A method for detecting defects of white grey fabric
By selecting appropriate detection modes and methods based on fabric weaving parameters and detecting fabric defects under different weaving methods, the problems of bias in the prior art and insufficient detection accuracy are solved, and a more comprehensive and accurate cloth quality evaluation is achieved.
Patent Information
- Application Number
- CN202410814743.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-24
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-06-24
AI Technical Summary
When judging the quality of fabric, the existing fabric defect detection system ignores the impact of wiring methods on fabric quality under different weaving methods, resulting in biased judgments, and manual inspection is high labor intensity and machine inspection accuracy is insufficient.
By obtaining the weaving parameters of the fabric, selecting different detection modes according to the type of braiding parameter, dividing the detection areas, detecting abnormal situations of the braided line, and performing detailed detection by simulating the extension path of the abnormal line and calculating the angle variance, so as to improve the detection Comprehensiveness and precision.
It improves the comprehensiveness and accuracy of cloth quality evaluation, can more accurately detect defects under different weaving methods, and reduces the detection cost and labor intensity.
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of cloth detection, and in particular to a method for detecting defects of white cloth. Background Art
[0002] Grey fabric is a pure white fabric that has not been dyed, printed or otherwise processed. Its ingredients can be cotton, linen, chemical fiber, etc. Grey fabric is the original state of clothing production. After cutting, splicing, sewing and other processes, it can eventually be made into various clothing, bedding, home textiles, decorations, industrial supplies, medical supplies, etc.
[0003] Before the white fabric leaves the factory, it is generally necessary to inspect the surface quality of the fabric. Only when the number of defect points contained in the fabric does not exceed the allowable range, the fabric is identified as a qualified product and is allowed to leave the factory. In the related art, the surface defects of the fabric are often inspected manually or by machine. When manual inspection is adopted, not only is the labor intensity high, but the judgment is also greatly influenced by subjectivity. When machine inspection is adopted, a Chinese reference document with application publication number CN117147559A discloses a fabric defect detection system and method. When the material defect detection system is used, the fabric to be inspected is illuminated by a light source module to form an illumination area for different types of defects, and the illumination area on the fabric to be inspected is imaged by an acquisition module to ensure that the acquisition module can accurately acquire the main light group image and the auxiliary light group image of the fabric to be inspected, and the main light group image and the auxiliary light group image are detected for defect points to avoid missed detection and improve the detection accuracy.
[0004] Most of the existing fabric defect detection systems focus on defects such as coarse and fine warp and weft defects, damage defects, pilling defects, hole defects, stains defects, etc. on the fabric, but ignore the impact of different wiring methods under different weaving methods on fabric quality, which leads to a certain bias in the judgment of fabric quality. Summary of the invention
[0005] Based on this, it is necessary to provide a defect detection method for white fabric in order to improve the detection quality in the current fabric detection process.
[0006] The above purpose is achieved through the following technical solutions:
[0007] A method for detecting defects of a greige fabric, the method comprising:
[0008] Get the weaving parameters of the cloth;
[0009] If the weaving parameters belong to the first target type, first information of the fabric is obtained and the fabric is detected according to the first detection mode; if the weaving parameters belong to the second target type, second information of the fabric is obtained and the fabric is detected according to the second detection mode;
[0010] The first information includes a first image;
[0011] The first detection mode includes:
[0012] Divide the first image into N detection areas, and detect all the detection areas in sequence along a preset path, where N is a natural number greater than 1;
[0013] Detect the braided wire in the i-th detection area, i=1, 2 to N;
[0014] If the braided wire belongs to the first abnormal form, the braided wire is marked as abnormal line one, and if the braided wire belongs to the second abnormal form, the braided wire is marked as abnormal line two;
[0015] Count the total number of abnormal first-line and abnormal second-line;
[0016] When the total number of abnormal one lines and abnormal two lines is greater than or equal to a first preset number, the i-th detection area is marked as an abnormal area, and the abnormal area is detected through an abnormal program.
[0017] Furthermore, abnormal procedures include:
[0018] If the abnormal line does not pass through the boundary of the i-th detection area, the number of pixel blocks that the abnormal line passes through is counted;
[0019] When the number of pixel blocks passed by the abnormal line is greater than a second preset number, an alarm is triggered.
[0020] Furthermore, the abnormal procedure also includes:
[0021] If the abnormal line passes through the boundary of the i-th detection area, the extension path of the abnormal line is simulated;
[0022] acquiring a second image of the detection area on the extended path;
[0023] Correct the detection area that the abnormal line actually passes through;
[0024] Acquire a third image of the detection area that the abnormal line actually passes through, wherein the resolution of the third image is greater than the resolution of the first image;
[0025] The braiding wires in the third image are detected.
