A method and system for detecting fabric surface defects based on machine vision

Abstract

The present invention relates to the technical field of fabric surface defect detection, and specifically discloses a machine vision-based fabric surface defect detection method and system. The method comprises analyzing the pilling characteristics of a fabric surface image to obtain the ratio of the number of abnormal areas, judging the fabric quality, and generating an unqualified signal and a suspected qualified signal; analyzing the abnormal marking results of the fabric surface areas to obtain a pilling trend value, determining the impact of fabric surface pilling on fabric surface defects, and generating a strong impact signal; and extracting all fabric samples with unqualified signals and strong impact signals within a test time, recording them as unqualified traceability samples and strong impact traceability samples, respectively. The present invention optimizes the fabric inspection time by determining the fabric optimal inspection time and the inspection time of fabric production equipment, and analyzing the fabric production inspection time. This not only improves the pertinence and efficiency of the inspection, but also helps to promptly discover and resolve problems in the production process, thereby ensuring the quality of the fabric.

Description

Technical Field

[0001] The present invention relates to the technical field of cloth surface defect detection, and in particular to a cloth surface defect detection method and system based on machine vision. Background Art

[0002] With the rapid development of computer technology and artificial intelligence technology, machine vision technology has gradually become an important tool in the field of automated inspection and quality control. Machine vision technology can recognize, analyze and process images and videos by simulating human visual functions. The textile industry is an important part of the national economy, providing people with clothing, curtains, bedding and other items that are indispensable in daily life. In order to ensure the quality of textiles, textile manufacturers need to conduct strict quality inspections on the surface of the fabrics.

[0003] However, existing methods for detecting surface defects in fabrics often rely on manual visual inspection after fabric production is completed. However, this method is inefficient and the detection results are easily affected by human factors. This may result in the omission of defective fabrics, affecting the quality of fabric shipments.

[0004] To this end, we propose a cloth surface defect detection method and system based on machine vision. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for detecting cloth surface defects based on machine vision to solve the technical problems in the above background.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A method for detecting surface defects of cloth based on machine vision, comprising:

[0008] Analyze the pilling characteristics of the fabric surface image, obtain the number ratio of abnormal areas, and determine whether the fabric generates a failed signal or a suspected qualified signal;

[0009] Based on the suspected qualified signal, the abnormal marking results of the fabric surface area are analyzed to obtain the pilling trend value, determine the impact of fabric surface pilling on fabric surface defects, and generate a strong impact signal;

[0010] Extract all fabric samples with unqualified signals and strong impact signals within the test time, record them as unqualified traceability samples and strong impact traceability samples respectively, obtain the production time, analyze them, and output the regular data of the traceability samples;

[0011] The time required for adjacent inspections of fabric production equipment for unqualified and highly impacted conditions is analyzed to determine the inspection time.

[0012] As a further technical solution of the present invention, the process of determining whether the fabric generates an unqualified signal or a suspected qualified signal is as follows:

[0013] Identify whether pilling exists in all areas of the fabric surface image. If so, the corresponding area is recorded as an abnormal area. If not, the corresponding area is recorded as a normal area.

[0014] Calculate the ratio of the number of abnormal areas. If the ratio is less than or equal to the threshold of the number of abnormal areas, generate a suspected qualified signal. If the ratio is greater than the threshold of the number of abnormal areas, generate an unqualified signal.

[0015] As a further technical solution of the present invention: the process of obtaining the pilling tendency value is as follows:

[0016] Analyze the pilling area of the abnormal area and conduct pilling test on the normal area to obtain the pilling performance value of the abnormal area and the increase coefficient of the normal area;

[0017] The pilling tendency value is obtained by comparing the pilling characteristic value of the abnormal area with the increase / change coefficient of the normal area.

[0018] As a further technical solution of the present invention, the process of obtaining the pilling performance value of the abnormal area is as follows:

[0019] Extract the pilling area of the abnormal area. If it is greater than or equal to the standard value of the pilling area, mark the corresponding pilling as prominent pilling.

[0020] Obtaining the average pilling area of all prominent pills, and calculating the deviation ratio from the standard value of the pilling area to obtain the prominent pilling area deviation ratio;

[0021] The ratio of the number of prominent pilling and the deviation ratio of the prominent pilling area are summed to obtain the pilling performance value of the abnormal area.

