, and region growth is performed around the character to be processed according to shape features of the matching character to obtain a target character; The target character is verified according to the matching character, and when the verification result meets the preset verification condition, the target character is used as the result of the license plate auxiliary recognition, and traffic control is performed according to the result of the license plate auxiliary recognition.

[0026] In the above method, the characters to be processed are matched with the preset character library to obtain matching characters; then, according to the shape characteristics of the matching characters, the surrounding area is grown to obtain the complete target characters. The license plate auxiliary recognition method can cope with the occlusion and contamination of license plate characters and improve the accuracy of character recognition. Through accurate license plate auxiliary recognition results, the smart card gate can accurately record and trigger corresponding traffic control measures such as fines and deductions for illegal vehicles; the smart card gate can accurately analyze traffic data in real time through accurate license plate auxiliary recognition results, and provide timely and accurate information support for traffic management departments, which helps traffic management departments make decisions quickly, optimize traffic flow, and improve road traffic efficiency.

[0027] As an optional example, this embodiment does not limit the execution subject of the above-mentioned smart card port license plate auxiliary recognition method. The above-mentioned smart card port license plate auxiliary recognition method can be executed on the license plate auxiliary recognition terminal 101. For example, when the license plate auxiliary recognition terminal 101 is a desktop computer, some or all steps of the above-mentioned smart card port license plate auxiliary recognition method can be executed on the desktop computer.

[0028] The above section introduces the contents of an exemplary implementation environment for applying the technical solution of the present application. Next, we will continue to introduce the license plate auxiliary recognition method of the smart card port of the present application.

[0029] In order to solve the problem of how to improve the accuracy of traffic control by smart checkpoints in the prior art, the embodiments of the present application respectively propose a smart checkpoint license plate auxiliary recognition method and a smart checkpoint license plate auxiliary recognition system. These embodiments will be described in detail below.

[0030] See also Figure 2 , Figure 2 A flow chart of a method for assisting license plate recognition of a smart card slot provided by an embodiment of the present invention is provided. The method can be applied to Figure 1 It should be understood that the method can also be applied to other exemplary implementation environments and specifically executed by devices in other implementation environments, and this embodiment does not limit the implementation environment to which the method is applicable.

[0031] like Figure 2 As shown, in an exemplary embodiment, the license plate auxiliary recognition method of the smart card port includes at least steps S210 to S240, which are described in detail as follows: In step S210, a front image of the vehicle captured by the smart camera is obtained.

[0032] Among them, the vehicle front image refers to the image containing the front of the vehicle captured by an image acquisition terminal (such as a camera). The image can show the front structure of the vehicle, which includes: the front of the vehicle, the front bumper, the headlights, etc.

[0033] For example, a smart checkpoint is set up on a main road in a city to monitor and manage traffic flow. The smart checkpoint is equipped with a high-definition camera installed on pillars on both sides of the road. The height of the high-definition camera is about 5 meters, and the shooting direction is perpendicular to the direction of vehicle travel. When a vehicle enters the shooting range of the high-definition camera, the high-definition camera automatically starts the shooting function. The high-definition camera captures the front image of the vehicle, which clearly shows the license plate, front of the vehicle, and headlights.

[0034] In step S220, contour detection is performed on the vehicle front image, and a license plate image is obtained based on the result of the contour detection, wherein the license plate image includes a plurality of characters to be processed.

[0035] Among them, contour detection is an image processing technology used to detect the boundaries or edges of objects in an image. During contour detection, the contour lines of the object can be extracted by analyzing the pixel values ​​in the image. Common contour detection methods include Canny edge detection, Sobel operator, Laplacian operator, etc. Through contour detection, the license plate can be separated from the complex background of the front image of the vehicle.

[0036] The license plate image refers to a sub-image containing the license plate portion extracted from the front image of the vehicle. The license plate image should contain the complete license plate.

[0037] The characters to be processed refer to the characters to be recognized in the license plate image. Each character is usually an independent area with a specific shape and size, and each character can be separated from the license plate image through character segmentation and recognition.

[0038] Exemplarily, after obtaining a front image of a vehicle, the front image of the vehicle is grayed to reduce the interference of color information; then, the Canny edge detection algorithm is used to perform contour detection on the image, edge information in the image is extracted and multiple contours are obtained based on the edge information, and contours that may contain license plates are screened out from the multiple contours. Usually, the license plate contour has a certain aspect ratio and shape characteristics; then, based on the screened contours, the license plate area is extracted from the original image to obtain a license plate image; finally, the license plate image is further processed, for example: the characters in the license plate image are segmented by a horizontal projection method to obtain multiple characters to be processed.

[0039] In this embodiment, through contour detection, the license plate area can be accurately extracted, background interference can be reduced, and the accuracy of character recognition can be improved; contour detection can effectively filter out edge information of non-license plate areas, reduce false detection rates, and avoid mistaking other objects for license plates; contour detection has good robustness to noise and slight deformations in the image, and can adapt to different shooting conditions and environments.

[0040] In step S230, for any of the characters to be processed, the character to be processed is matched with a preset character library to obtain a matching character, and region growth is performed around the character to be processed according to shape features of the matching character to obtain a target character.

[0041] The character library is a collection of various reference characters, which usually include letters, numbers, and special symbols. The preset character library is compared and matched with the characters to be processed to determine the specific content of the characters to be processed. The character library can be an image library or a feature vector library, depending on the matching algorithm used.