[0026] Furthermore, the abnormal procedure also includes:
[0027] Count the number of pixel blocks that the abnormal second line passes through;
[0028] When the number of pixel blocks passed by the abnormal second line is greater than a third preset number, an alarm is triggered.
[0029] Furthermore, if the weaving parameter belongs to the first target type, first information of the fabric is obtained and detection is performed according to the first detection mode, further comprising:
[0030] Obtain the angles A1, A2, ..., AM between the braided wires in the i-th detection area, where M is a natural number greater than 2;
[0031] Calculate the variance of A1, A2, ..., AM;
[0032] If the variance is within the set range, the i-th detection area is marked as a good product.
[0033] Furthermore, if the weaving parameter belongs to the first target type, first information of the fabric is obtained and detection is performed according to the first detection mode, further comprising:
[0034] If the number of abnormal areas is zero, the total number of abnormal first lines and abnormal second lines in all detection areas are sorted from large to small;
[0035] Acquire a fourth image of the first X detection areas, where the resolution of the fourth image is greater than the resolution of the first image, and X is a natural number greater than or equal to 1;
[0036] The braided wires in the fourth image are detected.
[0037] Furthermore, if the weaving parameter belongs to the first target type, first information of the fabric is obtained and detection is performed according to the first detection mode, further comprising:
[0038] When the number of abnormal areas is greater than a fourth preset number, an alarm is triggered.
[0039] Furthermore, the first image is captured by a pre-installed capturing device.
[0040] Further, the second information includes a fifth image; if the weaving parameter belongs to the second target type, obtaining the second information of the fabric and performing detection according to the second detection mode includes:
[0041] Divide the fifth image into Q detection areas, and detect all the detection areas in sequence along a preset path, where Q is a natural number greater than 1;
[0042] Detect the braided wires in the Pth detection area, P = 1, 2 to Q;
[0043] If the braided wire belongs to the third abnormal form, the braided wire is marked as abnormal third wire;
[0044] Count the number of abnormal three lines;
[0045] When the number of abnormal three lines is greater than or equal to the fifth preset number, an alarm is triggered.
[0046] Furthermore, the preset path is an S-shaped path to detect all detection areas.
[0047] The beneficial effects of the present invention are:
[0048] When used, the defect detection method for white grey fabric provided by the present invention first obtains the weaving parameters of the fabric; if the weaving parameters belong to the first target type, obtains the first information of the fabric and performs detection according to the first detection mode; if the weaving parameters belong to the second target type, obtains the second information of the fabric and performs detection according to the second detection mode. Thus, the quality of fabrics with different weaving methods and different routing methods can be detected through different detection modes, thereby improving the comprehensiveness of fabric quality judgment. DETAILED DESCRIPTION
[0049] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail by way of embodiments below. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0050] The serial numbers assigned to the components herein, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning. The "connection" and "coupling" mentioned in this application, unless otherwise specified, include direct and indirect connections (couplings).
[0051] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.
[0052] A defect detection method for a grey fabric provided by an embodiment of the present invention is used to detect defects in the grey fabric. In this embodiment, the defect detection method for the grey fabric is configured to include:
[0053] Get the weaving parameters of the cloth;
[0054] Specifically, the weaving method of the white fabric can be identified manually, and then the identified weaving form can be input into a computer; or the barcode information on the white fabric can be automatically read by a camera, and the barcode information includes the weaving method of the white fabric.
[0055] More specifically, the weaving methods of greige fabric include warp and weft interweaving, interweaving of multiple weaving threads, interweaving of special threads, and the like.
[0056] If the weaving parameters belong to the first target type, first information of the fabric is obtained and the fabric is detected according to the first detection mode; if the weaving parameters belong to the second target type, second information of the fabric is obtained and the fabric is detected according to the second detection mode;
[0057] Specifically, the first target type is that the weaving method of the white fabric is warp and weft interlacing, and the alignment of the warp and weft is cross-shaped or X-shaped; the second target type is that the weaving method of the white fabric is warp and weft interlacing, and the alignment of the warp and weft is loop-shaped.