[0022] As a further technical solution of the present invention: the process of obtaining the mutation coefficient of the normal area is:

[0023] The pilling test is performed on the normal area to obtain the pilling grade parameters, which are then compared with the standard pilling grade parameters to obtain the increase coefficient of the normal area.

[0024] As a further technical solution of the present invention: the process of outputting regular data of traceable samples includes:

[0025] Obtain the production time of the unqualified traceability sample and the production time of the strong-impact traceability sample, and divide them into the production time intervals of the unqualified traceability sample and the production time intervals of the strong-impact traceability sample;

[0026] Subtract the production time intervals of adjacent unqualified traceable samples to obtain the interval intervals of unqualified traceable samples, calculate the variance of the intervals of all unqualified traceable samples, and obtain the time variance value of the strongly influential traceable samples;

[0027] If it is greater than the time variance threshold of the unqualified traceability sample, an unqualified non-periodic signal is generated;

[0028] If it is less than or equal to the time variance threshold of the unqualified traceability sample, an unqualified periodic signal is generated.

[0029] As a further technical solution of the present invention, the process of outputting regular data of traceable samples further includes:

[0030] Subtract the production time intervals of adjacent strong-impact traceability samples to obtain the interval interval of the strong-impact traceability samples, calculate the variance of the interval intervals of all strong-impact traceability samples, and obtain the time variance value of the strong-impact traceability samples;

[0031] If it is greater than the time variance threshold of the strong impact tracing sample, a strong impact aperiodic signal is generated;

[0032] If it is less than or equal to the time variance threshold of the strong impact tracing sample, a strong impact periodic signal is generated.

[0033] As a further technical solution of the present invention: the process of obtaining the time of adjacent detections is:

[0034] Get the mean of the intervals of all unqualified traceable samples, which is the time between adjacent tests for unqualified cases during the production of the fabric;

[0035] The mean of the intervals of all strong-impact traceability samples is obtained, which is the time of adjacent inspections for strong-impact situations during the production of the fabric.

[0036] As a further technical solution of the present invention: the process of obtaining the detection time of the cloth production equipment is:

[0037] If the intervals of all strongly impacted traceability samples are before the intervals of unqualified traceability samples in terms of time, and the intervals of both are smaller than the preset intervals, the start time of the adjacent tests of the strongly impacted cases shall be recorded as the test time of the fabric production equipment.

[0038] A cloth surface defect detection system based on machine vision, the system comprising:

[0039] Preliminary detection module: Analyzes the pilling characteristics of the fabric surface image, obtains the number and ratio of abnormal areas, and determines whether the fabric generates a failed signal or a suspected qualified signal;

[0040] In-depth detection module: Based on the suspected qualified signal, it analyzes the abnormal marking results of the fabric surface area, obtains the pilling trend value, determines the impact of fabric surface pilling on fabric surface defects, and generates a strong impact signal;

[0041] Periodicity judgment module: extracts all fabric samples with unqualified signals and strong impact signals within the test time, records them as unqualified traceability samples and strong impact traceability samples respectively, obtains production time, performs analysis, and outputs regular data of traceability samples;

[0042] Optimal inspection time determination module: Analyzes the time of adjacent inspections for unqualified conditions and strong impact conditions during fabric production to obtain the inspection time of fabric production equipment.

[0043] Beneficial effects of the present invention:

[0044] (1) The present invention analyzes the pilling characteristics of the surface image of the fabric to obtain the proportion of the number of abnormal areas, judge the quality of the fabric, and generate unqualified signals and suspected qualified signals; based on the suspected qualified signals, the abnormal marking results of the fabric surface area are analyzed to obtain the pilling trend value, determine the impact of the fabric surface pilling on the fabric surface defects, and generate a strong impact signal. The present invention realizes the detection and evaluation of fabric surface pilling by combining image processing technology and data analysis methods, and improves the detection accuracy.

