Device and method for identifying tire sidewall characters

Abstract

The invention provides a device for identifying tire sidewall characters and an identification method. The device comprises a conveying unit used for conveying a tire to a to-be-detected area, a lifting platform used for jacking the tire to an identification position, a light source assembly used for illuminating the tire, and a camera used for shooting a top view image of the tire. The data processing module is used for controlling the camera to shoot the top view image of the tire, determining gradient information in the image of the tire according to the top view image of the tire and a photometric stereo algorithm, and identifying characters of the tire according to the gradient information in the image of the tire. According to the technical scheme, the camera and the light source assembly are matched to photograph the tire, and the gradient information in the image of the tire is confirmed through a three-dimensional algorithm, so that more accurate character information on the tire can be obtained. The characters of the tire are recognized through the gradient information in the image of the tire, the character recognition accuracy is improved, the whole recognition process is automatically achieved, and the recognition accuracy and recognition efficiency are improved.

Description

Technical Field

[0001] The present application relates to the technical field of tire production detection, and in particular to a device and method for identifying characters on a tire sidewall. Background Art

[0002] Traditional tire surface inspection mainly relies on manual visual inspection, which has many disadvantages. First, manual inspection is inefficient and difficult to meet the rapid inspection needs of large-scale production; second, manual inspection is easily affected by subjective factors, such as fatigue and vision differences of inspectors, which makes it difficult to ensure the accuracy and consistency of the inspection results; third, for defect detection of some tiny characters or complex patterns, manual inspection is difficult to achieve high-precision requirements.

[0003] With the development of machine vision technology, although there are some tire inspection devices based on machine vision, there are still some problems in the recognition and detection of characters and patterns on the tire surface. For example, factors such as the curvature, texture, black background and uneven lighting of the tire surface will interfere with the recognition of characters and patterns. The accuracy and robustness of the existing recognition algorithms in dealing with these complex situations need to be improved.

[0004] Existing tire surface character recognition methods mainly use two solutions: ordinary 2D camera imaging detection and 3D line scanning imaging detection. Among them, 2D camera imaging detection is often easily affected by uneven lighting. Due to the curvature of the tire surface, lighting in a single direction will cause some areas to be too bright or too dark, making it difficult to recognize characters clearly and accurately. The 3D line scanning imaging detection method has the disadvantages of high equipment requirements, high cost, slow imaging time, large data volume and long algorithm processing time, which increases the difficulty of use and system cost, and is difficult to apply in batches.

[0005] The two solutions based on ordinary 2D camera imaging detection and 3D line scanning imaging detection have inherent disadvantages. Here, a method and device for automatically detecting character information on the tire sidewall surface based on photometric stereo vision are invented, which can quickly and accurately identify the character information on the tire surface. Photometric stereo technology is a technology that can restore the surface shape and reflection characteristics of an object from multiple images under different lighting directions. Applying it to the field of tire surface character recognition can overcome many problems in the existing technology, improve the effect and efficiency of character recognition, and reduce the difficulty of use and system cost. Summary of the invention

[0006] The invention of the present application aims to provide a device and a method for identifying characters on a tire sidewall, so as to improve the recognition effect of the characters.

[0007] In a first aspect, a device for identifying characters on a tire sidewall is provided, the device comprising: A conveying unit, used for conveying the tire to an area to be inspected; A lifting platform, used to lift the tire located in the area to be detected to an identification position; A light source assembly, used for illuminating the tire; wherein the surface of the tire having characters is located within the illumination range of the light source assembly; A camera, used to take a top view image of the tire; wherein the top view image of the tire includes a surface of the tire with characters; A data processing module, wherein the data processing module is used to control the light source assembly to illuminate the tire and control the camera to capture a top-view image of the tire when the tire is raised to the identification area; the data processing module is also used to confirm the gradient information in the image of the tire based on the top-view image of the tire and the photometric stereo algorithm; and to identify the characters of the tire based on the gradient information in the image of the tire.

[0008] In the above technical solution, by using a camera and a light source assembly to take a picture of the tire, and confirming the gradient information in the tire image through a stereo algorithm, more accurate character information on the tire can be obtained. By recognizing the characters on the tire through the gradient information in the tire image, the accuracy of character recognition is improved, and the entire recognition process is realized through automation, which improves the accuracy and efficiency of recognition.

[0009] In a specific possible implementation manner, the light source assembly includes a light source bracket and a plurality of lamp posts arranged on the light source bracket; wherein the plurality of lamp posts are arranged around the tire; The data processing module is also used to control the lamp posts in the light source assembly to light up one by one, and when each lamp post is lit up, control the camera to take a photo of the tire once.

