A method and system for image segmentation of ceramic cracks

Abstract

The present invention relates to the technical field of ceramic crack extraction, and in particular to an image segmentation method and system for ceramic cracks. Firstly, an image containing ceramics is preprocessed and graphic segmented to obtain a ceramic image, wherein the ceramic image is a grayscale image. Then, cracks in the ceramic image are extracted, and the minimum circumscribed rectangle of the crack is determined, and the image region where the minimum circumscribed rectangle is located is used as an image to be identified. Then, image enhancement is performed on the image to be identified, and the image to be identified after image enhancement is segmented step by step using a sliding window method to determine whether cracks exist in the segmented local image, and the local image with cracks is used as a crack image. Finally, the cracks of the ceramic are determined according to the crack image and the ceramic image, and the ceramic cracks determined by the present invention are more accurate.

Description

Technical Field

[0001] The invention relates to the technical field of ceramic crack extraction, and in particular to a ceramic crack image segmentation method and system. Background Art

[0002] In the process of ceramic production, how to accurately detect and locate ceramic surface cracks is of great significance for analyzing defects in the ceramic production process and improving the ceramic production process.

[0003] In the existing technology, manual visual quality inspection is prone to missed inspections, and is time-consuming and labor-intensive, which cannot meet the current development needs of intelligent manufacturing. Therefore, an efficient, reliable and low-cost ceramic crack identification method is urgently needed to solve the above problems. Summary of the invention

[0004] The present invention provides a ceramic crack image segmentation method and system to solve one or more technical problems existing in the prior art, and at least provide a beneficial choice or create conditions.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] A method for image segmentation of ceramic cracks, the method comprising the following steps:

[0007] Preprocessing and segmenting the image containing ceramics to obtain a ceramic image, wherein the ceramic image is a grayscale image;

[0008] Extracting cracks from the ceramic image, determining a minimum bounding rectangle of the crack, and using the image region where the minimum bounding rectangle is located as an image to be identified;

[0009] Performing image enhancement on the image to be identified, segmenting the image to be identified after image enhancement step by step using a sliding window method, determining whether a local image obtained by segmentation has cracks, and using the local image with cracks as a crack image;

[0010] The cracks of the ceramic are determined according to the crack image and the ceramic image.

[0011] Further, the preprocessing and graphic segmentation of the image containing ceramics to obtain the ceramic image includes:

[0012] The CV model is used to segment the ceramic image to obtain the ceramic outer contour curve, and the ceramic outer contour curve is used as the ceramic image.

[0013] Furthermore, the cracks in the ceramic image are extracted by using any one of an edge detection algorithm, a threshold segmentation algorithm or a maximum inter-class variance method.

[0014] Furthermore, the local image is obtained by scaling down the image to be recognized in equal proportion, and the ratio of the local image to the image to be recognized is in the range of [0.01, 0.5].

[0015] Furthermore, the step size of the local image is the width of the local image.

[0016] Furthermore, the method for performing image enhancement on the image to be identified comprises:

[0017] The image to be identified is enhanced based on a point operation algorithm or a neighborhood denoising algorithm.

[0018] Further, determining the crack of the ceramic according to the crack image and the ceramic image includes:

[0019] Determine a pixel point where the crack is located in the crack image, calculate a first difference between a grayscale value of the pixel point in the crack image and a grayscale value in the ceramic image, and if the first difference is within a threshold range, take the pixel point as a valid point;

[0020] If the first difference exceeds the threshold range, eight adjacent points of the pixel in the crack image are determined, and second differences between the grayscale values ​​of the eight adjacent points in the crack image and the grayscale values ​​in the ceramic image are calculated respectively, and the adjacent point with the smallest second difference is taken as a valid point;

[0021] If the eight second differences are all beyond the threshold range, a 9*9 candidate pixel area is determined with the pixel as the center, and a candidate pixel is selected from the pixel search area in sequence from top to bottom along the sliding direction of the crack image, and the third difference between the gray value of the candidate pixel in the crack image and the gray value in the ceramic image is calculated respectively, and the adjacent point with the smallest third difference is taken as a valid point;

[0022] If all 80 third difference values ​​exceed the threshold range, the pixel point is regarded as an invalid point;

[0023] All effective points are connected to form cracks in the ceramic.

[0024] A ceramic crack image segmentation system, the system comprising:

[0025] at least one processor;

[0026] at least one memory for storing at least one program;

[0027] When the at least one program is executed by the at least one processor, the at least one processor implements any one of the above-mentioned methods for image segmentation of ceramic cracks.

[0028] A computer-readable storage medium stores a ceramic crack image segmentation program, which implements the steps of any one of the above-mentioned ceramic crack image segmentation methods when executed by a processor.