[0045] (2) The present invention extracts all fabric samples with unqualified signals and strong impact signals within the test time, records them as unqualified traceability samples and strong impact traceability samples respectively, obtains the production time, performs analysis, and outputs regular data of the traceability samples; analyzes the time of adjacent inspections for unqualified conditions and strong impact conditions during the production of the fabric, and obtains the inspection time of the fabric production equipment; the present invention determines the fabric preferred inspection time and the inspection time of the fabric production equipment, which is convenient for adjusting the inspection time according to the quality change of the fabric produced by the current equipment, effectively reducing the current frequency of fabric inspection, and using the start time of adjacent inspections of strong impact conditions to determine the inspection time of the fabric equipment during production, so that the fabric equipment can be inspected and repaired in advance at this time, which can effectively improve the quality of subsequent fabric production. Therefore, the analysis of the fabric production inspection time optimizes the fabric inspection time, which not only improves the pertinence and efficiency of the inspection, but also helps to timely discover and solve problems in the production process, thereby ensuring the quality of the fabric. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The present invention will be further described below with reference to the accompanying drawings.

[0047] Figure 1 This is a flowchart of a method for detecting surface defects of fabrics based on machine vision according to an embodiment of the present invention;

[0048] Figure 2 This is a system block diagram of a machine vision-based cloth surface defect detection system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0050] Example 1

[0051] See also Figure 1 As shown, the method for detecting surface defects of cloth based on machine vision according to an embodiment of the present invention comprises the following steps:

[0052] Step 1: Analyze the pilling characteristics of the fabric surface image, obtain the proportion of abnormal areas, judge the fabric quality, and generate unqualified signals and suspected qualified signals;

[0053] In some embodiments, a test time is set, and all currently tested fabric samples are analyzed, wherein the test time corresponds to the production time of the fabric samples and is arranged in ascending order: a surface image of the fabric is acquired using a scanner, the surface image of the fabric is divided into a plurality of regions in a grid form, and pilling features of the fabric surface are extracted using an edge detection algorithm, specifically: the fabric surface image is subjected to image preprocessing, an edge detection operator (such as a Canny operator, a Sobel operator, a Robert operator, or a Prewitt operator) is used to identify pilling regions by detecting edge information in the image, and morphological processing (such as dilation, erosion, opening operation, and closing operation) is performed to extract pilling features of the pilling regions;

[0054] Identify whether pilling exists on the surface of the fabric. If so, obtain the area corresponding to the pilling distribution location and mark it as an abnormal area. Mark the area without pilling on the surface of the fabric as a normal area. Count the number of abnormal areas and compare it with the total number of divided areas to obtain the ratio of the number of abnormal areas.

[0055] Compare the percentage of abnormal regions with the threshold value of the percentage of abnormal regions:

[0056] If the percentage of abnormal areas is greater than the threshold, it means that pilling is more distributed on the surface of the fabric, and a failure signal is generated;

[0057] If the percentage of abnormal areas is less than or equal to the threshold, it means that pilling is less distributed on the fabric surface, and a suspected qualified signal is generated;

[0058] For example, the surface image of the fabric is divided into 50*50 rectangular areas. If 80 abnormal areas with pilling are identified in the surface image of the fabric, the proportion of abnormal areas in the surface image of the fabric is 80 / (50*50)=0.032.

[0059] Through the above analysis, the abnormal area can be determined, and then the location of the pilling defect can be determined during the process of fabric surface defect detection. The degree of the defect can be determined based on the proportion of the number of abnormal areas. Therefore, step 1 of the present invention can achieve the location of the defect and the determination of the degree of the defect.

[0060] Step 2: Based on the suspected qualified signal, analyze the abnormal marking results of the fabric surface area to obtain the pilling trend value, determine the impact of fabric surface pilling on fabric surface defects, and generate a strong impact signal;

[0061] Compare the pilling area in the abnormal area when a suspected pass signal is generated with the pilling area standard value:

[0062] If the pilling area is greater than or equal to the standard value of the pilling area, the corresponding pilling will be marked as prominent pilling;

[0063] If the pilling area is smaller than the standard value of pilling area, the corresponding pilling will be marked as non-protruding pilling;

[0064] It should be noted that the standard value of pilling area is set by those skilled in the art based on fabric design requirements;

[0065] Count the number of prominent pilling and the number of non-prominent pilling, and sum them to get the total number of pilling. Ratio the number of prominent pilling to the total number of pilling to get the percentage of prominent pilling.

