Defect Detection Method and Defect Detection Device for Tire Belt

Abstract

The present application provides a method for defect detection of a tire belt layer, a defect detection device, an electronic device, and a computer-readable medium. The defect detection method includes: performing rotational projection on a tire belt layer image using a projection frame to obtain a set of projection histograms; calculating eigenvalues corresponding to the set of histograms; and determining the missing cord situation at the position where the projection frame is located according to the eigenvalues and the size of the projection frame. By rotational projection, the complex texture features of the cords are transformed into an intuitive and accurate peak-valley fluctuation state in the projection histogram, thereby simplifying the difficulty of detecting belt layer missing defects.

Description

Technical Field

[0001] The present application relates to the field of image processing, and relates to a method for detecting defects in a tire belt layer, a detection device, an electronic device, and a computer-readable medium. Background Art

[0002] As one of the important components of an automobile, the quality of a tire directly determines the quality of an automobile product. The belt layer is one of the important structures of a tire.

[0003] Due to the large number of tire cord layers and complex directions, it is easy to have misoperations such as missing laying or incorrect direction during manual laying, resulting in defects such as missing belt layers.

[0004] At present, the detection of missing defects in the tire belt layer at home and abroad can be divided into manual detection methods and traditional texture analysis detection methods. The manual detection method mainly observes the tire X-ray image manually, distinguishes the defects and makes a grading judgment on the possible defects. The manual detection has strong subjectivity and inconsistent evaluation criteria for defects, so the accuracy is not high. Moreover, long-term manual detection will cause visual fatigue of the detection personnel, which is likely to miss defects and cause phenomena such as false alarms and missed reports.

[0005] The traditional texture analysis detection method mainly uses Gabor transform to detect the missing defects of the belt layer. First, determine the number of cord layers and the angle direction of the belt layer according to the tire model. Secondly, determine the judgment threshold according to the tire model, then perform Gabor filtering on the belt layer area of the tire X-ray image along the cord direction and calculate the texture feature value, and finally establish a discrimination model. This method has a high detection accuracy, but it is necessary to determine the judgment threshold in advance according to different tire models, and the practicability is weak. Summary of the Invention

[0006] In order to solve the problems of low accuracy of manual detection and weak practicability of texture analysis detection methods in the existing detection process of tire belt layer defects, the present application provides a method for detecting defects in a tire belt layer, including:

[0007] Performing rotational projection on the tire belt layer image using a projection frame to obtain a set of projection histograms;

[0008] Calculating the feature values corresponding to the set of histograms;

[0009] Judging the cord missing situation at the position where the projection frame is located according to the feature values and the size of the projection frame.

[0010] According to some exemplary embodiments of the present application, the projection frame includes: a rectangular projection frame located in the middle area of the tire belt layer image.

[0011] According to some exemplary embodiments of the present application, obtaining a set of projection histograms includes: obtaining projection histograms by rotating the rectangular projection frame from 0° to 180° respectively.

[0012] According to some exemplary embodiments of the present application, the defect detection method further includes:

[0013] Traversing the entire image from top to bottom with the projection frame in the belt layer image;

[0014] Performing rotational projection on the tire belt layer image using the projection frame at each position of the projection frame to obtain a set of projection histograms;

[0015] Calculating the eigenvalue corresponding to the set of histograms at each position of the projection frame;

[0016] Judging the cord missing situation at each position of the projection frame according to the eigenvalue and the size of the projection frame;

[0017] If there is a cord missing at a certain position of the projected frame, it is determined that there is a belt layer missing in the belt layer image.

[0018] According to some exemplary embodiments of the present application, the eigenvalue includes one or more of the number of maximum values, the number of minimum values, the average period of maximum values, the period variance of maximum values, the average period of minimum values, and the period variance of minimum values.

[0019] According to some exemplary embodiments of the present application, judging the cord missing situation at the position of the projection frame according to the eigenvalue and the size of the projection frame includes:

[0020] When the number of maximum values, the average period of maximum values, the number of minimum values, and the average period of minimum values satisfy the following conditions with the width of the projection frame, there is a cord missing at the position of the projection frame:

[0021] N max ×T max ≈N min ×Tmi n ≈D

[0022] Wherein, N max is the number of maximum values, T max is the average period of maximum values, N min is the number of minimum values, T min is the average period of minimum values, and D is the width of the projection frame.