[0010] In a specific possible implementation manner, the data processing module is further specifically used to perform photometric stereo algorithm processing on the collected multiple overhead images of the tire to obtain gradient information in the image of the tire.

[0011] In a specific implementation scheme, the data processing module is specifically used to identify the characters of the tire based on the gradient information in the image of the tire, and segment the characters through a differentiable binarization algorithm; and recognize the characters through a convolutional recurrent neural network.

[0012] In a specific implementation manner, the data processing module is further configured to adjust the character to a horizontal state before recognizing the character.

[0013] In a specific possible implementation manner, it further includes a photoelectric switch disposed on the conveying unit, and the data processing module confirms that the tire moves to the area to be detected based on an electrical signal from the photoelectric switch.

[0014] In a specific feasible implementation scheme, the data processing module is also used to compare and verify the detected characters with the set character information; if the detected characters match the set character information, the conveying unit is controlled to continue conveying the tire; if the detected characters do not match the set character information, the conveying unit is paused.

[0015] In a specific possible implementation scheme, it also includes a camera bracket, which is located on one side of the conveying unit, and the camera is fixed on the camera bracket.

[0016] In a second aspect, a method for identifying characters on a tire sidewall is provided, wherein the method uses any of the above-mentioned devices for identifying characters on a tire sidewall for identification; the method comprises the following steps: Transport the tire to the area to be inspected; Lifting the tire located in the area to be detected to an identification position; Illuminating the tire by means of the light source assembly and taking a top view image of the tire; The gradient information in the image of the tire is determined based on the top view image of the tire and a photometric stereo algorithm; and the characters of the tire are recognized based on the gradient information in the image of the tire.

[0017] In the above technical solution, by taking a photo of the tire and confirming the gradient information in the tire image through a stereo algorithm, more accurate character information on the tire can be obtained. The characters on the tire are recognized through the gradient information in the tire image, which improves the accuracy of character recognition. The entire recognition process is realized through automation, which improves the accuracy and efficiency of recognition.

[0018] In a specific possible implementation scheme, the step of illuminating the tire by the light source assembly and taking a top view image of the tire specifically includes: The lamp posts in the light source assembly are controlled to light up one by one, and when each lamp post is lit up, the camera is controlled to take a photo of the tire once.

[0019] In a specific possible implementation manner, the step of confirming the gradient information in the image of the tire according to the top view image of the tire and the photometric stereo algorithm is as follows: The collected top-view images of the plurality of tires are processed using a photometric stereo algorithm to obtain gradient information in the images of the tires.

[0020] In a specific implementation manner, the identifying the character of the tire according to the gradient information in the image of the tire is specifically: The characters of the tire are identified according to the gradient information in the image of the tire, and the characters are segmented by a differentiable binarization algorithm; and the characters are identified by a convolutional recurrent neural network.

[0021] In a specific embodiment, the method further comprises: The detected characters are compared and verified with the set character information; if the detected characters match the set character information, the conveying unit is controlled to continue conveying the tire; if the detected characters do not match the set character information, the conveying unit is suspended.

[0022] On the third side, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for executing the second aspect and any possible design in the second aspect is implemented.

[0023] In a fourth aspect, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a computer to execute the method of the second aspect and any possible design of the second aspect.

[0024] In a fifth aspect, a computer program product is also provided, comprising instructions, which, when executed on a computer, enables the computer to execute the method in the second aspect of the present application and any possible design in the second aspect.

[0025] In addition, the technical effects brought about by any possible design method in the third to fifth aspects can be referred to the effects brought about by different design methods in the method part, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments provided according to the present disclosure and should not be regarded as limiting the scope of the present disclosure.

[0027] Figure 1 A schematic diagram of the structure of a device for recognizing tire sidewall characters provided in an embodiment of the present application; Figure 2 A schematic diagram of the cooperation between the lifting platform and the conveying unit provided in the embodiment of the present application; Figure 3 A flowchart of a method for identifying tire sidewall characters provided in an embodiment of the present application; Figure 4 A schematic diagram of a specific operation flow of a device for recognizing tire sidewall characters provided in an embodiment of the present application; Figure 5 A structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings.

[0029] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in one or more embodiments of this specification should be understood by people with ordinary skills in the field to which this disclosure belongs. The "first", "second" and similar words used in one or more embodiments of this specification do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0030] To facilitate understanding of the device for identifying tire sidewall characters provided in the embodiment of the present application, its application scenario is first explained. The device for identifying tire sidewall characters provided in the embodiment of the present application is mainly used in the tire sidewall surface character recognition detection scenario, such as first-piece detection in the rubber tire production process, laser engraving reference position detection and finished tire surface character information detection. By detecting the character information on the surface of the first tire after vulcanization, it can be reflected whether there is a mold combination error or whether the mold has a quality problem. The purpose is to prevent batch errors in the subsequent batch production of tires. Therefore, the first-piece inspection is of great significance.

