Quality inspection system applied to fiber cloth

Abstract

The invention innovatively provides a fiber cloth quality inspection system which is characterized by comprising a fan, a database and an image acquisition module, and the image acquisition module is used for acquiring an image of a fabric surface as an image to be analyzed; the flaw recognition module is used for acquiring the to-be-analyzed image in the image acquisition module, judging whether flaws exist on the surface of the fabric or not through a semantic segmentation model, if yes, generating flaw signals and performing form analysis on the flaws to obtain flaw forms, and the flaw forms comprise a stain form and a foreign matter form; the foreign matter type analysis module is used for acquiring to-be-analyzed images of the fabric under different fan wind speeds when the flaw forms are foreign matter forms, analyzing according to the outline Dongtai in the to-be-analyzed images to obtain the swing amplitude of foreign matters, and indexing the foreign matter types in a database according to the swing amplitude; and the flaw marking module is used for acquiring the flaw signal in the flaw recognition module and marking the flaw position and the foreign matter form in the to-be-analyzed image.

Description

Technical Field

[0001] The present invention relates to the technical field of quality inspection systems, and more particularly to a quality inspection system for fiber cloth. Background Art

[0002] After the fiber fabric is produced, the product needs to be inspected for quality and qualified products are selected for packaging. Currently, the size, quality and shape of the product are measured manually using tools such as rulers and scales to check whether the product meets the production standards and issue a test report. The process is cumbersome and inefficient, and it is not convenient for large-scale product testing. In addition, during the testing process, there may be defects on the surface of the fabric. Manual inspection of fabric defects takes a lot of time and may result in missed inspections, which is too inefficient. Summary of the invention

[0003] In view of the deficiencies in the prior art, an object of the present invention is to provide a fiber cloth quality inspection system for overcoming the above-mentioned defects in the prior art.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A fiber cloth quality inspection system, comprising a fan, and

[0006] A database, wherein fabric information is preset in the database, and the fabric information includes fabric patterns;

[0007] An image acquisition module, wherein the image acquisition module is used to acquire an image of the surface of the fabric as an image to be analyzed;

[0008] A defect recognition module, which is used to obtain the image to be analyzed in the image acquisition module, determine whether there is a defect on the surface of the fabric through a semantic segmentation model, and if so, generate a defect signal and perform morphological analysis on the defect to obtain the defect morphology, which includes stain morphology and foreign body morphology;

[0009] A foreign body type analysis module, when the defect form is a foreign body form, obtains the image to be analyzed of the fabric at different wind speeds of the fan, obtains the swing amplitude of the foreign body according to the contour analysis in the image to be analyzed, and indexes the foreign body type in the database based on the swing amplitude;

[0010] The defect marking module is used to obtain the defect signal in the defect recognition module, mark the defect position and foreign body shape in the image to be analyzed, and generate a detection report based on the defect marking information.

[0011] Preferably, a defect position marking unit is provided in the defect recognition module, and the defect position marking unit is used to obtain the image to be analyzed, and obtain a fabric area map by cutting it through a preset semantic segmentation model, and perform binarization image processing on the fabric area map to obtain a binarized image, and compare the binarized image with a binary image of a fabric pattern in a database to obtain a defect area, and extract the contour line of the defect area through a contour algorithm.

[0012] Preferably, the angle recognition unit is also provided in the defect recognition module, and the angle recognition unit is used to obtain the image to be analyzed at different angles, and obtain the outer contour line of the defect area in the image to be analyzed, calculate the fit of the outer contour line with the fabric in the binary image, and judge whether the defect is in the form of a stain or a foreign body according to the fit.

[0013] Preferably, a comparison and judgment unit is further provided in the defect recognition module, and the comparison and judgment unit is used to obtain the defect area and determine the edge points and LBP values ​​corresponding to the defect area. A standard defect area is preset, and the similarity value between the defect area and the standard defect area is determined by comparing the edge points and LBP values ​​of the defect area with those of the standard defect area, and the defect morphology of the defect area is judged according to the similarity value.

[0014] Preferably, the comparison and judgment unit further includes an edge judgment subunit and an LBP judgment subunit.

[0015] The edge judgment subunit is used to obtain the slope of the line corresponding to the adjacent corner points of the edge corresponding to the standard defect area, and determine the first similarity between the defect area and the pre-standard defect area according to the slope of the line corresponding to the adjacent corner points of the edge corresponding to each defect area and the slope of the line corresponding to the adjacent corner points of the edge corresponding to the standard defect area;

[0016] The LBP judgment unit is used to obtain the LBP value of each corner point of the edge corresponding to the standard defect area, and determine the second similarity between the defect area and the standard defect area according to the LBP value of each corner point of the edge corresponding to the defect area and the LBP value of each corner point of the edge corresponding to the standard defect area;

[0017] The comparison and judgment unit is used to obtain a first similarity and a second similarity, and obtain a similarity value according to the first similarity and the second similarity.