[0023] According to some exemplary embodiments of the present application, judging the cord missing situation at the position of the projection frame according to the eigenvalue and the size of the projection frame includes:

[0024] When the maximum period variance, the minimum period variance and a set threshold satisfy the following conditions, there is a missing cord at the position of the projection frame:

[0025] σ max <a max ,σ min <a min

[0026] Where σ max is the maximum period variance, σ min is the minimum period variance, a max is the set maximum period variance threshold, and a min is the set minimum period variance threshold.

[0027] According to some exemplary embodiments of the present application, the defect detection method further includes: preprocessing the tire image and segmenting out the tire belt layer image.

[0028] According to some exemplary embodiments of the present application, the preprocessing includes:

[0029] Performing gamma transformation on the tire image;

[0030] Taking the device shadow in the transformed tire image as a reference boundary to perform projection rough segmentation, and segmenting out the shoulder and belt layer parts in the tire image;

[0031] Adopting an adaptive binary algorithm for the segmented tire image to obtain the belt layer boundary;

[0032] Taking the second belt layer boundaries on the left and right sides as the left and right boundaries of the belt layer, and segmenting out the tire belt layer image in the tire image.

[0033] According to some exemplary embodiments of the present application, before calculating the eigenvalues corresponding to the set of projection histograms, the defect detection method further includes:

[0034] Performing mean smoothing on the set of projection histograms.

[0035] For the defect detection method, the smoothing process includes:

[0036] Performing mean smoothing on the burr points and the minimum value points at both ends thereof in the projection histogram according to the following formula:

[0037]

[0038] Where H l is the gray value of the burr point, and H s1 , H s2 are the gray values of the minimum value points at both ends of the burr point.

[0039] According to another aspect of the present application, there is also provided a defect detection device for a tire belt layer, including:

[0040] A first image processing module, which can be used to preprocess a tire image and segment the tire belt layer image;

[0041] A second image processing module, which can be used to perform rotational projection on the tire belt layer image using a projection frame to obtain a set of projection histograms;

[0042] A third image processing module, which can be used to perform mean smoothing processing on the set of projection histograms;

[0043] An eigenvalue calculation module, which can be used to calculate eigenvalues corresponding to the set of projection histograms;

[0044] A defect judgment module, which can be used to judge the cord missing situation at the position where the projection frame is located according to the eigenvalue and the size of the projection frame, and judge the belt layer defect situation in the tire belt layer image according to the cord missing situations at all positions of the projection frame.

[0045] According to another aspect of the present application, there is also provided an electronic device for detecting defects in a tire belt layer, characterized by including:

[0046] One or more processors;

[0047] A storage device for storing one or more programs;

[0048] When the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned defect detection method.

[0049] According to another aspect of the present application, there is also provided a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned defect detection method is implemented.

[0050] The defect detection method for the tire belt layer provided by the present application converts the complex texture features of the cords into the intuitive and accurate peak-valley fluctuation state in the projection histogram through rotational projection, thereby simplifying the difficulty of detecting belt layer missing defects. In addition, by calculating eigenvalues such as the number of maxima, average period of maxima, number of minima, average period of minima, variance of maxima period, and variance of minima period in the projection histogram, the peak-valley fluctuation state of the projection histogram is comprehensively reflected, thereby ensuring the comprehensiveness of the detection algorithm. Description of the Drawings

[0051] To more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other accompanying drawings can be obtained based on these drawings without exceeding the scope of protection required by the present application.

[0052] Figure 1A Shows an X-ray image of a normal tire belt layer;

[0053] Figure 1B Shows an X-ray image of a tire belt layer with a defect of missing belt layer;

[0054] Figure 2 Shows a flowchart of a method for detecting tire belt layer defects according to an exemplary embodiment of the present application;

[0055] Figure 3A Shows a projection histogram of a tire belt layer with cords according to an exemplary embodiment of the present application;

[0056] Figure 3B Shows a projection histogram of a tire belt layer without cords according to an exemplary embodiment of the present application;

[0057] Figure 4 Shows a flowchart of a method for detecting tire belt layer defects according to another exemplary embodiment of the present application;

[0058] Figure 5A Shows an original X-ray image of a tire belt layer according to an exemplary embodiment of the present application;