[0042] When matching the character to be processed with the preset character library, the extracted character to be processed can be compared with the reference character in the character library through a preset matching algorithm to find the most similar reference character as the matching character. The preset matching algorithm may include: template matching, feature point matching, convolutional neural network, etc.

[0043] The shape feature of the matched character refers to the geometric shape, stroke direction, stroke thickness, etc. of the matched character. The shape feature of the matched character is used as the growth direction to perform region growth on the pixels with similar grayscale values ​​around the processed character, and the judgment standard for stopping region growth can also be obtained according to the shape feature of the matched character.

[0044] Among them, region growing is an image segmentation technology that merges pixels with similar attributes into the same region by gradually expanding from a seed point. When region growing, the surrounding pixels can be gradually added to the target region starting from the seed point according to the set similarity criteria (such as color, texture, shape, etc.). Through region growing, the boundaries of the characters to be processed can be repaired and expanded to make them more complete and accurate.

[0045] Exemplarily, the character "B" to be processed is segmented from the license plate image; using a template matching algorithm, the character "B" to be processed is compared with the reference characters in the character library, the similarity between the character to be processed and each reference character is calculated, and the reference character with the highest similarity is selected as the matching character; the shape features of the matching characters, such as stroke direction, stroke thickness, etc., are extracted; according to the shape features of the matching characters, similarity criteria (such as color, texture, shape, etc.) are set, starting from the seed point of the character to be processed, the surrounding pixels with similar attributes are gradually added to the target character area; the expansion is continued until the target character area no longer changes or a predetermined stop condition is reached, and finally a more complete and accurate target character "B" is obtained. In this embodiment, through character library matching, the specific content of the character to be processed can be accurately identified, reducing the possibility of misrecognition; region growing technology can repair defects in the character image, such as disconnected strokes, noise points, etc., to make the characters more complete and clear; matching the shape features of the characters provides reliable guidance for region growing, enhancing the system's adaptability to different shooting conditions and image quality.

[0046] In step S240, the target character is verified according to the matching character, and when the verification result meets the preset verification condition, the target character is used as the result of license plate auxiliary recognition, and traffic control is performed according to the result of license plate auxiliary recognition.

[0047] Among them, on the basis of matching characters, the target characters are further verified to ensure their correctness and reliability. The verification methods can be, for example: checking whether the shape of the target characters is consistent with the matching characters, including edge direction, curvature, connectivity, etc.; checking whether the size of the target characters is within a reasonable range to avoid characters that are too small or too large; checking the texture features of the target characters, such as color, brightness, etc., to ensure that they are consistent with the matching characters; checking whether the position and arrangement of the target characters in the entire license plate are reasonable to avoid isolated or misplaced characters.

[0048] For example, a smart checkpoint is located at an important intersection of a city's main roads. It is responsible for monitoring traffic flow and identifying illegal vehicles. The smart checkpoint performs the following traffic control based on the results of license plate auxiliary recognition: if the recognized license plate number matches the record in the illegal vehicle database, the system immediately issues an alarm; at the same time, the smart checkpoint can link with nearby traffic lights, temporarily change the timing of the lights, and guide illegal vehicles into the checkpoint; notify nearby traffic police and inform them of the specific location and detailed information of the illegal vehicle so that they can be intercepted and handled in time.

[0049] For example, a city has implemented a license plate restriction policy, prohibiting vehicles with certain license plate numbers from entering the city during a specific time period. The smart toll gate performs the following traffic control based on the results of license plate assisted recognition: if the recognized license plate number falls within the restricted area, the system will issue a warning and record the violation; the smart toll gate can be linked to a nearby electronic display screen to display restriction prompt information to remind drivers to comply with regulations; when necessary, the system can control nearby traffic lights to restrict the passage of illegal vehicles and guide them to leave the restricted area.

[0050] For example, a smart checkpoint is located near a hospital, and it is necessary to ensure that special vehicles such as ambulances can pass quickly. The smart checkpoint performs the following traffic control based on the results of license plate auxiliary recognition: if the recognized license plate number belongs to a special vehicle, the system immediately starts the priority passage procedure; controls nearby traffic lights to provide green lights for special vehicles to ensure their quick passage; when necessary, the system can coordinate surrounding traffic flows to make room on the road for special vehicles.

[0051] For example, a smart checkpoint is located at the entrance of a large shopping mall and is responsible for managing vehicles entering the parking lot. The smart checkpoint performs the following traffic control based on the results of license plate auxiliary recognition: if the recognized license plate number belongs to a registered user, the system automatically opens the barrier at the entrance of the parking lot to allow the vehicle to enter; for non-registered users, the system can prompt the driver to pay for temporary parking or register as a member; and record the vehicle entry time to provide a basis for subsequent fee calculation and management.

[0052] It can be seen from the above steps S210 to S240 that in the scheme proposed in this embodiment, the characters to be processed are matched with the preset character library to obtain matching characters; then, according to the shape characteristics of the matching characters, the surrounding area is grown to obtain the complete target characters. The license plate auxiliary recognition method can cope with the occlusion and contamination of license plate characters and improve the accuracy of character recognition. Through accurate license plate auxiliary recognition results, the smart card gate can accurately record and trigger corresponding traffic control measures such as fines and deductions for illegal vehicles; the smart card gate can accurately analyze traffic data in real time through accurate license plate auxiliary recognition results, provide timely and accurate information support for traffic management departments, and help traffic management departments make decisions quickly, optimize traffic flow, and improve road traffic efficiency.

