Cloth defect marking method and system based on machine vision

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a cloth defect marking method and system based on machine vision. Obtaining a surface image including the texture of the cloth, obtaining a gray level image corresponding to the surface image, and obtaining a frequency domain image including edge information according to the gray level image; further obtaining the periodic direction and the texture direction of the texture in the gray level image; according to a gray level co-occurrence matrix corresponding to the period direction and the texture direction; selecting each group of corresponding pixel point pairs in the gray level co-occurrence matrix when the occurrence frequency is greater than a preset threshold value as a texture unit; and obtaining a symbiotic run matrix corresponding to each texture unit in the period direction and the texture direction, obtaining an abnormal texture unit according to the gray level co-occurrence matrix and the symbiotic run matrix, obtaining an interruption pixel point pair according to the abnormal texture unit, and obtaining a defect pixel point according to the interruption pixel point pair. Errors caused by noise points of the image are avoided, and efficiency and accuracy of cloth defect detection are improved.

Description

Technical field [0001] The present invention relates to the field of artificial intelligence technology, specifically to a cloth defect labeling method and system based on machine vision. Background [0002] Textile industry is the pillar industry of China's national economy, textile industry and steel, automobiles, ships, petrochemicals, light chemicals, non-ferrous metals, equipment manufacturing, electronic information and logistics industry and other industries, is China's main industrial composition. In the textile production process, cloth surface defects will directly affect the grade of cloth, is the key factor affecting the quality of cloth, and the price of different grades of cloth is also very different, so cloth defect detection is particularly important in textile quality control. [0003] Most of the existing cloth inspection is completed by manual inspection, relying on the experience and proficiency of the staff, but the inspection of cloth defects is a very tedi...

AI Technical Summary

Problems solved by technology

[0003] Most of the existing cloth detection is done by manual inspection, which depends on the experience and proficiency of the staff, but the inspection of cloth defects is a very tedious work, so false detection or missed detection often occurs, which greatly consumes Labor force, and detection efficiency and accuracy are low

Images