[0059] Figure 5B Shows an X-ray image of a tire belt layer after gamma transformation according to an exemplary embodiment of the present application;

[0060] Figure 5C Shows an X-ray image of a tire belt layer segmented by projection according to an exemplary embodiment of the present application;

[0061] Figure 5D Shows an X-ray image of a tire belt layer after adaptive binary segmentation according to an exemplary embodiment of the present application;

[0062] Figure 6 Shows a schematic diagram of the execution process of a method for detecting tire belt layer defects according to an exemplary embodiment of the present application;

[0063] Figure 7 Shows a block diagram of a device for detecting tire belt layer defects according to an exemplary embodiment of the present application;

[0064] Figure 8 Shows a block diagram of an electronic device for detecting tire belt layer defects according to an exemplary embodiment of the present application. Specific embodiments

[0065] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments in the present application without creative efforts belong to the scope of protection of the present application.

[0066] The tire belt layer is composed of multiple layers of cords in different directions. The absence of the belt layer means the lack of a cord layer in a certain direction. Therefore, the defect can be detected by judging the angular direction of the cord layer. After comparison Figure 1A with the normal tire belt layer X-ray image shown in Figure 1B and the tire belt layer X-ray image with the defect of belt layer absence shown in

[0067] the inventor of the present application found that the gray value of the cords in the tire belt layer is relatively low, the gray value of the background is relatively high, and the absence of the belt layer essentially means the lack of a cord layer in a certain direction. Therefore, the number of cord layers and the angular direction in the tire belt layer can be obtained by the method of projection.

[0068] Therefore, in view of the problems in the existing tire belt layer detection technology, the present application provides a method for detecting defects in a tire belt layer according to the above characteristics of the cords in the tire belt layer, which can accurately and efficiently detect the defect of the absence of the tire belt layer on the basis of meeting real-time performance by using the texture characteristics shown when the tire belt layer is absent.

[0069] Figure 2 The flowchart of the method for detecting defects in a tire belt layer according to an exemplary embodiment of the present application is shown.

[0070] As Figure 2 shown, the method for detecting defects in a tire belt layer provided by the present application includes:

[0071] In step S110, a set of projection histograms is obtained by performing rotational projection on the tire belt layer image using a projection frame. According to some embodiments of the present application, the projection frame may be a rectangular projection frame located in the middle area of the tire belt layer image. The process of the rotational projection includes rotating the rectangular projection frame from 0° to 180° to obtain projection histograms respectively. As shown in FIGS. 3A and 3B, the projection histograms of the belt layer with and without cords when the rectangular projection frame is rotated by 30° are shown respectively.

[0072] In step S130, calculate the eigenvalues corresponding to the set of projection histograms. According to an exemplary embodiment of the present application, the eigenvalues include one or more of: the number of maxima, the number of minima, the average period of maxima, the variance of the period of maxima, the average period of minima, and the variance of the period of minima. Calculating the eigenvalues corresponding to the projection histogram includes:

[0073] First, calculate the number of peaks and the number of valleys in the projection histogram, that is, the number of maxima and the number of minima;

[0074] Next, calculate the average period of maxima and the variance of the period of maxima;

[0075] Finally, calculate the average period of minima and the variance of the period of minima.

[0076] In step S140, determine the cord missing situation at the position of the projection frame according to the eigenvalues and the size of the projection frame. After calculating the eigenvalues of the projection histogram, the cord missing situation at the position of the projection frame can be determined according to the number of maxima, the number of minima, the average period of maxima, the variance of the period of maxima, the average period of minima, the variance of the period of minima, and the size of the rectangular projection frame.

[0077] According to an exemplary embodiment of the present application, when the number of maxima, the average period of maxima, the number of minima, the average period of minima, and the width of the rectangular projection frame satisfy the following conditions, there is a cord missing at the position of the projection frame:

[0078] N max ×T max ≈N min ×T min ≈D

[0079] Wherein, N max is the number of maxima, T max is the average period of maxima, N min is the number of minima, T min is the average period of minima, and D is the width of the projection frame.