[0053] In one embodiment of the present application, after obtaining the license plate image, the following steps are included: When the license plate image is in color, grayscale processing is performed on the license plate image to obtain a grayscale image corresponding to the license plate image; Performing dilation processing on the grayscale image by using a preset structural element to obtain a grayscale image after dilation processing; Performing an erosion process on the grayscale image after the dilation process by using the preset structural element to obtain an eroded grayscale image; The grayscale image after the corrosion process is subjected to threshold segmentation process to obtain a binary license plate image, and the binary license plate image is used to match with the preset character library.

[0054] Among them, grayscale processing of the license plate image can convert the color image into a grayscale image, that is, each pixel only retains one intensity value (grayscale value). Commonly used methods include weighted average method, maximum value method, etc., which can reduce the interference of color information, simplify the image processing process, and improve the efficiency and accuracy of subsequent processing.

[0055] Among them, the structural element refers to a small image matrix used for image morphological processing, usually a 3x3 or 5x5 matrix. The structural element can be used for dilation and erosion processing to control the effect and range of the processing. Common structural elements include circle, square, cross, etc.

[0056] The dilation process is a morphological operation that expands the white area in the image by convolving the structural element with each pixel in the image. For each pixel, if any pixel in the structural element intersects with the corresponding pixel in the image and is white, the pixel becomes white. The dilation process can fill small holes in the image, connect adjacent white areas, and enhance the connectivity of the target area.

[0057] Among them, the erosion process is also a morphological operation. By convolving the structural element with each pixel in the image, the white area in the image is reduced. For each pixel, if all the pixels in the structural element intersect with the corresponding pixels in the image and are white, the pixel remains white, otherwise it becomes black. Through the erosion process, small noise points in the image are removed, the boundary of the target area is refined, and the compactness of the target area is enhanced.

[0058] Among them, threshold segmentation is an image processing technology that divides the pixels in the image into foreground (white) and background (black) by setting a threshold. Commonly used threshold segmentation methods include global threshold method, local threshold method, etc. Through threshold segmentation, the grayscale image can be converted into a binary image, so that the target area (license plate characters) is separated from the background area (non-character part), which is convenient for subsequent character recognition and processing.

[0059] For example, see Figure 3 , Figure 3 A schematic diagram of a binary license plate image provided by an embodiment of the present invention. Figure 3 It can be seen that the white part in the binary license plate image is the target area (that is, the license plate characters), and the black part is the background area (that is, the non-character part).

[0060] In this embodiment, through grayscale processing, expansion processing, corrosion processing and threshold segmentation processing, noise can be effectively removed, holes can be filled, and boundaries can be refined, so that the license plate characters are clearer and more standardized, and the accuracy of character recognition is improved.

[0061] In one embodiment of the present application, matching the character to be processed with a preset character library to obtain a matching character includes: Determining a preset character library corresponding to the character to be processed according to the position of the character to be processed, and calculating the matching degree between the character to be processed and a plurality of reference characters in the preset character library; The matching character is determined from the plurality of reference characters according to the matching degree.

[0062] Among them, according to the position of the character to be processed in the license plate image, a suitable preset character library can be selected for matching. Characters in different positions may have different fonts, sizes and styles. Preparing multiple character libraries in advance, each character library corresponding to a specific position, can improve the accuracy of matching and reduce misrecognition caused by mismatching character libraries.

[0063] When calculating the degree of matching between the character to be processed and multiple reference characters in the preset character library, the similarity between the character to be processed and each reference character in the character library can be calculated by a preset matching algorithm. Common matching algorithms include template matching, feature point matching, convolutional neural network, etc. Through the matching degree, it can be determined which reference character in the character library is most similar to the character to be processed, so as to find the best matching character.

[0064] When determining a matching character from multiple reference characters according to the matching degree, the reference character with the highest matching degree can be selected as the final matching character according to the calculated matching degree. Usually, the reference character with the highest matching degree is selected, or a threshold is set, and only the reference characters with a matching degree exceeding the threshold are considered valid matching characters.

[0065] Exemplarily, the gaps between characters in the license plate are fixed, and the characters in the license plate are arranged horizontally. Based on the binary license plate image, the characters in the license plate are divided into regions; for the divided characters, the character library is matched in combination with their positions to determine the matching characters. Due to characteristics such as stroke order, different characters on the license plate have different pixel point trends in different regions, which can be reflected by the position and number of corner points. At the same time, the distribution characteristics of corner points can also be used as a standard for judging whether two characters are the same character.

[0066] In this embodiment, selecting a suitable character library according to the character position can reduce misrecognition caused by character library mismatch and improve the accuracy of character recognition; calculating the matching degree and setting the threshold can effectively filter out reference characters with low similarity and reduce the possibility of misrecognition.