[0018] Preferably, a quality inspection unit is also included, and the quality inspection unit is used to obtain fabric parameters such as fabric quality and thickness.

[0019] Preferably, an initial inspection module is also included, which is used to obtain the image to be analyzed, and obtain a fabric area map by cutting it through a preset semantic segmentation model, and perform stroke processing on the fabric area map, and obtain the fabric contour line, and compare the fabric contour line with the fabric information in the database and generate the contour line similarity. If the contour line similarity is higher than the threshold, the initial inspection is qualified, and if the contour line similarity is less than the threshold, the initial inspection is unqualified.

[0020] Preferably, the types of foreign matter include adhesions, burrs, etc.

[0021] The beneficial effects of the present invention are as follows: it realizes the full automation from image acquisition to defect recognition, marking and report generation, thereby improving the detection efficiency; it adopts advanced semantic segmentation models and image processing technology to ensure the accuracy and reliability of defect recognition; it can automatically analyze the types of foreign matter and provide strong support for production improvement; the modules of the system are flexibly designed and easy to integrate with other production equipment or management systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is the overall structural diagram of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] It should be noted that when a component is referred to as being "fixed to" another component, it may be directly on the other component or there may also be a component centered. When a component is considered to be "connected to" another component, it may be directly connected to the other component or there may also be a component centered. When a component is considered to be "set on" another component, it may be directly set on the other component or there may also be a component centered. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0026] The embodiments of the present invention are further described in detail below with reference to the accompanying drawings:

[0027] A fiber cloth quality inspection system includes a fan, which can provide different wind speed conditions during the inspection process to observe and analyze the dynamic characteristics of foreign matter on the cloth surface, provide basic data for subsequent foreign matter type analysis, and

[0028] A database, in which fabric information is preset, includes various preset information required by the fabric pattern storage system, including fabric information (such as fabric pattern, quality parameters, etc.), defect sample data, foreign body types and their characteristic data, etc.;

[0029] An image acquisition module, the image acquisition module is used to obtain an image of the fabric surface as an image to be analyzed, and to capture the image of the fabric surface in real time as an image to be analyzed;

[0030] The defect recognition module is used to obtain the image to be analyzed in the image acquisition module, and determine whether there are defects on the fabric surface through the semantic segmentation model. If so, a defect signal is generated, and the defect is morphologically analyzed to obtain the defect morphology, which includes stain morphology and foreign body morphology. The defect morphology receives the image to be analyzed transmitted by the image acquisition module, accurately segments the fabric area through the preset semantic segmentation model, and identifies the defects on the fabric surface. According to the characteristics of the defect area, the defect is morphologically analyzed and distinguished into stain morphology and foreign body morphology. The types of foreign bodies include removable foreign bodies such as adhesions and burrs, and the stain morphology is color pollution on the fabric surface during the dyeing and weaving process.

[0031] A defect position marking unit is set in the defect recognition module. The defect position marking unit is used to obtain the image to be analyzed, and obtain the fabric area map by cutting it through a preset semantic segmentation model, and perform binary image processing on the fabric area map to obtain a binary image, and compare the binary image with the binary image of the fabric pattern in the database to obtain the defect area, and extract the contour line of the defect area through the contour algorithm; after identifying the defect, the unit further accurately marks the defect position. It first performs binary processing on the fabric area map, and then compares it with the binary image of the fabric pattern in the database, determines the defect area through difference analysis, and finally uses the contour algorithm to extract the contour line of the defect area to provide accurate position information for subsequent processing.

[0032] Foreign body type analysis module, when the defect form is a foreign body form, obtain the image of the fabric to be analyzed at different fan speeds, analyze the contour in the image to be analyzed to obtain the swing amplitude of the foreign body, and index the foreign body type in the database based on the swing amplitude; when the defect form is determined to be a foreign body form, the module starts working. It first obtains the image of the fabric to be analyzed at different fan speeds to observe the dynamic behavior of the foreign body; by analyzing the contour changes of the foreign body in the image, the swing amplitude of the foreign body is calculated. Then, using the swing amplitude as an index, the corresponding foreign body type information is searched in the database; during the detection process, when there are foreign bodies such as burrs on the surface of the fabric, the burrs will swing under the action of the fan and the shape will change. The type of foreign body and the connection relationship between the foreign body and the fabric can be determined by the swing amplitude of the foreign body.