[0031] When identifying characters on a tire, it is necessary to be able to detect the DOT (Department of Transportation, U.S. Department of Transportation safety standards) identification code and other character information on the sidewall surface in the detection scenario of the character information on the surface of the finished tire. During the tire production process, the characters on the tire surface contain important information such as the tire model, specification, DOT, and production date. Accurately identifying these characters is of great significance for tire quality control, risk prevention, production quality control, cost-saving inventory management, and after-sales service. However, the tire surface has a curved shape, and traditional image recognition methods face many challenges in identifying characters on the tire surface because the curved surface causes character deformation and the characters and their background are both black and have low contrast. Therefore, the embodiment of the present application provides a device for identifying tire sidewall characters to improve the recognition effect of tire sidewall characters. The following is a detailed description of it in conjunction with specific drawings and embodiments.

[0032] refer to Figure 1 and Figure 2 As shown, Figure 1 The schematic diagram of the structure of the device for recognizing tire sidewall characters provided in the embodiment of the present application is shown. Figure 2 A schematic diagram of the cooperation between the lifting platform 400 and the conveying unit 100 provided in an embodiment of the present application is shown. The device for identifying characters on the sidewall of a tire provided in an embodiment of the present application mainly includes components such as a conveying unit 100, a lifting platform 400, a light source assembly 300, a camera 200, and a data processing module. Among them, the conveying unit 100 is used to transmit the tire, and the lifting platform 400 is used to lift the tire to the identified position, so as to illuminate the tire through the light source assembly 300, and take a photo of the tire through the camera 200 to obtain an image of the tire. The data processing module is used to process the image taken by the camera 200, and identify the characters on the sidewall of the tire through the image of the tire. It is described in detail below in conjunction with specific drawings and embodiments.

[0033] The conveying unit 100 provided in the embodiment of the present application is used to convey the tire to the inspection area to be inspected. The conveying unit 100 can adopt different styles of conveying units 100, such as a roller conveyor belt, so as to stably support and convey the tire. Of course, in addition to the roller conveyor belt in the above example, other feasible solutions can also be adopted, such as a common belt conveyor belt can also be used to convey the tire.

[0034] In addition, the device for identifying tire sidewall characters provided in the present application also includes a lifting platform 400, which is used to lift the tire to the identification position. The identification position is located below the camera 200 and the light source assembly 300. And the lifting platform 400 is located in the area to be detected. When the tire is transmitted to the area to be detected by the conveying unit 100, the tire can be lifted by the lifting platform 400 so that the tire is close to the light source assembly 300 and the camera 200, so that the tire can be better illuminated and photographed.

[0035] Continue to refer Figure 1 The light source assembly 300 provided in the embodiment of the present application is used to illuminate the tire. In the embodiment of the present application, the light source assembly 300 is located directly above the tire to provide better light when illuminating the tire. It should be understood that when the light source assembly 300 illuminates the tire, the surface of the tire with the characters is located within the illumination range of the light source assembly 300, so that the camera 200 can capture a clear image when capturing an image.

[0036] The camera 200 provided in the embodiment of the present application is used to capture a top view image of a tire, and the top view image of the tire includes the surface of the tire with characters, so as to provide a detection image for subsequent recognition of the characters.

[0037] In the implementation of the present application, the above components are controlled by a data processing module, and the collected images are processed. In the specific processing, the data processing module is used to control the light source assembly 300 to illuminate the tire when the tire rises to the recognition area to provide sufficient light so that the subsequently captured images are clearer. In addition, the data processing module is also used to control the camera 200 to capture a top-view image of the tire to obtain an image with characters. In addition, the data processing module is also used to confirm the gradient information in the image of the tire based on the top-view image of the tire and the photometric stereo algorithm, and recognize the characters of the tire based on the gradient information in the image of the tire.

[0038] It can be seen from the above description that the device for identifying characters on the sidewall of a tire provided in the embodiment of the present application uses a camera 200 and a light source assembly 300 to take a picture of the tire, and confirms the gradient information in the image of the tire through a stereo algorithm, thereby obtaining more accurate character information on the tire. By identifying the characters on the tire through the gradient information in the image of the tire, the accuracy of character recognition is improved, and the entire recognition process is realized through automation, thereby improving the accuracy and efficiency of recognition.