[0067] In one embodiment of the present application, the calculating the matching degree between the character to be processed and a plurality of reference characters in the preset character library includes: Performing corner point detection on the character to be processed to obtain a first corner point set corresponding to the character to be processed; Performing corner point detection on each of the reference characters to obtain a second corner point set corresponding to each of the reference characters; Mapping the positions of corner points in the first corner point set to the second corner point set, and determining corner points in the second corner point set that meet a preset distance threshold around the mapped positions; The matching degree between the character to be processed and each of the reference characters is obtained according to the number of corner points in the second corner point set that meet a preset distance threshold around the mapped position.

[0068] Corner detection is an image processing technology used to detect corners or feature points in an image. Corner points are usually points in an image where the grayscale changes significantly and can reflect the local features of the image. By detecting corner points, key feature points of the characters to be processed and the reference characters are extracted, providing a basis for subsequent matching.

[0069] Among them, by mapping the corner point position of the character to be processed to the corner point position of the reference character, a corresponding relationship between the two can be established, and geometric transformation methods such as affine transformation or perspective transformation can be used to map the corner point position of the character to be processed to the corner point position of the reference character. Through position mapping, the feature points of the character to be processed can be aligned with the feature points of the reference character, which is convenient for subsequent matching and comparison.

[0070] Among them, in the set of corner points of the reference character, find the corner points around the mapping position of the character to be processed, and the distance between these corner points and the mapping position is less than a preset distance threshold. In specific implementation, the corner points that meet the conditions can be screened out by calculating distance metrics such as Euclidean distance or Manhattan distance. By screening the corner points that meet the distance threshold, the similarity between the character to be processed and the reference character can be determined.

[0071] Among them, when calculating the matching degree between the character to be processed and the reference character according to the number of corner points that meet the preset distance threshold, the number of corner points that meet the conditions can be used as a measure of the matching degree, and the greater the number, the higher the matching degree. By calculating the matching degree, the similarity between the character to be processed and the reference character can be determined, and the most similar reference character can be selected as the matching result.

[0072] Exemplarily, the license plate is divided into multiple character areas, and the character types and directions represented by different character areas are different, so the content of the characters in the character libraries of different character areas will also be different. For example: the first character from left to right of a common license plate is composed of Chinese characters, which are often used to represent provinces; the second character is an uppercase English letter used to represent a prefecture-level city. To achieve character matching, the license plate area in the binary license plate image must first be divided, and the character library is matched according to the divided areas, and the fixed width and spacing of each character in the license plate are used to divide them into several areas equally according to the number of characters. The reference characters in the character library corresponding to the characters at fixed positions on the license plate have their fixed shapes, so the number and distribution positions of the corner points of these reference characters have their own characteristics. The number and position of the corner points detected from a character to be processed in the binary license plate image are used to match the reference characters in the preset character library corresponding to the character to be processed.

[0073] Exemplarily, the first character to be processed on the leftmost side is selected from the multiple characters to be processed that are segmented, and the corner point detection algorithm is used to detect the corner points of the characters to be processed to obtain the first corner point set A. Corner point detection is performed once for all reference characters to obtain multiple second corner point sets B. The first corner point set A is matched with multiple second corner point sets B, and the matching has a one-to-many feature. Then, any one set is selected from the multiple second corner point sets B for matching, that is, the matching operation is performed on each corner point in the two sets. It is necessary to determine which of the first corner point set A and the multiple second corner point sets B has the highest matching degree, that is, based on the corner points in the first corner point set A and their positions, the corner points in each second corner point set B are respectively matched to obtain the matching degree corresponding to each second corner point set B, and the characters represented by the second corner point set B with the highest matching degree are selected as matching characters. The corner points in the first corner point set A can be used to find the corner points with the highest matching degree at that position in the second corner point set B through the Euclidean distance. If the distance between a corner point in the first corner point set A and the corner point near the position in the second corner point set B is less than the preset distance threshold, the two corner points in the first corner point set A and the second corner point set B are considered to be matched successfully. If there are multiple intersections in the second corner point set B that meet the preset distance threshold, the corner point with the smallest distance is selected for matching. The first corner point set A is matched with the character library. Here, one first corner point set A corresponds to one second corner point set B and a matching degree is obtained. If there are multiple second corner point sets B in the character library, there will be multiple matching degrees. Among these matching degrees, the character corresponding to the maximum value is found as the matching character.

[0074] In this embodiment, through corner point detection and position mapping, the key feature points of the character to be processed and the reference character can be extracted and aligned to improve the matching accuracy; by determining the number of corner points that meet the preset distance threshold, the reference characters with low similarity can be effectively filtered out to reduce the possibility of misrecognition.

[0075] In one embodiment of the present application, performing region growing around the character to be processed according to the shape feature of the matching character includes: When a first corner point in the first corner point set is positionally mapped to the second corner point set, if there are corner points around that meet a preset distance threshold, the first corner point is used as a seed point; Setting a gray value difference threshold when filling pixels around the seed point, and setting a region growth direction according to a stroke feature corresponding to the position of the seed point in the matching character; For any of the seed points, region growing is performed around the seed point according to the gray value difference threshold and the region growing direction.

[0076] The seed point refers to the starting point for region growing, which is usually a key point or feature point in the image. When the first corner point in the first corner point set is mapped to the second corner point set, if there are corner points around that meet the preset distance threshold, the first corner point is used as the seed point. Selecting a suitable seed point ensures that the region growing starts from the correct starting point, thereby improving the accuracy and reliability of the growth.