[0080] According to another embodiment of the present application, when the variance of the period of maxima and the variance of the period of minima satisfy the following conditions with a set threshold, there is a cord missing at the position of the projection frame:

[0081] σ max <a max ,σ min <a min

[0082] Wherein, σ max is the variance of the period of maxima, σ minis the minimum value of the periodic variance, a max is the set maximum value of the periodic variance threshold, a min is the set minimum value of the periodic variance threshold.

[0083] When judging the cord breakage situation of the position where the projection frame is located according to the eigenvalue and the size of the projection frame, one of the above judgment methods can be adopted, or the judgment results of the above judgment methods can be combined to determine the cord breakage situation of the position where the projection frame is located.

[0084] Figure 4 Shows a flowchart of a tire belt layer defect detection method according to another embodiment of the present application.

[0085] According to another embodiment of the present application, the defect detection method of the above tire belt layer further includes:

[0086] In step S100, preprocess the tire image and segment the tire belt layer image.

[0087] According to the exemplary embodiment of the present application, for the original tire X-ray image as shown in Figure 5A , gamma transformation can be performed first to stretch the smaller gray values in the image and improve the overall brightness of the tire image. The tire image after gamma transformation is as shown in Figure 5B . Next, taking the device shadow in the transformed tire image as the reference boundary, perform projection rough segmentation to segment the shoulder and belt layer parts in the tire image. The segmented tire image is as shown in Figure 5C . Then, use the adaptive binary algorithm for the segmented tire image to obtain the belt layer boundary. Finally, taking the second belt layer boundaries on the left and right sides as the left and right boundaries of the belt layer, segment the tire belt layer image in the tire image, as shown in Figure 5D .

[0088] Before step S130, the above defect detection method of the tire belt layer further includes:

[0089] In step S120, perform mean smoothing on the group of projection histograms. According to the exemplary embodiment of the present application, the mean smoothing process may include the following steps:

[0090] First, determine the burr points in the projection histogram. For example, determine the maximum value points in the projection histogram with relatively low peak height compared to other peak heights, a large difference in the ordinate of the minimum value points at the left and right ends, and a particularly narrow width of the peak as burrs.

[0091] Next, perform mean smoothing on the burr points and the minimum value points at their left and right ends in the projection histogram according to the following formula:

[0092]

[0093] Among them, H l is the gray value of the burr point, and H s1 , H s2 are the gray values of the minimum value points at the left and right ends of the burr point. According to some embodiments of the present application, for two or more consecutive burr points, the highest burr point can be first judged and retained, and then the other burrs are smoothed by averaging.

[0094] By smoothing the burr points in the projection histogram, the influence of the burr points on the characteristic peaks of the projection histogram can be avoided.

[0095] In step S150, the projection frame traverses the entire image from top to bottom in the belt layer image, and steps S100 to S140 are repeated to obtain the cord missing conditions at each position.

[0096] After steps S100 to S140 are executed, the image at the position of the projection frame is detected. To perform a complete defect detection on this belt layer, it is also necessary to traverse the entire image from top to bottom starting from the top position of the tire belt layer, and judge whether there is a cord missing in the image at each position of the projection frame.

[0097] In step S160, if there is a cord missing at a certain position of the projection frame, it is determined that there is a belt layer missing in the belt layer image. If there is no cord missing in the images at all positions of the projection frame, it can be determined that the tire does not have a belt layer missing defect.

[0098] Figure 6 Shows a schematic diagram of the execution process of the tire belt layer defect detection method according to an exemplary embodiment of the present application.

[0099] As Figure 6 shown, the tire belt layer defect detection method provided by the present application may include the following steps during execution:

[0100] In step S210, read the X-ray image of the tire.

[0101] In step S220, preprocess the tire image to obtain the tire belt layer image.

[0102] In step S230, set the rotation projection angle Degree = 0.

[0103] In step S240, judge whether the rotation projection angle satisfies Degree ≤ 180. When this condition is not met, step S250 is executed; when this condition is met, step S300 is executed.

[0104] In step S250, perform a rotation projection to obtain a projection histogram.

[0105] In step S260, perform mean smoothing on the projection histogram.

[0106] In step S270, extract the eigenvalue of the projection histogram.

[0107] In step S280, judge and record the missing cord situation according to the eigenvalue.

[0108] In step S290, increase the rotation projection angle: Degree++, and execute step S240.

[0109] In step S300, record the missing belt layer situation at the current position of the projection frame.