[0039] When specifically set, the conveying unit 100 can be a roller conveyor, which can carry and transmit the tire in a straight line to transmit it to the area to be detected. When specifically determining whether the tire has reached the area to be detected, it can be detected by the photoelectric switch 700 set on the conveying unit 100. When the tire reaches the area to be detected, the photoelectric switch 700 generates an electrical signal, and the tire can be confirmed to move to the area to be detected according to the electrical signal of the photoelectric switch 700, and the roller conveyor is controlled to stop transmitting the tire to keep it in the area to be detected. It can be seen that when the tire provided in the embodiment of the present application is detected, there is no need to use a clamp to fix the tire again, and the gravity of the tire on the roller conveyor is used to keep it in the area to be detected. It should be understood that in the scheme disclosed in the present application, when detecting whether the tire has reached the area to be detected, different methods can be used, such as a proximity switch, or other sensors such as a distance sensor for detection, not limited to the example photoelectric switch 700.

[0040] Continue to refer Figure 1 and Figure 2 When the tire moves to the area to be inspected, in order to obtain a clearer image of the tire, the lifting platform 400 is used to lift the tire so that the tire can be closer to the light source assembly 300 and the camera 200, so that the light source assembly 300 can illuminate the tire more clearly. In addition, the camera 200 can also obtain clearer image information when shooting. When the lifting platform 400 is specifically set, the lifting platform 400 is set on the conveying unit 100, and the lifting platform 400 can be driven by a driving cylinder or a driving cylinder to control the lifting of the tire. When the tire moves to the area to be inspected, the tire is located above the lifting platform 400, and the lifting platform 400 moves upward to support and drive the tire to lift. It should be understood that when the lifting platform 400 is set on the conveying unit 100, the structure on the conveying unit 100 for transmitting the tire avoids the lifting platform 400 to ensure that the two devices can work independently.

[0041] In an practicable solution, the lifting platform 400 can be driven by a driving mechanism with a servo motor, and its driving height can be precisely controlled according to the specifications of different tires to ensure that the surface of the tire sidewall is within the depth of field of the camera 200. It should be understood that the driving mechanism with a servo motor is a common lifting driving mechanism, in which the servo motor provides power, and other structures in the driving mechanism can adopt a mechanism similar to a stage lift or other lifting mechanisms, such as a screw, or a common driving mechanism such as a servo motor and a transmission belt.

[0042] In an practicable solution, four movable columns are arranged on the lifting platform 400, and the four columns are controlled by cylinders. After the tire reaches the designated position, the movable columns can stretch the tire from the inside to the outside, so as to ensure that the center positions of different tires are relatively consistent and avoid that the tire surface information is not within the field of view of the camera 200. Exemplarily, the height direction of the column is perpendicular to the vertical direction of the conveying unit 100 conveying the tire. The telescopic direction of the cylinder is parallel to the area to be detected, that is, the telescopic direction of the cylinder is parallel to the support surface of the lifting platform 400 supporting the tire. When the cylinder is set, the cylinder can be arranged around the vertical axis of the support platform and arranged radially. When the cylinder is extended, the movable column can be driven to expand outward, and when the cylinder is retracted, the movable column can be driven to move closer to the vertical axis of the support platform. In the above solution, the movable column and the cylinder form a positioning mechanism to position the tire, so that the accurate conveying of the conveying unit 100 is not required, and it only needs to be located in the area to be detected. When the tire is located in the area to be inspected, it can be accurately positioned by the positioning mechanism on the lifting platform 400 .

[0043] It should be understood that when the lifting platform 400 is in use, when the lifting platform 400 does not lift the tire, the positioning mechanism should avoid the conveying unit 100 to ensure that the conveying unit 100 can transport the tire to the top of the lifting platform 400. When the lifting platform 400 rises, the positioning mechanism can be inserted into the space of the inner ring of the tire and position the tire during the expansion of the movable column.

[0044] Continue to refer Figure 1 As shown, the camera 200 is used to capture a top view image of the tire, and the top view image of the tire includes the surface to be printed. Figure 1 It can be seen that the tire is placed flat on the lifting platform 400, and the top view image taken by the camera 200 includes the overall outer circumferential contour of the tire. The camera 200 can be a high-precision industrial camera 200, which can obtain clear tire image information. In the specific arrangement, the camera 200 is located directly above the area to be detected, so that when the tire moves to the identification position, the camera 200 can capture a complete tire image. In an implementable scheme, the camera 200 is fixed by a camera bracket 500. Exemplarily, the camera bracket 500 is located on one side of the conveying unit 100, and the camera 200 is fixed to the camera bracket 500. The camera bracket 500 is an inverted L-shaped structure, and the crossbar of the camera bracket 500 extends above the lifting platform 400, so that the camera 200 can be located directly above the identification position. Thereby, it is ensured that a complete tire image is captured.