[0066] Obtaining the pilling area of the prominent pilling, subtracting the subtracted area from the standard pilling area value to obtain a pilling area deviation, summing and averaging all the pilling area deviations to obtain a pilling area deviation mean, and then comparing the pilling area deviation mean with the standard pilling area value to obtain a prominent pilling area deviation ratio;

[0067] The percentage of prominent pilling and the deviation ratio of prominent pilling area are summed to obtain the pilling performance value of the abnormal area.

[0068] It should be noted that the pilling performance value is obtained by processing the percentage of prominent pilling and the deviation ratio of prominent pilling area. The percentage of prominent pilling reflects the number of pilling areas with a large area in the abnormal area when generating a suspected qualified signal. The deviation ratio of prominent pilling area reflects the degree of deviation between the prominent pilling area and the standard value of the pilling area in the abnormal area when generating a suspected qualified signal. The larger the deviation, the more serious the pilling trend in the abnormal area, indicating that the surface defect of the fabric is greater.

[0069] Get a normal area on the surface of the fabric and conduct a pilling test;

[0070] Specifically, the pilling test time is preset, the fabric is loaded on the sample holder, and the fabric sample is subjected to circular motion under a certain pressure to first cause pilling with nylon, and then with standard fabric. After a certain number of times, the sample is compared with the original fabric or a standard sample in a rating box to obtain the pilling grade parameters. The pilling grade parameters are then compared with the standard pilling grade parameters to obtain the increase coefficient of the normal range.

[0071] It should be noted that the standard pilling grade parameters are set by those skilled in the art based on actual needs. The larger the pilling grade parameter, the worse the pilling effect and the better the anti-pilling effect. The maximum is 5 and the minimum is 1. Grade 5 indicates mild pilling and grade 1 indicates severe pilling. When the result is between two adjacent grades, 0.5 is taken. The smaller the pilling grade parameter, the smaller the variation coefficient and the more severe the pilling tendency.

[0072] The pilling tendency value is obtained by performing a ratio process on the pilling characteristic value of the abnormal area and the increase / change coefficient of the normal area;

[0073] Compare the pilling tendency value to the pilling tendency threshold:

[0074] If the pilling tendency value is greater than or equal to the pilling tendency threshold, it means that pilling has a greater impact on the surface defects of the fabric and a strong impact signal is generated;

[0075] If the pilling tendency value is less than the pilling tendency threshold, it means that pilling has little impact on the surface defects of the fabric, and a weak impact signal is generated;

[0076] It should be noted that the unqualified signals, strong influence signals, and weak influence signals obtained from the fabric sample testing reflect the degree of defects in the fabric samples. Specifically, the fabric sample with an unqualified signal has the highest degree of defect, the fabric sample with a strong influence signal has the second highest degree of defect, and the fabric sample with a weak influence signal has the lowest degree of defect. Furthermore, the degree of impact on the fabric sample's subsequent use is opposite: the fabric sample with an unqualified signal has the worst performance, the fabric sample with a strong influence signal has the second highest performance, and the fabric sample with a weak influence signal has very little performance.

[0077] The technical solution of the embodiment of the present invention is mainly as follows: analyzing the pilling characteristics of the surface image of the fabric, obtaining the proportion of the number of abnormal areas, judging the quality of the fabric, and generating an unqualified signal and a suspected qualified signal; based on the suspected qualified signal, analyzing the abnormal marking results of the fabric surface area, obtaining a pilling trend value, determining the impact of fabric surface pilling on fabric surface defects, and generating a strong impact signal. By combining image processing technology and data analysis methods, the present invention realizes the detection and evaluation of fabric surface pilling, thereby improving detection accuracy.

[0078] Example 2

[0079] Based on Example 1, please refer to Figure 1 As shown, the method for detecting surface defects of cloth based on machine vision according to an embodiment of the present invention comprises the following steps:

[0080] Step 3: Extract all fabric samples with unqualified signals and strong impact signals during the test time, record them as unqualified traceability samples and strong impact traceability samples respectively, obtain the production time, analyze them, and output the regular data of the traceability samples;

[0081] In some embodiments, all fabric samples with unqualified signals and strong impact signals within the test time are obtained, and are marked as unqualified traceability samples and strong impact traceability samples according to the different signals. The production time of the unqualified traceability samples and the production time of the strong impact traceability samples are obtained through a timer;