[0029] The beneficial effects of the present invention are as follows: the present invention discloses an image segmentation method and system for ceramic cracks. The present invention first directly extracts cracks from the ceramic image, then determines the minimum circumscribed rectangle of the cracks, and uses the image area where the minimum circumscribed rectangle is located as the image to be identified; further narrows the scope of image processing and improves processing efficiency. After the image to be identified is enhanced, the sliding window method is used to extract cracks in sections, and the cracks after image enhancement and the directly extracted cracks are integrated. The cracks of the ceramic are obtained by integrating the crack image and the ceramic image, and the ceramic cracks finally determined are more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0031] Figure 1 is a schematic flow chart of a ceramic crack image segmentation method according to an embodiment of the present invention;

[0032] Figure 2 Schematic diagram of searching for effective points in an embodiment of the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of this application, so as to fully understand the purpose, scheme and effect of this application. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0034] refer to Figure 1 ,like Figure 1 A ceramic crack image segmentation method provided in an embodiment of the present application is shown, and the method comprises the following steps:

[0035] Step S100, preprocessing and segmenting the image containing ceramics to obtain a ceramic image, wherein the ceramic image is a grayscale image;

[0036] Step S200, extracting cracks from the ceramic image, determining the minimum bounding rectangle of the crack, and using the image area where the minimum bounding rectangle is located as the image to be identified;

[0037] Step S300, performing image enhancement on the image to be identified, using a sliding window method to gradually segment the image to be identified after image enhancement, determining whether a local image obtained by segmentation has cracks, and using the local image with cracks as a crack image;

[0038] Step S400: determining cracks of the ceramic according to the crack image and the ceramic image.

[0039] In the embodiment provided by the present invention, cracks are first directly extracted from the ceramic image, and then the minimum circumscribed rectangle of the cracks is determined, and the image area where the minimum circumscribed rectangle is located is used as the image to be identified; the scope of image processing is further narrowed and the processing efficiency is improved. After the image to be identified is enhanced, the cracks are extracted in sections using a sliding window method, and the cracks after image enhancement and the directly extracted cracks are integrated. The cracks of the ceramic are obtained by integrating the crack image and the ceramic image, and the ceramic cracks finally determined are more accurate.

[0040] In an improved embodiment, the preprocessing and graphic segmentation of the image containing ceramics to obtain the ceramic image includes:

[0041] The CV model is used to segment the ceramic image to obtain the ceramic outer contour curve, and the ceramic outer contour curve is used as the ceramic image.

[0042] In an improved embodiment, the cracks in the ceramic image are extracted by using any one of an edge detection algorithm, a threshold segmentation algorithm or a maximum inter-class variance method.

[0043] In an improved embodiment, the partial image is obtained by scaling down the image to be recognized in equal proportion, and the ratio of the partial image to the image to be recognized is in the range of [0.01, 0.5].

[0044] In an improved embodiment, the step size of the partial image is the width of the partial image.

[0045] In an improved embodiment, the method for performing image enhancement on the image to be identified includes:

[0046] The image to be identified is enhanced based on a point operation algorithm or a neighborhood denoising algorithm.

[0047] Among them, point operation algorithms include grayscale correction, grayscale transformation and histogram correction, etc., the purpose is to make the image uniform, or to expand the dynamic range of the image and extend the contrast. Neighborhood enhancement algorithms include image smoothing and image sharpening.

[0048] In an improved embodiment, the step S400 includes:

[0049] Determine a pixel point where the crack is located in the crack image, calculate a first difference between a grayscale value of the pixel point in the crack image and a grayscale value in the ceramic image, and if the first difference is within a threshold range, take the pixel point as a valid point;

[0050] If the first difference exceeds the threshold range, eight adjacent points of the pixel in the crack image are determined, and second differences between the grayscale values ​​of the eight adjacent points in the crack image and the grayscale values ​​in the ceramic image are calculated respectively, and the adjacent point with the smallest second difference is taken as a valid point;

[0051] If the eight second differences are all beyond the threshold range, a 9*9 candidate pixel area is determined with the pixel as the center, and a candidate pixel is selected from the pixel search area in sequence from top to bottom along the sliding direction of the crack image, and the third difference between the gray value of the candidate pixel in the crack image and the gray value in the ceramic image is calculated respectively, and the adjacent point with the smallest third difference is taken as a valid point;

[0052] If all 80 third difference values ​​exceed the threshold range, the pixel point is regarded as an invalid point;

[0053] All effective points are connected to form cracks in the ceramic.

[0054] refer to Figure 2In a specific embodiment, let point O be the pixel point where the crack is located in the crack image, let point A be one of the eight adjacent points of the pixel point in the crack image, let point B be a candidate pixel point in the 9*9 pixel candidate area, then first determine the first difference between the grayscale value of the pixel point in the crack image and the grayscale value in the ceramic image to determine whether the pixel point is a valid point; if not, determine whether there is a point within the threshold range among the eight adjacent points. Taking point A as an example, if the second difference between the grayscale value of point A in the crack image and the grayscale value in the ceramic image is within the threshold range, and the second difference calculated based on point A is within the 8 If the third difference between the grayscale value of point B in the crack image and the grayscale value of point B in the ceramic image is within the threshold range, and the third difference calculated based on point B is the smallest among the third difference calculated for all the candidate pixels in the 9*9 pixel candidate area, then point B is determined to be a valid point; if no valid point is found in the 9*9 pixel candidate area, the pixel is regarded as an invalid point and discarded; finally, all the valid points are connected, and the final pattern is the crack of the searched ceramic.