[0045] In an implementable solution, the light source assembly 300 provided in the embodiment of the present application includes a light source bracket 600 fixed on the bracket, and a plurality of lamp posts 310 disposed on the light source bracket 600; wherein the plurality of lamp posts 310 are arranged around the tire.

[0046] like Figure 1 As shown in , the light source bracket 600 is arranged on one side of the conveying unit 100, and the light source bracket 600 and the camera bracket 500 are located on the same side of the conveying unit 100. The light source bracket 600 is also an inverted L-shaped structure, wherein the structure where the light source bracket 600 extends above the lifting platform 400 is an annular structure, and a plurality of lamp posts 310 are fixed on the annular structure. When the tire is located at the identification position, the plurality of lamp posts 310 are arranged around the tire and are located on the outside of the tire. It should be understood that when the plurality of lamp posts 310 are arranged, the plurality of lamp posts 310 are also located directly above the identification position. That is, in the vertical direction, the plurality of lamp posts 310 are arranged around the light column of the camera 200, and the camera 200 is located above the plurality of lamp posts 310. In addition, in an optional solution, when multiple lamp posts 310 and camera 200 are specifically arranged, the center line of the viewing angle of camera 200 can be colinear with the vertical axis of lifting platform 400, and multiple lamp posts 310 surround the vertical axis of lifting platform 400, so that the light paths of multiple lamp posts 310 illuminating the tire are approximately the same. At the same time, it is also ensured that camera 200 can capture a relatively complete tire image when shooting.

[0047] The data processing module provided in the embodiment of the present application serves as a core component of the entire device, which integrates the control functions of the camera 200 , the lifting platform 400 , the light source assembly 300 and the control of the conveying unit 100 .

[0048] Specifically, the data processing module is used to control the conveying unit 100 to convey the tire, wherein the data processing module can confirm that the tire moves to the area to be detected according to the electrical signal of the photoelectric switch 700. Exemplarily, after the data processing module receives the signal of the photoelectric sensor switch, it is determined that the tire is in the area to be detected, and the conveying unit 100 stops conveying the tire. In addition, after the data processing module receives the signal of the photoelectric sensor switch, it controls the lifting platform 400 to lift upward until the tire is lifted to the identification position.

[0049] The data processing module is used to control the light source assembly 300 to illuminate the tire and control the camera 200 to take a top view image of the tire when the tire moves to the identification position. When specifically controlling the light source assembly 300 and the camera 200, the control logic is: control the lamp posts 310 in the light source assembly 300 to light up one by one, and when each lamp post 310 is lit, control the camera 200 to take a photo of the tire once. Exemplarily, when there are three lamp posts 310, the three lamp posts 310 are controlled to light up one by one, and when each lamp post 310 is lit, take a photo of the tire once, thereby obtaining three different top view images.

[0050] In addition, when processing the tire image, the data processing module specifically processes the multiple tire top-view images collected by the photometric stereo algorithm to obtain the gradient information in the tire image. Photometric stereo, or Photometric Stereo, is based on the principle of photometric stereo vision, for the gradient information in multiple (three or more) images collected under different lighting directions. When the data processing module processes the multiple tire top-view images, it will splice the multiple top-view images into a complete tire image and obtain the gradient information in the tire image.

[0051] When the above method is adopted, even in the case of uneven lighting, accurate tire sidewall surface information can be restored through photometric stereo, laying the foundation for character recognition. The principle of the related technical algorithm refers to the paper "Photometric stereo: A reflectance map technique for determining surface orientation from image intensity".

[0052] When specifically identifying characters on a tire, the data processing module is specifically used to identify characters on the tire based on gradient information in the tire image, and to segment the characters using a differentiable binarization algorithm; and to identify characters using a convolutional recurrent neural network. In addition, when specifically identifying characters, the data processing module is also specifically used to adjust the characters to a horizontal state before identifying the characters to facilitate identification.

[0053] That is, in the embodiment of the present application, the character information recognition algorithm adopts a deep learning OCR (Optical Character Recognition) recognition and detection algorithm, which adopts the efficient PaddleOCR model architecture and technical principles. The detection principle mainly includes text detection, text box correction and text recognition, where the purpose of text detection is to locate the text area in the image, that is, to recognize the text information in the image based on the gradient information in the image of the tire. In specific operations, differentiable binarization (DB for short) can be used in the PaddleOCR model as a text detector based on a simple segmentation network. The detection box correction is used to transform the text box (recognized text information) into a horizontal rectangular box before recognizing the detected text for subsequent text recognition.