[0082] According to time continuity (time continuity refers to fabric samples with the same signal appearing at adjacent times), the production time of unqualified traceable samples and the production time of traceable samples with strong influence are divided respectively, and the production time intervals of multiple unqualified traceable samples and the production time intervals of traceable samples with strong influence are obtained;

[0083] Analyze the unqualified traceability samples, make a difference between the production time intervals of adjacent unqualified traceability samples, calculate the interval intervals of the unqualified traceability samples, then integrate the interval intervals of all unqualified traceability samples in order of production time from smallest to largest, construct the interval interval data group of unqualified traceability samples, calculate the variance of the data group, and obtain the time variance value of the unqualified traceability samples;

[0084] Compare the time variance value of the unqualified traceability sample with the time variance threshold of the unqualified traceability sample:

[0085] If the time variance value of the unqualified traceability sample is greater than the time variance threshold of the unqualified traceability sample, an unqualified non-periodic signal is generated;

[0086] If the time variance value of the unqualified traceable sample is less than or equal to the time variance threshold of the unqualified traceable sample, an unqualified periodic signal is generated;

[0087] Similarly, for the strong impact traceability samples, the production time intervals of adjacent strong impact traceability samples are subtracted to calculate the interval intervals of the strong impact traceability samples. Then, the interval intervals of all strong impact traceability samples are integrated in order of production time from small to large to construct the interval interval data group of the strong impact traceability samples. The variance of the data group is calculated to obtain the time variance value of the strong impact traceability samples.

[0088] Compare the time variance value of the strongly impacted tracing sample with the time variance threshold of the strongly impacted tracing sample:

[0089] If the time variance value of the strong impact tracing sample is greater than the time variance threshold of the strong impact tracing sample, a strong impact aperiodic signal is generated;

[0090] If the time variance value of the strong impact tracing sample is less than or equal to the time variance threshold of the strong impact tracing sample, a strong impact periodic signal is generated;

[0091] It should be noted that when a periodic signal is obtained, it can effectively indicate that the equipment used in fabric processing may have intermittent periodic faults during the time period of the traced sample. For example, periodic abnormalities may occur in the bearings, belts, engines, or any other components in the production line of the fabric processing equipment, thereby affecting the quality of the fabric products. Therefore, step 4 of the present invention not only determines the regularity of the fabric product quality, but also deduces the nature of the fault in the fabric processing equipment based on the generated signal.

[0092] Step 4: Analyze the time of adjacent inspections for unqualified conditions and strong impact conditions during fabric production to obtain the inspection time of fabric production equipment;

[0093] In some embodiments, if the periodic signal of the unqualified sample and the periodic signal of the strongly affected sample are generated simultaneously, the optimal detection time of the fabric is analyzed, and the specific process is as follows:

[0094] First, the intervals of unqualified traceable samples are obtained, and the average time of the intervals of all unqualified traceable samples is calculated to obtain the average interval of the unqualified traceable samples. Based on the average interval of the unqualified traceable samples, the time between adjacent tests for unqualified conditions during the production of the fabric is determined; and based on the number of intervals between the unqualified traceable samples, the frequency of testing for unqualified conditions during the production of the fabric is determined;

[0095] Then, the intervals of the strong-impact traceability samples are obtained, and the intervals of all the strong-impact traceability samples are averaged to obtain the average interval of the strong-impact traceability samples. Based on the average interval of the strong-impact traceability samples, the time of adjacent tests for the strong-impact situation during the production of the fabric is determined; and based on the number of intervals that appear in the intervals of the strong-impact traceability samples, the frequency of testing for the strong-impact situation during the production of the fabric is determined;

[0096] Furthermore, the intervals of the unqualified traceability samples are compared with the intervals of the strongly impacted traceability samples in ascending order of time. If the intervals of all the strongly impacted traceability samples are located before the intervals of the unqualified traceability samples in terms of time, and the intervals of both are smaller than the preset intervals, then based on the change in the degree of fabric defects during the production time, the fabric defects will increase with the extension of time within the time interval, and the start time of the adjacent tests of the strongly impacted situation will be recorded as the test time of the fabric production equipment.