[0033] The defect marking module is used to obtain the defect signal in the defect recognition module, mark the defect position and the foreign body shape in the image to be analyzed, and generate a detection report based on the defect marking information; receive the defect signal sent by the defect recognition module, accurately mark the defect position and the foreign body shape in the image to be analyzed according to the position information and morphological analysis results provided by the defect position marking unit, and generate a detailed detection report based on the marking results, including information such as the defect position, shape, type and possible causes.

[0034] The defect recognition module is also provided with an angle recognition unit, which is used to obtain the image to be analyzed at different angles, obtain the outer contour line of the defect area in the image to be analyzed, calculate the fit of the outer contour line with the fabric in the binary image, and judge the defect as a stain or a foreign body according to the fit; receive fabric photos at different angles, extract the outer contour line of the defect area, compare the extracted contour line with the shape and texture characteristics of the fabric itself, and calculate the fit between the contour line and the fabric. The fit is used to describe the degree of matching between the contour line and the edge or texture of the fabric; according to the calculated fit value, the angle recognition unit will judge the shape of the defect; if the fit is high, that is, the contour line fits closely with the edge or texture of the fabric, then the defect is more likely to be a stain; on the contrary, if the fit is low, there is a large deviation between the contour line and the edge or texture of the fabric, then the defect is more likely to be a foreign body; according to the angle recognition unit, the defect shape can be quickly determined.

[0035] A comparison and judgment unit is also provided in the defect recognition module. The comparison and judgment unit is used to obtain the defect area and determine the edge points and LBP values ​​corresponding to the defect area. A standard defect area is preset. By comparing the edge points and LBP values ​​of the defect area with those of the standard defect area, the similarity value between the defect area and the standard defect area is determined, and the defect shape of the defect area is judged according to the similarity value; by calculating the similarity between the defect area and the standard defect area, the unit can automatically judge the shape of the defect.

[0036] The comparison judgment unit also includes an edge judgment subunit and an LBP judgment subunit.

[0037] The edge judgment subunit is used to obtain the slope of the connection line corresponding to the adjacent corner points of the edge corresponding to the standard defect area, and determine the first similarity between the defect area and the pre-standard defect area according to the slope of the connection line corresponding to the adjacent corner points of the edge corresponding to each defect area and the slope of the connection line corresponding to the adjacent corner points of the edge corresponding to the standard defect area; the edge judgment subunit is mainly responsible for obtaining and analyzing the edge features of the defect area and the standard defect area. By identifying the adjacent corner points on the edge and calculating the slope of the connection line between these corner points, the subunit can quantify the similarity in edge shape between the defect area and the standard defect area; obtain the edge point data of the defect area and the standard defect area, sort the edge points so as to extract the adjacent corner points in sequence, calculate the slope of the connection line of each pair of adjacent corner points to form a slope sequence, compare the slope sequence of the defect area and the standard defect area, and calculate the first similarity between the two.

[0038] The LBP judgment unit is used to obtain the LBP value of each corner point of the edge corresponding to the standard defect area, and determine the second similarity between the defect area and the standard defect area according to the LBP value of each corner point of the edge corresponding to the defect area and the LBP value of each corner point of the edge corresponding to the standard defect area; by calculating the LBP value of each corner point on the edge of the defect area and the standard defect area, and comparing these values ​​to evaluate the similarity between the two in texture features, a certain number of corner points on the edge of the defect area and the standard defect area are selected as sample points, the LBP algorithm is applied to each sample point, its LBP value is calculated, and the LBP values ​​of each sample point of the defect area and the standard defect area are compared to calculate the second similarity between the two;

[0039] The comparison and judgment unit is used to obtain the first similarity and the second similarity, and obtain a similarity value according to the first similarity and the second similarity. According to the preset weight allocation strategy, it can be adjusted according to the actual application scenario, and the first similarity and the second similarity are weighted and summed to obtain the final similarity value. According to the comparison result of the similarity value and the preset threshold value, it is judged whether the defect shape of the defect area matches the standard defect area.

[0040] It also includes a quality inspection unit, which is used to obtain fabric parameters such as fabric quality and thickness; use sensors (such as thickness sensors, quality sensors, etc.) to perform non-contact or contact measurement on the fabric to collect fabric parameters such as thickness and quality.