[0054] Text Recognition: In the PaddleOCR model, we use CRNN (Convolutional Recurrent Neural Network) as the text recognizer, which has wide practicality for text recognition.

[0055] The data processing module provided in the embodiment of the present application is also used to compare and verify the detected characters with the set character information; if the detected characters match the set character information, the conveying unit 100 is controlled to continue conveying the tire; if the detected characters do not match the set character information, the conveying unit 100 is suspended. Exemplarily, the deep learning OCR algorithm detection effect used in the embodiment of the present application compares and verifies the detected character information with the character information in the corresponding tire standard CAD design drawing. If the data processing module determines OK, the tire is normally unloaded through the conveyor belt; if the data processing module determines NG, an alarm is activated to prompt the conveyor belt to suspend conveying.

[0056] As an optional solution, the device for identifying tire sidewall characters provided in the embodiment of the present application may also include a visual display device. When the characters detected by the data processing module do not match the set character information, the visual display device may be used to display the characters so that the operator can check and confirm whether there is indeed an abnormality in the characters on the tire, thereby reducing the risk of misjudgment.

[0057] It can be seen from the above description that in the device for identifying tire sidewall characters provided in the embodiment of the present application, multiple lamp posts 310 are used to illuminate the tire sidewall surface from different directions and angles, and multiple images are collected by the camera 200, and then the gradient information of the sidewall surface is restored by using the principle of photometric stereo vision, so as to identify the tire sidewall character information. The present invention can effectively overcome the influence of factors such as the tire sidewall curved surface and uneven illumination, and improve the accuracy and reliability of character recognition.

[0058] refer to Figure 3 As shown, in order to facilitate understanding of the device for identifying tire sidewall characters provided in the embodiment of the present application, the embodiment of the present application also provides a method for identifying tire sidewall characters, which uses any of the above-mentioned devices for identifying tire sidewall characters to identify characters on the tire. The method comprises the following steps: Step 001: transport the tire to the area to be inspected; Specifically, the tire can be transported to the area to be inspected by the transport unit. For details, please refer to the above Figure 1 and Figure 2 The relevant description in will not be repeated in detail here.

[0059] Step 002: Lift the tire located in the area to be inspected to the identification position; Specifically, the tire can be lifted by a lifting platform, which can be specifically adopted as described above. Figure 1 and Figure 2 The relevant description in will not be repeated in detail here.

[0060] Step 003: lighting the tire through the light source assembly and taking a top view image of the tire; Specifically, the light source assembly may use a plurality of lamp posts, which are arranged around the tire. When lighting, the lamp posts in the light source assembly are controlled to light up one by one, and when each lamp post is lit, the camera is controlled to take a picture of the tire. Figure 1 and Figure 2 The relevant description in will not be repeated in detail here.

[0061] Step 004: confirming the gradient information in the tire image according to the top view image of the tire and the photometric stereo algorithm; and recognizing the characters of the tire according to the gradient information in the tire image.

[0062] Specifically, the overhead image of the tire can be processed by the data processing module to identify the characters on the tire sidewall. Specifically, the overhead images of the multiple tires collected can be processed by the photometric stereo algorithm to obtain the gradient information in the tire image. In addition, the characters of the tire can be identified based on the gradient information in the tire image, and the characters can be segmented by a differentiable binarization algorithm; and the characters can be identified by a convolutional recurrent neural network. Specifically, the above-mentioned Figure 1 and Figure 2 The relevant description in will not be repeated in detail here.

[0063] In the above technical solution, by taking a photo of the tire and confirming the gradient information in the tire image through a stereo algorithm, more accurate character information on the tire can be obtained. The characters on the tire are recognized through the gradient information in the tire image, which improves the accuracy of character recognition. The entire recognition process is realized through automation, which improves the accuracy and efficiency of recognition.

[0064] In addition, the method provided in the embodiment of the present application also includes: The detected characters are compared with the set character information; if the detected characters match the set character information, the conveying unit is controlled to continue conveying the tire; if the detected characters do not match the set character information, the conveying unit is suspended. Figure 1 and Figure 2 The relevant description in will not be repeated in detail here.

[0065] refer to Figure 4 To facilitate understanding of the above method, the following is a detailed description of the operation steps of the device for recognizing tire sidewall characters: The entire device includes the following steps when specifically recognizing characters: Step S1: System preparation and start-up operation; Specifically, place the tire at the front end of the roller conveyor belt, start the device operation button, and the tire drives the roller conveyor belt to move to the area to be identified (the position below the camera lens) through the servo motor. After the photoelectric switch detects the tire, the roller conveyor belt stops transmitting and the tire is located on the lifting platform.