[0097] Therefore, by determining the optimal inspection time for fabrics and the inspection time for fabric production equipment, it is convenient to make adaptability adjustments to the inspection time for the fabrics produced by the current equipment according to their quality changes, effectively reducing the current frequency of fabric inspections, and utilizing the start time of adjacent inspections with strong influence to determine the inspection time during fabric equipment production, so that the fabric equipment can be inspected and repaired in advance at this time, which can effectively improve the quality of subsequent fabric production.

[0098] The technical solution of the embodiment of the present invention mainly includes: extracting all fabric samples with unqualified signals and strong influence signals within the test time, recording them as unqualified traceable samples and strong influence traceable samples respectively, obtaining the production time, analyzing them, and outputting regular data of the traceable samples; analyzing the time of adjacent inspections for unqualified conditions and strong influence conditions during fabric production to obtain the inspection time of the fabric production equipment; the present invention determines the optimal fabric inspection time and the inspection time of the fabric production equipment, which facilitates the adaptability adjustment of the inspection time according to the quality changes of the fabric produced by the current equipment, effectively reducing the current frequency of fabric inspections, and using the start time of adjacent inspections for strong influence conditions to determine the inspection time during fabric production. At this time, the fabric equipment can be overhauled in advance, which can effectively improve the quality of subsequent fabric production. Therefore, the analysis of the fabric production inspection time optimizes the fabric inspection time, not only improving the pertinence and efficiency of inspections, but also helping to promptly discover and resolve problems in the production process, thereby ensuring fabric quality.

[0099] Example 3

[0100] Based on Example 1 and Example 2, please refer to Figure 2 As shown, a cloth surface defect detection system based on machine vision according to an embodiment of the present invention includes:

[0101] Preliminary detection module: Analyzes the pilling characteristics of the surface image of the fabric, obtains the proportion of abnormal areas, determines the fabric's quality, and generates unqualified signals and suspected qualified signals;

[0102] In-depth detection module: Based on the suspected qualified signal, it analyzes the abnormal marking results of the fabric surface area, obtains the pilling trend value, determines the impact of fabric surface pilling on fabric surface defects, and generates a strong impact signal;

[0103] Periodicity judgment module: extracts all fabric samples with unqualified signals and strong impact signals within the test time, records them as unqualified traceability samples and strong impact traceability samples respectively, obtains production time, performs analysis, and outputs regular data of traceability samples;

[0104] Optimal inspection time determination module: Analyzes the time of adjacent inspections for unqualified conditions and strong impact conditions during fabric production to obtain the inspection time of fabric production equipment.

[0105] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for detecting surface defects of cloth based on machine vision, characterized in that: include: Analyze the pilling characteristics of the surface image of the fabric and identify whether pilling exists in all areas of the surface image of the fabric. If pilling exists, the corresponding area is recorded as an abnormal area; if not, the corresponding area is recorded as a normal area; If the proportion of abnormal areas is greater than the threshold of the proportion of abnormal areas, a failure signal is generated; If the proportion of abnormal areas is less than or equal to the threshold of the proportion of abnormal areas, a suspected qualified signal is generated; Based on the suspected qualified signal, the abnormal marking results of the fabric surface area are analyzed to obtain the pilling trend value, determine the impact of fabric surface pilling on fabric surface defects, and generate a strong impact signal; The process of obtaining the pilling trend value is as follows: Extract the pilling area of the abnormal area. If it is greater than or equal to the standard value of the pilling area, mark the corresponding pilling as prominent pilling. The ratio of the number of prominent pilling to the total number of pilling is calculated to obtain the percentage of prominent pilling. Subtracting the pilling area in the prominent pilling from the standard pilling area value to obtain the pilling area deviation, averaging all the pilling area deviations, and then performing a ratio processing with the standard pilling area value to obtain the prominent pilling area deviation ratio; The percentage of prominent pilling and the deviation ratio of prominent pilling area are summed to obtain the pilling performance value of the abnormal area. Perform pilling test on normal area to obtain pilling grade parameters, and compare them with standard pilling grade parameters to obtain the increase coefficient of normal area; The pilling performance value of the abnormal area is compared with the increase coefficient of the normal area to obtain the pilling trend value; If the pilling tendency value is greater than or equal to the pilling tendency threshold, it means that pilling has a greater impact on the surface defects of the fabric and a strong impact signal is generated; Extract all fabric samples with unqualified signals and strong impact signals within the test time, record them as unqualified traceability samples and strong impact traceability samples respectively, obtain the production time, analyze them, and output the regular data of the traceability samples; The process of obtaining the regular data of the traceable samples is as follows: Obtain the production time of unqualified traceability samples and highly impacted traceability samples, and divide the production time intervals of unqualified traceability samples and highly impacted traceability samples; Obtain the interval intervals of the production time intervals of adjacent unqualified traceable samples, calculate the variance of the interval intervals of all unqualified traceable samples, and obtain the time variance value of the unqualified traceable samples; Obtain the interval intervals of the production time intervals of adjacent strong-impact traceability samples, calculate the variance of the interval intervals of all strong-impact traceability samples, and obtain the time variance value of the strong-impact traceability samples; According to the time variance value of unqualified traceability samples and the time variance value of strong-impact traceability samples, the production periodicity of unqualified traceability samples and strong-impact traceability samples are identified respectively; The time required for adjacent inspections of fabric production equipment for unqualified and highly impacted conditions is analyzed to determine the inspection time.