[0058] More specifically, when the warp and weft of the cloth are arranged in a cross shape, multiple warp threads are arranged in parallel and at equal intervals in the horizontal direction, and multiple weft threads are arranged in parallel and at equal intervals in the vertical direction, and the angle between the warp threads and the weft threads is ninety degrees; when the warp and weft of the cloth are arranged in an X shape, the angle between the warp and the weft threads is a preset angle, and the preset angle is not equal to ninety degrees; when the warp or weft of the cloth is arranged in a loop shape, the warp or weft threads are bent into coils in sequence, and the coils are then interlaced.
[0059] The first information includes a first image;
[0060] Specifically, a pre-installed shooting device may be used to shoot to obtain a square or rectangular first image.
[0061] It is understandable that the first image can be set to be taken by a camera with a smaller magnification and lower precision, so as to reduce the detection cost while ensuring the detection efficiency.
[0062] It can be understood that the first image can be a color image or a black-and-white image.
[0063] The first detection mode includes:
[0064] Divide the first image into N detection areas, and detect all the detection areas in sequence along a preset path, where N is a natural number greater than 1;
[0065] Specifically, N can be set to nine so that the first image forms a nine-grid arrangement, and one grid represents a detection area; more specifically, the preset path can be set to an S-shaped path to detect the nine detection areas in sequence along the horizontal direction or along the vertical direction.
[0066] Detect the braided wire in the i-th detection area, i=1, 2 to N;
[0067] Specifically, the i-th detection area is any detection area among the N detection areas.
[0068] If the braided wire belongs to the first abnormal form, the braided wire is marked as abnormal line one, and if the braided wire belongs to the second abnormal form, the braided wire is marked as abnormal line two;
[0069] Specifically, the first abnormal form is line running, which means that the braided wire is in a state where it is not completely straightened; the second abnormal form is line breaking.
[0070] Count the total number of abnormal first-line and abnormal second-line;
[0071] When the total number of abnormal one lines and abnormal two lines is greater than or equal to a first preset number, the i-th detection area is marked as an abnormal area, and the abnormal area is detected through an abnormal program.
[0072] Specifically, when the total number of abnormal one lines and abnormal two lines is greater than the first preset number, it means that the number of abnormal longitudes and latitudes in the current detection area is large. In order to ensure the detection quality, the current detection area needs to be focused on detection.
[0073] It can be understood that the first preset number is a set number, which can be determined according to the total number of longitudes and latitudes in the detection area.
[0074] In this embodiment, the abnormal program is configured to include:
[0075] If the abnormal line does not pass through the boundary of the i-th detection area, the number of pixel blocks that the abnormal line passes through is counted;
[0076] Specifically, when the abnormal line does not cross the boundary of the i-th detection area, it means that the abnormal line is abnormal only in the current detection area and does not affect other detection areas.
[0077] When the number of pixel blocks passed by the abnormal line is greater than a second preset number, an alarm is triggered.
[0078] Specifically, when the number of pixel blocks passed by the abnormal line is greater than the second preset number, it indicates that the abnormality of the abnormal line is relatively large and has a greater impact on the quality of the fabric. Therefore, it is set to remind the inspector through an alarm to facilitate timely processing of the abnormal line.
[0079] It can be understood that the second preset number is a set number, which can be determined according to the total number of pixel blocks in the detection area.
[0080] In this embodiment, the second information includes a fifth image;
[0081] Specifically, the fifth image may be captured by a pre-installed capturing device to obtain a square or rectangular fifth image.
[0082] It is understandable that the fifth image can be set to be taken by a camera with a smaller magnification and lower accuracy, so as to reduce the detection cost while ensuring the detection efficiency.
[0083] It can be understood that the fifth image can be a color image or a black-and-white image.
[0084] If the knitting parameters belong to the second target type, obtaining second information of the fabric and performing detection according to the second detection mode includes:
[0085] Divide the fifth image into Q detection areas, and detect all the detection areas in sequence along a preset path, where Q is a natural number greater than 1;
[0086] Specifically, Q can be set to nine so that the fifth image forms a nine-grid arrangement, and one grid represents a detection area; more specifically, the preset path can be set to an S-shaped path to detect the nine detection areas in sequence along the horizontal direction or along the vertical direction.
[0087] Detect the braided wires in the Pth detection area, P = 1, 2 to Q;
[0088] Specifically, the Pth detection area is any one of the Q detection areas.
[0089] If the braided wire belongs to the third abnormal form, the braided wire is marked as abnormal third wire;
[0090] Specifically, the third abnormal form is a situation where the warp or weft threads are offset along the weaving direction.
[0091] Count the number of abnormal three lines;
[0092] When the number of abnormal three lines is greater than or equal to the fifth preset number, an alarm is triggered.