[0066] Step S2: The tire moves to the photo taking position; Specifically, the lifting platform will be lifted to a specified height range (identification position) according to the specifications of the tire so that the height of the tire sidewall surface is within the depth of field of the camera lens, thereby ensuring clear imaging. This process does not require manual adjustment. As shown in Figure 2, the lifting platform automatically adjusts its height according to the batch of tires produced.

[0067] In specific implementation, the lifting height corresponding to the tire batch can be constructed first and input into the data processing module. The data processing module can determine the lifting height according to the tire batch, that is, determine the identification position.

[0068] Step S3: The camera takes pictures in sequence to obtain multiple images; Specifically, the data processing module starts the camera to take pictures of the tire to be identified and detected, and turns on the corresponding lamp post synchronously during the process of taking pictures. That is, each time the camera takes a picture, a corresponding lamp post is turned on synchronously. In the present invention, 3 or more lamp posts are used, that is, after taking the image, 3 or more lamp posts need to be turned on in sequence, and one lamp post is lit each time. At the same time, the camera takes pictures in the corresponding sequence to take 3 or more images, and these multiple images are used for subsequent photometric stereo algorithm reconstruction; Step S4: photometric stereo algorithm reconstruction and image post-processing; Specifically, the data processing module starts the software algorithm to perform photometric stereo reconstruction algorithm processing on the three or more images collected in step S3, obtains the gradient information in the tire image, and then performs post-processing enhancement algorithm processing on the gradient information in the tire image to highlight the contrast of the character information area, thereby completing photometric stereo reconstruction and image post-processing. The post-processed image obtained in this step is convenient for subsequent deep learning OCR character information recognition detection, and can improve the accuracy and stability of subsequent recognition; Step S5: deep learning OCR detection and recognition; Specifically, according to the post-processed image obtained in step S4, the post-processed image is detected and recognized according to the deep learning OCR algorithm to obtain all the character information results on the tire sidewall surface.

[0069] Step S6: Verify the recognition result by comparing it with the template; Specifically, the character information result recognized in step S5 is compared and verified with the character information on the corresponding standard tire template pre-input in the data processing module to obtain a result of whether the tire meets the expected design; Step S7: handle and record the exception; Specifically, according to the judgment result obtained in step S6, if the data processing module judges OK, the tire is normally unloaded through the universal wheel conveyor belt. If the data processing module judges NG, the abnormality is handled and the alarm is activated. At the same time, the data processing module automatically records the abnormal position on the upper computer software interface and suspends the conveyor belt until the operator checks and confirms the tire abnormality before performing subsequent operations.

[0070] Step S8: Complete the process and enter the next working cycle; Specifically, after the processing result is confirmed, the task of automatically performing character information recognition and detection on the tire sidewall surface in a photometric stereo manner is completed and the next cycle is entered.

[0071] It can be seen from the above specific steps that in the above technical solution, by taking a photo of the tire and confirming the gradient information in the tire image through a stereo algorithm, more accurate character information on the tire can be obtained. The characters on the tire are recognized through the gradient information in the tire image, which improves the accuracy of character recognition. The entire recognition process is realized through automation, which improves the accuracy and efficiency of recognition.

[0072] An embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for executing any one of the possible designs described above is implemented.

[0073] An embodiment of the present application also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute any one of the above-mentioned possible design methods.

[0074] The embodiment of the present application further provides a computer program product, including instructions, which, when executed on a computer, enable the computer to execute any one of the above-mentioned possible design methods.

[0075] In addition, the technical effects of any of the above possible design methods can be found in Figure 3 The effects of different design methods in the method section of the example will not be repeated here.

[0076] Figure 5 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0077] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0078] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store the operating system 100 and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0079] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0080] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0081] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010 , the memory 1020 , the input / output interface 1030 , and the communication interface 1040 ).

[0082] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0083] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0084] A person of ordinary skill in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples. In line with the concept of the present disclosure, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of different aspects of one or more embodiments of the present specification as above, which are not provided in detail for the sake of simplicity.

[0085] In addition, to simplify the description and discussion, and in order not to obscure one or more embodiments of the present specification, known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided figures. In addition, devices may be shown in the form of block diagrams to avoid obscuring one or more embodiments of the present specification, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which one or more embodiments of the present specification are to be implemented (i.e., these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present disclosure, it is apparent to those skilled in the art that one or more embodiments of the present specification may be implemented without these specific details or with variations in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0086] Although the present disclosure has been described in conjunction with specific embodiments of the present disclosure, many alternatives, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the discussed embodiments.