2. The method for detecting surface defects of cloth based on machine vision according to claim 1, characterized in that: The process of outputting regular data of traceable samples includes: Obtain the production time of the unqualified traceability sample and the production time of the strong-impact traceability sample, and divide them into the production time intervals of the unqualified traceability sample and the production time intervals of the strong-impact traceability sample; Subtract the production time intervals of adjacent unqualified traceable samples to obtain the interval intervals of unqualified traceable samples, calculate the variance of the intervals of all unqualified traceable samples, and obtain the time variance value of the strongly influential traceable samples; If it is greater than the time variance threshold of the unqualified traceability sample, an unqualified non-periodic signal is generated; If it is less than or equal to the time variance threshold of the unqualified traceability sample, an unqualified periodic signal is generated.

3. The method for detecting surface defects of fabrics based on machine vision according to claim 1, characterized in that: The process of outputting regular data of traceable samples also includes: Subtract the production time intervals of adjacent strong-impact traceability samples to obtain the interval interval of the strong-impact traceability samples, calculate the variance of the interval intervals of all strong-impact traceability samples, and obtain the time variance value of the strong-impact traceability samples; If it is greater than the time variance threshold of the strong impact tracing sample, a strong impact aperiodic signal is generated; If it is less than or equal to the time variance threshold of the strong impact tracing sample, a strong impact periodic signal is generated.

4. The method for detecting surface defects of fabrics based on machine vision according to claim 1, characterized in that: The process of obtaining the time of adjacent detections is: Get the mean of the intervals of all unqualified traceable samples, which is the time between adjacent tests for unqualified cases during the production of the fabric; The mean of the intervals of all strong-impact traceability samples is obtained, which is the time of adjacent inspections for strong-impact situations during the production of the fabric.

5. The method for detecting surface defects of fabrics based on machine vision according to claim 4, characterized in that: The process of obtaining the detection time of fabric production equipment is as follows: If the intervals of all strongly impacted traceability samples are before the intervals of unqualified traceability samples in terms of time, and the intervals of both are smaller than the preset intervals, the start time of the adjacent tests of the strongly impacted cases shall be recorded as the test time of the fabric production equipment.

6. A cloth surface defect detection system based on machine vision, characterized in that: The system is used to execute the method according to any one of claims 1 to 5, and the system comprises: Preliminary detection module: Analyzes the pilling characteristics of the fabric surface image, obtains the number and ratio of abnormal areas, and determines whether the fabric generates a failed signal or a suspected qualified signal; In-depth detection module: Based on the suspected qualified signal, it analyzes the abnormal marking results of the fabric surface area, obtains the pilling trend value, determines the impact of fabric surface pilling on fabric surface defects, and generates a strong impact signal; Periodicity judgment module: extracts all fabric samples with unqualified signals and strong impact signals within the test time, records them as unqualified traceability samples and strong impact traceability samples respectively, obtains production time, performs analysis, and outputs regular data of traceability samples; Optimal inspection time determination module: Analyzes the time of adjacent inspections for unqualified conditions and strong impact conditions during fabric production to obtain the inspection time of fabric production equipment.

Images