[0093] Specifically, when the number of abnormal three lines is greater than or equal to the fifth preset number, it means that the number of abnormal warp or weft lines in the current detection area is large, which has a greater impact on the quality of the fabric. Therefore, it is set to remind the inspector through an alarm to facilitate timely processing of the abnormal three lines.
[0094] It can be understood that the fifth preset number is a set number, which can be determined according to the number of longitudes or latitudes in the detection area.
[0095] In a further embodiment, the exception procedure is arranged to further include:
[0096] If the abnormal line passes through the boundary of the i-th detection area, the extension path of the abnormal line is simulated;
[0097] Specifically, when the abnormal line passes through the boundary of the i-th detection area, it means that the abnormal line is not only abnormal in the current detection area, but also affects other detection areas. In order to ensure the accuracy of the detection, it is necessary to continuously detect the abnormal line, and the extension path of the abnormal line can be simulated by computer to preliminarily determine other detection areas affected by the abnormal line, so as to facilitate subsequent tracking and detection, thereby improving detection efficiency.
[0098] acquiring a second image of the detection area on the extended path;
[0099] Correct the detection area that the abnormal line actually passes through;
[0100] Acquire a third image of the detection area that the abnormal line actually passes through, wherein the resolution of the third image is greater than the resolution of the first image;
[0101] The braiding wires in the third image are detected.
[0102] Specifically, timely tracking of the detection area affected by the abnormal line helps to timely determine the degree of abnormality of the abnormal line and the degree of impact on fabric quality, so as to facilitate subsequent timely processing.
[0103] It is understandable that the third image can be set to be taken by a camera with a larger magnification and higher precision to ensure detection accuracy.
[0104] In a further embodiment, the exception procedure is arranged to further include:
[0105] Count the number of pixel blocks that the abnormal second line passes through;
[0106] When the number of pixel blocks passed by the abnormal second line is greater than a third preset number, an alarm is triggered.
[0107] Specifically, when the number of pixel blocks passed by the abnormal second line is greater than the third preset number, it indicates that the abnormal degree of the abnormal second line is relatively large and has a greater impact on the quality of the fabric. Therefore, it is set to remind the inspector through an alarm to facilitate timely processing of the abnormal second line.
[0108] It can be understood that the third preset number is a set number, which can be determined according to the total number of pixel blocks in the detection area.
[0109] In other embodiments, if the weaving parameter belongs to the first target type, obtaining the first information of the fabric and performing detection according to the first detection mode further includes:
[0110] Obtain the angles A1, A2, ..., AM between the braided wires in the i-th detection area, where M is a natural number greater than 2;
[0111] Calculate the variance of A1, A2, ..., AM;
[0112] If the variance is within the set range, the i-th detection area is marked as a good product.
[0113] Specifically, when the warp and weft of the cloth are arranged in a cross shape or an X shape, in addition to the conditions of the warp and weft themselves affecting the quality of the cloth, the angle between the warp and weft will also affect the quality of the cloth. Therefore, it is set to calculate the variance of the angle between each warp and each weft in the detection area to determine the discreteness of the angle between the warp and weft in the current detection area; when the variance is within the set range, it means that the discreteness of the angle between the warp and weft is small, indicating that the quality of the current detection area is high.
[0114] In other embodiments, if the weaving parameter belongs to the first target type, obtaining the first information of the fabric and performing detection according to the first detection mode further includes:
[0115] If the number of abnormal areas is zero, the total number of abnormal first lines and abnormal second lines in all detection areas are sorted from large to small;
[0116] Acquire a fifth image of the first X detection areas, where the resolution of the fifth image is greater than the resolution of the first image, and X is a natural number greater than or equal to 1;
[0117] The braided wires in the fourth image are detected.
[0118] Specifically, when the number of abnormal areas is zero, in order to avoid the situation where relatively subtle defects are not detected due to the low resolution of the first image, it is set to take the fourth image of the first X detection areas; the reason for taking the first X detection areas is that the greater the total number of abnormal one lines and abnormal two lines in the detection area, the greater the possibility that other subtle defects exist in the detection area.
[0119] It is understandable that the fourth image can be set to be taken by a camera with a larger magnification and higher precision to ensure detection accuracy.
[0120] In other embodiments, if the weaving parameter belongs to the first target type, obtaining the first information of the fabric and performing detection according to the first detection mode further includes:
[0121] When the number of abnormal areas is greater than a fourth preset number, an alarm is triggered.