[0110] In step S310, move the projection frame downward.

[0111] In step S320, judge whether the image traversal is finished. When the image traversal is not finished, execute step S230; when the image traversal is finished, execute step S330.

[0112] In step S330, judge the missing belt layer situation according to the missing cord situation at all positions of the projection frame.

[0113] Figure 7 Show a block diagram of a tire belt layer defect detection device according to an exemplary embodiment of the present application.

[0114] According to another aspect of the present application, there is also provided a defect detection device 200 for a tire belt layer, including a first image processing module 210, a second image processing module 220, a third image processing module 230, an eigenvalue calculation module 240, and a defect judgment module 250. Among them,

[0115] The first image processing module 210 can be used to preprocess the tire image and segment the tire belt layer image. For example, the tire image can be an X-ray image. The preprocessing process can include gamma transformation, projection rough segmentation, and adaptive binary segmentation, etc. The belt layer image can be segmented from the tire image through the first image processing module.

[0116] The second image processing module 220 can be used to perform rotational projection on the tire belt layer image using a projection frame to obtain a set of projection histograms. The projection frame can be a rectangular projection frame located in the middle area of the tire belt layer image. The process of rotational projection can be to rotate the rectangular projection frame from 0° to 180°, and obtain projection histograms respectively.

[0117] The third image processing module 230 can be used to perform mean smoothing on the set of projection histograms. The mean smoothing process may include determining the spike points in the projection histogram, and then performing mean smoothing on the spike points and the minimum value points at both ends thereof in the projection histogram, so as to avoid the influence of the spike points on the characteristic peaks of the projection histogram.

[0118] The eigenvalue calculation module 240 can be used to calculate the eigenvalues corresponding to the set of projection histograms. The eigenvalues may include one or more of: the number of maximum values, the number of minimum values, the average period of the maximum values, the variance of the maximum value periods, the average period of the minimum values, and the variance of the minimum value periods.

[0119] The defect judgment module 250 can be used to judge the cord missing condition at the position where the projection frame is located according to the eigenvalues and the size of the projection frame, and judge the band layer defect condition in the tire band layer image according to the cord missing conditions at all positions of the projection frame.

[0120] Figure 8 The block diagram showing the composition of the electronic device for detecting tire band layer defects according to the exemplary embodiments of the present application.

[0121] The present application also provides an electronic device 600 for detecting tire band layer defects. Figure 8 The displayed electronic device 600 is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present application.

[0122] As Figure 8 shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), etc.

[0123] The storage unit 620 stores the processing program code, and the processing program code can be executed by the processing unit 610, so that the processing unit 610 executes the methods according to the various embodiments of the present application described in this specification.

[0124] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 6201 and / or a cache storage unit 6202, and may further include a read-only storage unit (ROM) 6203.

[0125] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205. Such program modules 6205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment.

[0126] The bus 630 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus structures.

[0127] The electronic device 600 may also communicate with one or more external devices 6001 (such as a touch screen, keyboard, pointing device, Bluetooth device, etc.), and may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (such as a router, modem, etc.). Such communication may be through an input / output (I / O) interface 650. Also, the electronic device 600 may communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 through the bus 630. It should be understood that although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0128] According to some embodiments of the present application, the present application may also provide a computer-readable medium having a computer program stored thereon, and when the computer program is executed by a processor, the above-mentioned defect detection method is implemented.

[0129] The defect detection method for the tire belt layer provided by the present application converts the complex texture features of the cord into an intuitive and accurate peak-valley undulation state in the projection histogram through rotational projection, thereby simplifying the difficulty of detecting the missing defect of the belt layer. In addition, by calculating eigenvalue such as the number of maxima, the average period of maxima, the number of minima, the average period of minima, the variance of the maxima period, and the variance of the minima period in the projection histogram, the undulation state of the peaks and valleys in the projection histogram is comprehensively reflected, thereby ensuring the comprehensiveness of the detection algorithm.