[0077] The gray value difference threshold refers to the maximum allowable gray value difference between the pixel points in the newly added area and the seed point during the region growing process. According to actual needs and image characteristics, set a suitable gray value difference threshold, which is usually an empirical value or determined through experiments. By setting the gray value difference threshold, ensure that the pixel points in the newly added area have similar gray values ​​to the seed point, avoid background or noise points from being mistakenly added to the region, and improve the accuracy of region growing.

[0078] The region growth direction refers to the priority expansion direction during the region growth process, which is usually determined based on the stroke features of the character. According to the position of the seed point in the matching character, the stroke features of the position (such as the direction and thickness of the stroke) are analyzed to set the corresponding region growth direction. By setting a reasonable region growth direction, it is ensured that the region growth is carried out along the stroke direction of the character, avoiding deviation from the character boundary, and improving the accuracy and consistency of region growth.

[0079] For example, to perform region growing around the character to be processed, the position of the seed point must be determined first. During region growing, the determination of the position of the seed point also determines the region growing direction and affects the growth quality. Figure 3 The binary license plate image shown in the figure shows that the edges of the characters formed by the processing of the license plate characters are defective and discontinuous. In this case, the seed point needs to be set on the region, and the area around the seed point is filled by region growing. For the selection of seed points, a random one of the successfully matched corner points is selected as the seed point.

[0080] For example, the grayscale values ​​of the pixels in the character area in the binary license plate image are relatively large, and the grayscale values ​​along the stroke direction of the characters are relatively close and extensible, and the standard for regional growth is the approximate standard of the grayscale value. A grayscale value difference threshold is set to 20, and based on the determined seed point, the pixels with grayscale value differences within 20 are searched around the seed point and filled. For these filled pixels, the grayscale value difference of the surrounding pixels is further searched.

[0081] For example, in the process of growing the seed point, the pixels that meet the conditions in all directions around the seed point are filled and continue to grow, which will include the pixels in the snowflake area with similar grayscale values ​​that are not in the character area, which will cause errors in license plate character recognition. In view of this situation, the growth direction of the position where the seed point is located is determined based on the shape characteristics of the matching characters. In the character library, the position point d corresponding to the selected seed point in the binary license plate image is located, the stroke position of d in the character is located, and the corresponding growth direction is determined according to the stroke characteristics.

[0082] In this embodiment, by selecting a suitable seed point and setting a reasonable gray value difference threshold, it can be ensured that the region growth starts from the correct starting point and proceeds along the stroke direction of the character, thereby improving the accuracy of character recognition. The gray value difference threshold can effectively filter out background and noise points, avoid adding irrelevant pixels to the target area by mistake, and reduce the possibility of misrecognition; the setting of the region growth direction is based on the stroke characteristics of the character, which enhances the adaptability to different character shapes and styles and improves the robustness of the system.

[0083] In one embodiment of the present application, performing region growing around the seed point according to the gray value difference threshold and the region growing direction includes: According to the gray value difference threshold, a plurality of pixel points are determined from around the seed point to obtain an area to be filled; Performing grayscale filling on the pixel points in the area to be filled, and connecting the seed point with the pixel points after grayscale filling to obtain a growth vector; Determining the growth possibility according to the angle between the growth direction of the region and the growth vector; The growth possibility is compared with a preset growth possibility threshold, and the region growing process is controlled according to the comparison result.

[0084] Among them, multiple pixels are selected from the neighborhood around the seed point to form an area to be filled. Usually, 8 neighboring pixels around the seed point (4 direct neighbors and 4 diagonal neighbors) are selected to determine the pixels that may be filled in preparation for subsequent grayscale filling and region growing.

[0085] When grayscale filling is performed on the pixel points in the area to be filled, the grayscale value of the pixel points in the area to be filled is set to the same grayscale value as the seed point. Each pixel point in the area to be filled is traversed, and its grayscale value is set to the grayscale value of the seed point to ensure that the pixel points in the area to be filled have similar grayscale values ​​to the seed point, providing a consistent basis for regional growth.

[0086] When the seed point is connected to the grayscale filled pixel point to obtain the growth vector, a vector is drawn from the seed point to the grayscale filled pixel point, called the growth vector, and the vector between the seed point and each grayscale filled pixel point is calculated. The direction and path of regional growth can be determined by the growth vector.

[0087] Among them, when determining the growth possibility according to the angle between the regional growth direction and the growth vector, the angle between the regional growth direction and the growth vector can be calculated, and the growth possibility can be determined according to the size of the angle. The angle is calculated using the dot product or cross product of the vectors, and the smaller the angle, the greater the growth possibility. By calculating the angle, it is ensured that the regional growth is carried out along the predetermined stroke direction to avoid deviation from the boundary of the character.

[0088] For example, based on the determined seed point, check the area to be filled whose grayscale value of each pixel in the 3×3 neighborhood around it is not greater than 20. Connect the pixel points in the area to be filled with the seed point and generate multiple vectors. Calculate the angle between these vectors and the growth direction. , the angle is used to calculate whether the pixel points around the seed point corresponding to the vector are suitable for continued growth. The growth possibility can be expressed as: in, Indicates the possibility of growth, The smaller it is, the more likely the pixels around the seed point are suitable for continued growth. The larger the value, the greater the possibility that the pixel is suitable for continued growth.