[0122] Specifically, when the number of abnormal areas is greater than the fourth preset number, it indicates that the quality of the current cloth is poor. To avoid affecting the quality of subsequent processed products, an alarm is set to remind the inspector so that the cloth can be processed in time.
[0123] It can be understood that the fourth preset number is a set number, which can be determined according to the total number of detection areas.
[0124] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0125] The above-described embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.
Claims
1. A method for detecting defects in white fabric, characterized in that: The defect detection method of the white grey fabric comprises: Get the weaving parameters of the cloth; If the weaving parameters belong to the first target type, first information of the fabric is obtained and the fabric is detected according to the first detection mode; if the weaving parameters belong to the second target type, second information of the fabric is obtained and the fabric is detected according to the second detection mode; The first target type is that the weaving method of the white fabric is warp and weft interlacing, and the alignment of the warp and weft is a cross or X shape; the second target type is that the weaving method of the white fabric is warp and weft interlacing, and the alignment of the warp and weft is a circle shape; The first information includes a first image; The first detection mode includes: Divide the first image into N detection areas, and detect all the detection areas in sequence along a preset path, where N is a natural number greater than 1; Detect the braided wire in the i-th detection area, i=1, 2 to N; If the braided wire belongs to the first abnormal form, the braided wire is marked as abnormal line one, and if the braided wire belongs to the second abnormal form, the braided wire is marked as abnormal line two; Count the total number of abnormal first-line and abnormal second-line; When the total number of abnormal first lines and abnormal second lines is greater than or equal to a first preset number, the i-th detection area is marked as an abnormal area, and the abnormal area is detected by an abnormal program; The second information includes a fifth image; If the knitting parameters belong to the second target type, obtaining second information of the fabric and performing detection according to the second detection mode includes: Divide the fifth image into Q detection areas, and detect all the detection areas in sequence along a preset path, where Q is a natural number greater than 1; Detect the braided wires in the Pth detection area, P = 1, 2 to Q; If the braided wire belongs to the third abnormal form, the braided wire is marked as abnormal third wire; Count the number of abnormal three lines; When the number of abnormal three lines is greater than or equal to the fifth preset number, an alarm is triggered.
2. The method for detecting defects of greige fabric according to claim 1, characterized in that: Abnormal procedures include: If the abnormal line does not pass through the boundary of the i-th detection area, the number of pixel blocks that the abnormal line passes through is counted; When the number of pixel blocks passed by the abnormal line is greater than a second preset number, an alarm is triggered.
3. The method for detecting defects of greige fabric according to claim 2, characterized in that: Abnormal procedures also include: If the abnormal line passes through the boundary of the i-th detection area, the extension path of the abnormal line is simulated; acquiring a second image of the detection area on the extended path; Correct the detection area that the abnormal line actually passes through; Acquire a third image of the detection area that the abnormal line actually passes through, wherein the resolution of the third image is greater than the resolution of the first image; The braiding wires in the third image are detected.
4. The method for detecting defects of greige fabric according to claim 3, characterized in that: Abnormal procedures also include: Count the number of pixel blocks that the abnormal second line passes through; When the number of pixel blocks passed by the abnormal second line is greater than a third preset number, an alarm is triggered.
5. The method for detecting defects of greige fabric according to claim 1, characterized in that: If the weaving parameters belong to the first target type, obtaining first information of the fabric and performing detection according to the first detection mode also includes: Obtain the angles A1, A2, ..., AM between the braided wires in the i-th detection area, where M is a natural number greater than 2; Calculate the variance of A1, A2, ..., AM; If the variance is within the set range, the i-th detection area is marked as a good product.
6. The method for detecting defects of greige fabric according to claim 1, characterized in that: If the weaving parameters belong to the first target type, obtaining first information of the fabric and performing detection according to the first detection mode also includes: If the number of abnormal areas is zero, the total number of abnormal first lines and abnormal second lines in all detection areas are sorted from large to small; Acquire a fourth image of the first X detection areas, where the resolution of the fourth image is greater than the resolution of the first image, and X is a natural number greater than or equal to 1; The braided wires in the fourth image are detected.
7. The method for detecting defects of greige fabric according to claim 1, characterized in that: If the weaving parameters belong to the first target type, obtaining first information of the fabric and performing detection according to the first detection mode also includes: When the number of abnormal areas is greater than a fourth preset number, an alarm is triggered.
8. The method for detecting defects of greige fabric according to claim 1, characterized in that: The first image is captured by a pre-installed capturing device.
9. The method for detecting defects of greige fabric according to claim 1, characterized in that: The default path is an S-shaped path to detect all detection areas.
