Fabric flaw detection method based on independent classification feature extraction
A type of feature and defect detection technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of low detection efficiency, single detection object, difficult production and other problems, so as to improve efficiency, realize accuracy and breadth, reduce effect of complexity
Pending Publication Date: 2022-01-11
杭州云图智检科技有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In view of the defects or deficiencies in the above-mentioned fabric defect detection process, the purpose of the present invention is to provide a fabric defect detection method based on independent classification feature extraction, to solve the above problems that are difficult to be truly applied to production due to the single defect detection object and low detection efficiency. practical problem
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0030] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0031] Such as figure 1 As shown, the present invention provides a fabric defect detection method based on independent classification feature extraction, including a preprocessing method and a modeling principle for building a model process, a principle for a chroma anomaly detection process, and a method for color block The method of extraction, the design of convex hull and embedding algorithms, and the method of fabric defect aggregation labeling;
[0032] Such as figure 2 As shown, it is a sample image of the defect type, which includes embedded type defect 1, chroma anomaly defect 2 and convex hull type defect 3, and these types of defects are also three types that often appear in discrete regular pattern fabrics; Among them, chromaticity abnormal defect 2 refers to a type in which the color of an area is judged as a defect because it does not exist i...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a fabric flaw detection method based on independent classification feature extraction, which is mainly used for flaw detection of a fabric containing discrete regular patterns or plain yarns at present, and comprises the following steps of: manually modeling a normal fabric to obtain a model containing color block type information, and then under a certain threshold value, according to the matching degree of fabric color blocks and a model, color blocks are divided, abnormal color blocks are marked, then corresponding image reprocessing is carried out on the divided color blocks, and corresponding flaws are extracted and marked by using a convex hull defect detection algorithm and an embedded defect detection algorithm respectively. Therefore, independent classification extraction of fabric flaws on characteristics of chromaticity, convex hulls, embedding and the like is realized. The fabric detection method comprises the steps of fabric model establishment, detection principle design and the like, and in combination with a multi-thread technology, independent classification of fabric flaws is rapidly extracted, so that the fabric detection method can be more conveniently and efficiently applied to the fabric flaw detection process.
Description
technical field [0001] The invention belongs to the field of computer vision image processing, and relates to a method for quickly extracting surface defects of textiles, in particular to a method for detecting fabric defects based on independent classification feature extraction. Background technique [0002] The textile industry is the pillar industry of our country's economy, and its development is closely related to our daily life. With the great development of internationalization, the export volume of my country's textiles is also increasing rapidly, but the problems brought about by it are gradually emerging in front of people. In the general environment of the textile industry, since machines with textile functions appeared very early, although this has liberated people's hands to a large extent, there is still a large amount of manual investment in the field of textile quality inspection, so How to improve the quality and production efficiency of textile products i...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06V10/44G06V10/56G06V10/75G06V10/762
CPCG06T7/0004G06T2207/30124G06F18/23
Inventor 沈人朱聪强焦阳博翰
Owner 杭州云图智检科技有限公司