[0089] In this embodiment, by determining the area to be filled, grayscale filling, generating growth vectors and calculating the angle, it is possible to ensure that the region grows along the predetermined stroke direction, thereby improving the accuracy of character recognition; by setting the growth possibility threshold, the background and noise points can be effectively filtered out, avoiding the mistaken addition of irrelevant pixels to the target area, thereby reducing the possibility of misrecognition; the setting of the region growth direction is based on the stroke characteristics of the character, thereby enhancing the adaptability to different character shapes and styles and improving the robustness of the system.

[0090] In one embodiment of the present application, the controlling the region growing process according to the comparison result includes: When the comparison result shows that the growth possibility is greater than or equal to the preset growth possibility threshold, the pixel point after grayscale filling is used as a new seed point, and regional growth is performed around the new seed point according to the grayscale value difference threshold; When the comparison result is that the growth possibility is less than the preset growth possibility threshold, the region growing around the seed point is stopped.

[0091] Exemplarily, the preset growth possibility threshold is 0.85. If the growth possibility is greater than or equal to 0.85, the grayscale-filled pixel point is used as a new seed point, and regional growth is performed around the new seed point according to the grayscale value difference threshold.

[0092] In one embodiment of the present application, after performing region growing around the new seed point, the method further includes: Based on a new character region obtained by performing region growth around the new seed point, a plurality of edge vectors are established along the region growth direction for edge pixel points of the new character region, and the angle change difference between each two adjacent edge vectors is calculated; According to the angle change difference, the probability of the character pixel point corresponding to the edge pixel point is obtained; Determine the lateral distance between the spaced edge pixel points along the region growth direction; The process of the region growth is controlled by combining the possible degree of the character pixel points and the lateral distance.

[0093] Among them, edge pixels refer to pixels on the border of the character area, which usually have obvious grayscale changes. The edge pixels of the character area are extracted through the edge detection algorithm.

[0094] When establishing multiple edge vectors along the region growth direction, multiple edge vectors are established starting from edge pixels along the region growth direction. For each edge pixel, a vector pointing to the inside of the character is drawn according to the region growth direction.

[0095] The angle between each two adjacent edge vectors is calculated to obtain the angle change difference. The angle is calculated using the dot product or cross product of the vectors. The angle change difference reflects the shape change between edge pixels. The shape characteristics of edge pixels are evaluated through the angle change difference to determine their possibility as character pixels.

[0096] Among them, in the region growth direction, the lateral distance between the spaced edge pixels is calculated. Along the region growth direction, the lateral distance between each pair of adjacent edge pixels is measured. Through the lateral distance, the spatial relationship between edge pixels is evaluated to ensure the coherence and rationality of region growth.

[0097] Among them, the possibility of character pixels is comprehensively evaluated according to the angle change difference and lateral distance of edge pixels, and the process of region growth is controlled accordingly. A threshold can be set. If the possibility and lateral distance of character pixels meet the preset conditions, region growth will continue; otherwise, growth will stop. Through comprehensive evaluation, it is ensured that region growth is carried out along the stroke direction of the character to avoid erroneous growth and noise interference.

[0098] Exemplarily, the matching characters all have certain shape features, the edge areas of the matching characters are relatively smooth, and the matching character strokes have a fixed width. However, the above steps are based only on the grayscale value difference threshold and the growth direction as growth conditions, which may lead to problems of incomplete growth or overgrowth. Therefore, in the process of growth, a new character area is obtained by performing regional growth around the new seed point, and multiple edge vectors are established along the regional growth direction for the edge pixels of the new character area, and the angle change difference between each two adjacent edge vectors is calculated. The multiple angle change differences are averaged to obtain the angle change difference average value. The average value of the angle change difference is used as the judgment standard to judge the difference between the angle between the vector generated between the edge pixel point of the filling area and the previous edge pixel point in the process of continued growth and the previous angle. The possible degree of character pixel can be expressed as: in, Indicates the possible degree of character pixel points; It indicates the difference between the angle between two adjacent pixel vectors at the edge of the latest growing area and the average value of the angle change difference during the growth process. The smaller the difference is, the more uniform the angle change of the edge pixel points of the new character area is.

[0099] in, The larger the value, the greater the possibility that the edge pixel is a pixel.

[0100] For example, the character pixel probability threshold can be set to 0.85. If it is greater than or equal to 0.85, the edge pixel is more likely to be the inner area of ​​the character, and it is suitable to continue growing. If it is less than 0.85, then growth stops at this moment.

[0101] Exemplarily, when the smoothness of the area around the characters is used as a condition for judging the cessation of regional growth, the area with smooth edge contours but enlarged character shapes due to excessive growth is included. The character strokes on the license plate all have a fixed width. Therefore, two edge pixels are located every k pixels along the growth direction, a vertical line is drawn perpendicular to the growth direction between the two edge pixels, and the lateral distance D between the edge pixels is obtained. The preset standard lateral distance is L, and the process of regional growth is controlled by the difference m between the lateral distance D between the edge pixels and the standard lateral distance. For example, the difference threshold is set to 0.1. If the m value is greater than or equal to 0.01 during the growth process, it is considered that the lateral distance between the edge pixels meets the reference character standard and the growth can be stopped.