[0055] and Figure 1 Corresponding to the method, an embodiment of the present invention further provides an image segmentation system for ceramic cracks, the system comprising:

[0056] at least one processor;

[0057] at least one memory for storing at least one program;

[0058] When the at least one program is executed by the at least one processor, the at least one processor implements the ceramic crack image segmentation method described in any one of the above embodiments.

[0059] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0060] and Figure 1 Corresponding to the method, an embodiment of the present invention further provides a computer-readable storage medium, on which a ceramic crack image segmentation program is stored. When the ceramic crack image segmentation program is executed by a processor, the steps of the ceramic crack image segmentation method as described in any of the above embodiments are implemented.

[0061] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the image segmentation system of ceramic cracks, and uses various interfaces and lines to connect various parts of the entire ceramic crack image segmentation system to operate the device.

[0062] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the image segmentation system of ceramic cracks by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart-Media-Card, SMC), a secure digital (Secure-Digital, SD) card, a flash card (Flash-Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0063] Although the description of the present application has been quite detailed and specifically describes several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but should be regarded as providing a broad possible interpretation of these claims by reference to the attached claims, taking into account the prior art, so as to effectively cover the intended scope of the present application. In addition, the above description of the present application is based on the embodiments foreseeable by the inventor, and its purpose is to provide a useful description, and those non-substantial changes to the present application that have not yet been foreseen may still represent equivalent changes to the present application.

Claims

1. A method for image segmentation of ceramic cracks, characterized in that: The method comprises the following steps: Preprocessing and segmenting the image containing ceramics to obtain a ceramic image, wherein the ceramic image is a grayscale image; Extracting cracks from the ceramic image, determining a minimum bounding rectangle of the crack, and using the image region where the minimum bounding rectangle is located as an image to be identified; Performing image enhancement on the image to be identified, segmenting the image to be identified after image enhancement step by step using a sliding window method, determining whether a local image obtained by segmentation has cracks, and using the local image with cracks as a crack image; determining cracks of the ceramic according to the crack image and the ceramic image; The determining the crack of the ceramic according to the crack image and the ceramic image comprises: Suppose point O is the pixel point where the crack is located in the crack image, point A is one of the 8 adjacent points of the pixel point in the crack image, and point B is a candidate pixel point in the 9*9 pixel candidate area. Then, first determine the first difference between the grayscale value of the pixel point in the crack image and the grayscale value in the ceramic image; if the first difference is within the threshold range, then take the pixel point as a valid point; if the first difference exceeds the threshold range, then determine whether there is a point within the threshold range among the 8 adjacent points. If the second difference between the grayscale value of point A in the crack image and the grayscale value in the ceramic image is within the threshold range, and the first difference calculated based on point A is If the second difference is the smallest among the 8 adjacent points, point A is determined to be a valid point; if the 8 second differences are all beyond the threshold range, the search range will be further expanded, and if the third difference between the grayscale value of point B in the crack image and the grayscale value in the ceramic image is within the threshold range, and the third difference calculated based on point B is the smallest among the third differences calculated for all candidate pixel points in the 9*9 pixel candidate area, point B is determined to be a valid point; if no valid point is still found in the 9*9 pixel candidate area, the pixel point is regarded as an invalid point and discarded; finally, all the valid points are connected, and the final pattern is the crack of the searched ceramic.

2. The method for image segmentation of ceramic cracks according to claim 1, characterized in that: The step of preprocessing and segmenting the image containing ceramics to obtain a ceramic image includes: The CV model is used to segment the ceramic image to obtain the ceramic outer contour curve, and the ceramic outer contour curve is used as the ceramic image.

3. The method for image segmentation of ceramic cracks according to claim 2, characterized in that: The cracks of the ceramic image are extracted by using any one of an edge detection algorithm, a threshold segmentation algorithm or a maximum inter-class variance method.

4. The method for image segmentation of ceramic cracks according to claim 3, characterized in that: The local image is obtained by scaling down the image to be identified in equal proportion, and the ratio of the local image to the image to be identified is in the range of [0.01, 0.5].

5. The method for image segmentation of ceramic cracks according to claim 4, characterized in that: The step size of the local image is the width of the local image.

6. The method for image segmentation of ceramic cracks according to claim 5, characterized in that: The method for performing image enhancement on the image to be identified comprises: The image to be identified is enhanced based on a point operation algorithm or a neighborhood denoising algorithm.

7. A ceramic crack image segmentation system, characterized in that: The system comprises: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the image segmentation method for ceramic cracks as described in any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a ceramic crack image segmentation program, and when the ceramic crack image segmentation program is executed by the processor, the steps of the ceramic crack image segmentation method according to any one of claims 1 to 6 are implemented.

Images