[0130] The above has introduced the embodiments of the present application in detail. Specific examples are used in this text to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application. At the same time, any changes or deformations made by those skilled in the art based on the idea of the present application, within the specific implementation manner and application scope of the present application, fall within the scope of protection of the present application. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for defect detection of a tire belt layer, characterized in that, Including: Performing rotational projection on the tire belt layer image using a projection frame to obtain a set of projection histograms; Calculating the eigenvalues corresponding to the set of histograms; Judging the cord missing situation at the position where the projection frame is located according to the eigenvalues and the size of the projection frame; Traversing the entire image from top to bottom with the projection frame in the belt layer image; At each position, performing rotational projection on the tire belt layer image using the projection frame to obtain a set of projection histograms; Calculating the eigenvalues corresponding to the set of histograms at each position of the projection frame; Judging the cord missing situation at each position where the projection frame is located according to the eigenvalues and the size of the projection frame; If there is cord missing at any position of the projection frame, it is determined that there is a belt layer missing in the belt layer image; The eigenvalues include one or more of the number of maximum values, the number of minimum values, the average period of maximum values, the period variance of maximum values, the average period of minimum values, and the period variance of minimum values; Judging the cord missing situation at the position where the projection frame is located according to the eigenvalues and the size of the projection frame includes: When the number of maximum values, the average period of maximum values, the number of minimum values, and the average period of minimum values satisfy the following conditions with the width of the projection frame, then there is cord missing at the position where the projection frame is located: wherein, is the number of maximum values, is the average period of maximum values, is the number of minimum values, is the average period of minimum values, is the width of the projection frame; or When the period variance of maximum values and the period variance of minimum values satisfy the following conditions with the set threshold, then there is cord missing at the position where the projection frame is located: Among them, is the maximum value period variance, is the minimum value period variance, is the set maximum value period variance threshold, is the set minimum value period variance threshold.

2. The defect detection method according to claim 1, characterized in that, The projection frame includes: A rectangular projection frame located in the middle area of the tire belt layer image.

3. The defect detection method according to claim 2, wherein The obtaining of a set of projection histograms includes: The projection histograms respectively obtained by rotating the rectangular projection frame from 0° to 180°.

4. The defect detection method according to claim 1, characterized in that Also including: Preprocessing the tire image and segmenting out the tire belt layer image.

5. The defect detection method according to claim 4, wherein The preprocessing includes: Performing gamma transformation on the tire image; Taking the device shadow in the transformed tire image as the reference boundary to perform projection rough segmentation, and segmenting out the shoulder and belt layer parts in the tire image; Adopting an adaptive binary algorithm for the segmented tire image to obtain the belt layer boundary; Taking the second belt layer boundaries on the left and right sides as the left and right boundaries of the belt layer, and segmenting out the tire belt layer image in the tire image.

6. The defect detection method according to claim 1, characterized in that, Before calculating the eigenvalues corresponding to the set of projection histograms, it also includes: Performing mean smoothing processing on the set of projection histograms.

7. The defect detection method according to claim 6, wherein The smoothing processing includes: Performing mean smoothing on the burr points and the minimum value points at both ends on the left and right of the projection histogram according to the following formula: Among them, is the gray value of the burr point, , are the gray values of the minimum value points at both ends of the burr point.

8. A defect detection device for a tire belt layer, characterized in that, For executing the defect detection method as described in any one of claims 1 - 7, the defect detection device includes: A first image processing module for preprocessing the tire image and segmenting out the tire belt layer image; A second image processing module for performing rotational projection on the tire belt layer image using a projection frame to obtain a set of projection histograms; A third image processing module for performing mean smoothing processing on the set of projection histograms; An eigenvalue calculation module for calculating the eigenvalues corresponding to the set of projection histograms; A defect judgment module, configured to judge the cord missing situation at the position where the projection frame is located according to the feature value and the size of the projection frame, and judge the belt layer defect situation in the tire belt layer image according to the cord missing situations at all positions of the projection frame; The defect judgment module is further configured to: Traverse the entire belt layer image from top to bottom with the projection frame in the belt layer image; Perform rotational projection on the tire belt layer image using the projection frame at each position to obtain a set of projection histograms; Calculate the feature value corresponding to the set of histograms at each position of the projection frame; Judge the cord missing situation at each position where the projection frame is located according to the feature value and the size of the projection frame; If there is a cord missing at any position of the projection frame, it is determined that there is a belt layer missing in the belt layer image.

9. An electronic device, characterized in that, Comprising: One or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the defect detection method according to any one of claims 1-7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the defect detection method according to any one of claims 1-7.

Images