[0102] The degree of growth satisfaction can be expressed by the difference between the lateral distance D between edge pixels and the standard lateral distance and the possible degree of character pixels: in, Indicates the degree of growth satisfaction; Indicates the difference between the horizontal distance D between edge pixels and the standard horizontal distance, Indicates the possible degree of character pixel.

[0103] in, The larger the value, the more the horizontal distance between edge pixels meets the reference character standard. The growth satisfaction degree can be compared with a preset growth satisfaction degree threshold. For example, if the preset growth satisfaction degree threshold is 0.8, if n is greater than or equal to 0.8, the region growth is stopped.

[0104] In this embodiment, by extracting edge pixels, establishing edge vectors, calculating angle change differences, and evaluating the degree of character pixel probability, it is possible to ensure that the region growth is carried out along the stroke direction of the character, thereby improving the accuracy of character recognition. By setting a threshold and comprehensively evaluating the probability and lateral distance of character pixel points, background and noise points can be effectively filtered out, irrelevant pixels can be avoided from being mistakenly added to the target area, and the possibility of misrecognition can be reduced.

[0105] In one embodiment of the present application, the preset verification condition includes a preset character inflection point matching degree threshold, and the target character is verified according to the matching character, and when the result of the verification meets the preset verification condition, the target character is used as the result of the license plate auxiliary recognition, including: Comparing the inflection point of the matching character with the inflection point of the target character to obtain the degree of coincidence of the inflection points of the characters; When the degree of matching of the inflection points of the characters is greater than or equal to the preset threshold value of the degree of matching of the inflection points of the characters, it is determined that the target character is the result of the auxiliary license plate recognition.

[0106] Among them, the inflection point refers to the point where the direction of the character contour changes significantly, usually the turning point or cusp of the character. The inflection point on the character contour is extracted through edge detection and curve fitting. The inflection point is an important feature point of the character and is used to distinguish different character shapes.

[0107] The inflection point match degree refers to the similarity between the inflection point of the matching character and the inflection point of the target character. The match degree is evaluated by calculating the distance, angle and other parameters between the inflection points of the matching character and the target character. The consistency between the target character and the matching character is verified by the inflection point match degree to ensure the accuracy of the recognition result.

[0108] Exemplarily, the preset character inflection point matching degree threshold is 0.87. If the character inflection point matching degree is greater than or equal to 0.87, it is determined that the target character is the result of license plate auxiliary recognition.

[0109] In this embodiment, by extracting and comparing inflection points, the consistency between the target character and the matching character can be accurately verified, the possibility of misrecognition can be reduced, and the accuracy of character recognition can be improved. The calculation method of the degree of inflection point matching can effectively filter out characters with inconsistent shapes, avoid mistaking noise or background information for valid characters, and reduce misrecognition.

[0110] Figure 4 A schematic diagram of the structure of a smart card slot license plate auxiliary recognition system provided by an embodiment of the present invention. The system can be applied to Figure 1 The system can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the system is applied.

[0111] like Figure 4 As shown, the exemplary smart card port license plate auxiliary recognition system includes: An image acquisition module 401 is used to acquire a front image of a vehicle captured by a smart camera; The contour detection module 402 is used to perform contour detection on the front image of the vehicle and obtain a license plate image according to the result of the contour detection, wherein the license plate image includes a plurality of characters to be processed; The region growing module 403 is used for matching any of the characters to be processed with a preset character library to obtain a matching character, and performing region growing around the character to be processed according to the shape feature of the matching character to obtain a target character; The character verification module 404 is used to verify the target character according to the matching character, and when the verification result meets the preset verification condition, use the target character as the result of license plate auxiliary recognition, and perform traffic control according to the result of license plate auxiliary recognition.

[0112] In the exemplary smart card port's license plate auxiliary recognition system, the characters to be processed are matched with the preset character library to obtain matching characters; then, according to the shape characteristics of the matching characters, the surrounding area is grown to obtain the complete target characters. This license plate auxiliary recognition method can cope with the occlusion and contamination of license plate characters, and improve the accuracy of character recognition. Through accurate license plate auxiliary recognition results, the smart card port can accurately record and trigger corresponding traffic control measures such as fines and deductions for illegal vehicles; the smart card port can accurately analyze traffic data in real time through accurate license plate auxiliary recognition results, and provide timely and accurate information support for traffic management departments, which helps traffic management departments make decisions quickly, optimize traffic flow, and improve road traffic efficiency.

[0113] It should be noted that the license plate auxiliary recognition system of the smart card port provided in the above embodiment and the license plate auxiliary recognition method of the smart card port provided in the above embodiment belong to the same concept, and the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment, which will not be repeated here. In actual applications, the license plate auxiliary recognition system of the smart card port provided in the above embodiment can distribute the above functions to different functional modules as needed, that is, divide the internal structure of the system into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0114] It should be noted that the sequence of the above embodiments of the present invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0115] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A smart card slot auxiliary license plate recognition method, characterized in that: The method comprises: Obtain the front image of the vehicle captured by the smart camera; Performing contour detection on the front image of the vehicle, and obtaining a license plate image according to the result of the contour detection, wherein the license plate image includes a plurality of characters to be processed; For any of the characters to be processed, the character to be processed is matched with a preset character library to obtain a matching character, and region growth is performed around the character to be processed according to shape features of the matching character to obtain a target character; The target character is verified according to the matching character, and when the verification result meets the preset verification condition, the target character is used as the result of the license plate auxiliary recognition, and traffic control is performed according to the result of the license plate auxiliary recognition.