[0041] It also includes an initial inspection module, which is used to obtain the image to be analyzed, and obtain the fabric area map by cutting it through a preset semantic segmentation model, and perform outlining processing on the fabric area map, and obtain the fabric contour line, and compare the fabric contour line with the fabric information in the database and generate the contour line similarity. If the contour line similarity is higher than the threshold, the initial inspection is qualified, and if the contour line similarity is less than the threshold, the initial inspection is unqualified; the initial inspection module is the front link of the quality inspection system, and is used for preliminary processing and screening of the input image to be analyzed. Through the semantic segmentation model and image processing technology, the initial inspection module can automatically cut out the fabric area map and extract the fabric contour line, compare it with the standard fabric information in the database, and quickly determine the initial inspection qualification of the fabric; receive the fabric image to be analyzed as the input data for the initial inspection, use the preset semantic segmentation model to process the image, automatically identify and cut out the fabric area map, and perform border processing on the fabric area map to clearly define the fabric contour line; compare the extracted fabric contour line with the standard fabric contour line stored in the database, and calculate the contour line similarity; determine whether the fabric is qualified for the initial inspection based on the comparison result of the contour line similarity and the preset threshold. If the similarity is higher than the threshold, the initial inspection is qualified; if the similarity is lower than the threshold, the initial inspection is unqualified.

[0042] The above are only preferred embodiments of the present invention. The protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A fiber cloth quality inspection system, characterized in that: Including fans, and A database, wherein fabric information is preset in the database, and the fabric information includes fabric patterns; An image acquisition module, wherein the image acquisition module is used to acquire an image of the surface of the fabric as an image to be analyzed; A defect recognition module, which is used to obtain the image to be analyzed in the image acquisition module, determine whether there is a defect on the surface of the fabric through a semantic segmentation model, and if so, generate a defect signal and perform morphological analysis on the defect to obtain the defect morphology, which includes stain morphology and foreign body morphology; A foreign body type analysis module, when the defect form is a foreign body form, obtains the image to be analyzed of the fabric at different wind speeds of the fan, obtains the swing amplitude of the foreign body according to the contour analysis in the image to be analyzed, and indexes the foreign body type in the database based on the swing amplitude; The defect marking module is used to obtain the defect signal in the defect recognition module, mark the defect position and foreign body shape in the image to be analyzed, and generate a detection report based on the defect marking information.

2. The fiber cloth quality inspection system according to claim 1, characterized in that: A defect position marking unit is provided in the defect recognition module, and the defect position marking unit is used to obtain the image to be analyzed, and obtain a fabric area map by cutting it through a preset semantic segmentation model, perform binarization image processing on the fabric area map to obtain a binarized image, compare the binarized image with a binary image of a fabric pattern in a database to obtain a defect area, and extract the contour line of the defect area through a contour algorithm.

3. The fiber cloth quality inspection system according to claim 2, characterized in that: The angle recognition unit is also provided in the defect recognition module, and the angle recognition unit is used to obtain the image to be analyzed at different angles, and obtain the outer contour line of the defect area in the image to be analyzed, calculate the fit of the outer contour line with the fabric in the binary image, and judge whether the defect is in the form of a stain or a foreign body according to the fit.

4. The fiber cloth quality inspection system according to claim 1, characterized in that: The defect recognition module is also provided with a comparison and judgment unit, which is used to obtain the defect area and determine the edge points and LBP values ​​corresponding to the defect area. A standard defect area is preset, and the similarity value between the defect area and the standard defect area is determined by comparing the edge points and LBP values ​​of the defect area with those of the standard defect area, and the defect morphology of the defect area is judged according to the similarity value.

5. The fiber cloth quality inspection system according to claim 4, characterized in that: The comparison and judgment unit further includes an edge judgment subunit and an LBP judgment subunit. The edge judgment subunit is used to obtain the slope of the line corresponding to the adjacent corner points of the edge corresponding to the standard defect area, and determine the first similarity between the defect area and the pre-standard defect area according to the slope of the line corresponding to the adjacent corner points of the edge corresponding to each defect area and the slope of the line corresponding to the adjacent corner points of the edge corresponding to the standard defect area; The LBP judgment unit is used to obtain the LBP value of each corner point of the edge corresponding to the standard defect area, and determine the second similarity between the defect area and the standard defect area according to the LBP value of each corner point of the edge corresponding to the defect area and the LBP value of each corner point of the edge corresponding to the standard defect area; The comparison and judgment unit is used to obtain a first similarity and a second similarity, and obtain a similarity value according to the first similarity and the second similarity.

6. The fiber cloth quality inspection system according to claim 1, characterized in that: It also includes a quality inspection unit, which is used to obtain fabric parameters such as fabric quality and thickness.

7. The fiber cloth quality inspection system according to claim 1, characterized in that: It also includes an initial inspection module, which is used to obtain the image to be analyzed, and obtain a fabric area map by cutting it through a preset semantic segmentation model, and perform outlining processing on the fabric area map, and obtain the fabric contour line, and compare the fabric contour line with the fabric information in the database and generate the contour line similarity. If the contour line similarity is higher than the threshold, the initial inspection is qualified, and if the contour line similarity is less than the threshold, the initial inspection is unqualified.

8. The fiber cloth quality inspection system according to claim 1, characterized in that: The types of foreign matter include adhesions, burrs, etc.

Images