[0087] One or more embodiments of this specification are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of this specification should be included in the scope of protection of this disclosure.

[0088] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A device for identifying characters on a tire sidewall, characterized in that: include: A conveying unit, used for conveying the tire to an area to be inspected; A lifting platform, used to lift the tire located in the area to be detected to an identification position; A light source assembly, used for illuminating the tire; wherein the surface of the tire having characters is located within the illumination range of the light source assembly; A camera, used to take a top view image of the tire; wherein the top view image of the tire includes a surface of the tire with characters; A data processing module, wherein the data processing module is used to control the light source assembly to illuminate the tire and control the camera to capture a top-view image of the tire when the tire is raised to the identification area; the data processing module is also used to confirm the gradient information in the image of the tire based on the top-view image of the tire and the photometric stereo algorithm; and to identify the characters of the tire based on the gradient information in the image of the tire.

2. The device for identifying tire sidewall characters according to claim 1, characterized in that: The light source assembly includes a light source bracket and a plurality of lamp posts arranged on the light source bracket; wherein the plurality of lamp posts are arranged around the tire; The data processing module is also used to control the lamp posts in the light source assembly to light up one by one, and when each lamp post is lit up, control the camera to take a photo of the tire once.

3. The device for identifying tire sidewall characters according to claim 2, characterized in that: The data processing module is also specifically used to perform photometric stereo algorithm processing on the collected top-view images of the multiple tires to obtain gradient information in the images of the tires.

4. The device for identifying tire sidewall characters according to claim 3, characterized in that: The data processing module is specifically used to identify the characters of the tire according to the gradient information in the image of the tire, and to segment the characters through a differentiable binarization algorithm; and to recognize the characters through a convolutional recursive neural network.

5. The device for identifying tire sidewall characters according to claim 4, characterized in that: The data processing module is also specifically used to adjust the character to a horizontal state before recognizing the character.

6. The device for identifying tire sidewall characters according to claim 1, characterized in that: It also includes a photoelectric switch arranged on the conveying unit, and the data processing module confirms that the tire moves to the area to be detected according to the electrical signal of the photoelectric switch.

7. The device for identifying tire sidewall characters according to any one of claims 1 to 6, characterized in that: The data processing module is also used to compare and verify the detected characters with the set character information; if the detected characters match the set character information, the conveying unit is controlled to continue conveying the tire; if the detected characters do not match the set character information, the conveying unit is paused.

8. The device for identifying tire sidewall characters according to claim 7, characterized in that: It also includes a camera bracket, which is located at one side of the conveying unit, and the camera is fixed on the camera bracket.

9. A method for identifying characters on a tire sidewall, characterized in that: The device for identifying tire sidewall characters according to any one of claims 1 to 8 is used for identification; the method comprises the following steps: Transport the tires to the area to be inspected; Lifting the tire located in the area to be detected to an identification position; Illuminating the tire by means of the light source assembly and taking a top view image of the tire; The gradient information in the image of the tire is determined based on the top view image of the tire and a photometric stereo algorithm; and the characters of the tire are recognized based on the gradient information in the image of the tire.

10. The method for identifying tire sidewall characters according to claim 9, characterized in that: The step of illuminating the tire by the light source assembly and taking a top view image of the tire specifically includes: The lamp posts in the light source assembly are controlled to light up one by one, and when each lamp post is lit up, the camera is controlled to take a photo of the tire once.

11. The method for identifying tire sidewall characters according to claim 10, characterized in that: The step of confirming the gradient information in the image of the tire according to the top view image of the tire and the photometric stereo algorithm is as follows: The collected top-view images of the plurality of tires are processed using a photometric stereo algorithm to obtain gradient information in the images of the tires.

12. The method for identifying tire sidewall characters according to any one of claims 9 to 11, characterized in that: The step of identifying the character of the tire according to the gradient information in the image of the tire is specifically: The characters of the tire are identified according to the gradient information in the image of the tire, and the characters are segmented by a differentiable binarization algorithm; and the characters are identified by a convolutional recurrent neural network.

13. The method for identifying tire sidewall characters according to claim 12, characterized in that: Also includes: The detected characters are compared and verified with the set character information; if the detected characters match the set character information, the conveying unit is controlled to continue conveying the tire; if the detected characters do not match the set character information, the conveying unit is suspended.

14. A computer program product, characterized in that The method comprises instructions which, when executed on a computer, enable the computer to execute the method for recognizing tire sidewall characters as described in any one of claims 9 to 13.

Images