2. The license plate auxiliary recognition method of the smart card port as claimed in claim 1, characterized in that: After obtaining the license plate image, the method includes: When the license plate image is in color, grayscale processing is performed on the license plate image to obtain a grayscale image corresponding to the license plate image; Performing dilation processing on the grayscale image by using a preset structural element to obtain a grayscale image after dilation processing; Performing an erosion process on the grayscale image after the dilation process by using the preset structural element to obtain an eroded grayscale image; The grayscale image after the corrosion process is subjected to threshold segmentation process to obtain a binary license plate image, and the binary license plate image is used to match with the preset character library.

3. The license plate auxiliary recognition method of the smart card port as claimed in claim 1, characterized in that: The step of matching the character to be processed with a preset character library to obtain a matching character includes: Determining a preset character library corresponding to the character to be processed according to the position of the character to be processed, and calculating the matching degree between the character to be processed and a plurality of reference characters in the preset character library; The matching character is determined from the plurality of reference characters according to the matching degree.

4. The license plate auxiliary recognition method of the smart card port as claimed in claim 3, characterized in that: The calculating the matching degree between the character to be processed and a plurality of reference characters in the preset character library comprises: Performing corner point detection on the character to be processed to obtain a first corner point set corresponding to the character to be processed; Performing corner point detection on each of the reference characters to obtain a second corner point set corresponding to each of the reference characters; Mapping the positions of corner points in the first corner point set to the second corner point set, and determining corner points in the second corner point set that meet a preset distance threshold around the mapped positions; The matching degree between the character to be processed and each of the reference characters is obtained according to the number of corner points in the second corner point set that meet a preset distance threshold around the mapped position.

5. The license plate auxiliary recognition method of the smart card port as claimed in claim 4, characterized in that: The step of performing region growing around the character to be processed according to the shape feature of the matching character comprises: When a first corner point in the first corner point set is positionally mapped to the second corner point set, if there are corner points around that meet a preset distance threshold, the first corner point is used as a seed point; Setting a gray value difference threshold when filling pixels around the seed point, and setting a region growth direction according to a stroke feature corresponding to the position of the seed point in the matching character; For any of the seed points, region growing is performed around the seed point according to the gray value difference threshold and the region growing direction.

6. The license plate auxiliary recognition method of the smart card port as claimed in claim 5, characterized in that: The performing region growing around the seed point according to the gray value difference threshold and the region growing direction includes: According to the gray value difference threshold, a plurality of pixel points are determined from around the seed point to obtain an area to be filled; Performing grayscale filling on the pixel points in the area to be filled, and connecting the seed point with the pixel points after grayscale filling to obtain a growth vector; Determining the growth possibility according to the angle between the growth direction of the region and the growth vector; The growth possibility is compared with a preset growth possibility threshold, and the region growing process is controlled according to the comparison result.

7. The license plate auxiliary recognition method of the smart card port as claimed in claim 6, characterized in that: The controlling of the region growing process according to the comparison result comprises: When the comparison result shows that the growth possibility is greater than or equal to the preset growth possibility threshold, the pixel point after grayscale filling is used as a new seed point, and regional growth is performed around the new seed point according to the grayscale value difference threshold; When the comparison result is that the growth possibility is less than the preset growth possibility threshold, the region growing around the seed point is stopped.

8. The license plate auxiliary recognition method of the smart card port as claimed in claim 7, characterized in that: After performing region growing around the new seed point, the method further includes: Based on a new character region obtained by performing region growth around the new seed point, a plurality of edge vectors are established along the region growth direction for edge pixel points of the new character region, and the angle change difference between each two adjacent edge vectors is calculated; According to the angle change difference, the probability of the character pixel point corresponding to the edge pixel point is obtained; Determine the lateral distance between the spaced edge pixel points along the region growth direction; The process of the region growth is controlled by combining the possible degree of the character pixel points and the lateral distance.

9. The smart card slot auxiliary license plate recognition method as claimed in claim 1, characterized in that: The preset verification condition includes a preset character inflection point matching degree threshold, and the target character is verified according to the matching character, and when the result of the verification meets the preset verification condition, the target character is used as the result of the license plate auxiliary recognition, including: Comparing the inflection point of the matching character with the inflection point of the target character to obtain the degree of coincidence of the inflection points of the characters; When the degree of matching of the inflection points of the characters is greater than or equal to the preset threshold value of the degree of matching of the inflection points of the characters, it is determined that the target character is the result of the auxiliary license plate recognition.

10. A smart card slot auxiliary license plate recognition system, characterized in that: The system comprises: An image acquisition module, used to acquire the front image of the vehicle captured by the smart camera; A contour detection module, used to perform contour detection on the front image of the vehicle, and obtain a license plate image according to the result of the contour detection, wherein the license plate image includes a plurality of characters to be processed; A region growing module, for matching any of the characters to be processed with a preset character library to obtain a matching character, and performing region growing around the character to be processed according to shape features of the matching character to obtain a target character; The character verification module is used to verify the target character according to the matching character, and when the verification result meets the preset verification condition, the target character is used as the result of the license plate auxiliary recognition, and traffic control is performed according to the result of the license plate auxiliary recognition.

Images