Pattern cloth flaw online visual inspection method

Abstract

The present invention provides a loom pattern cloth flaw online visual inspection method, which comprises: accurately calculating a texture primitive period, constructing a flaw-free primitive image offset sequence, and extracting pattern cloth characteristics so as to achieve real-time monitoring and flaw generation shutdown during a loom pattern cloth weaving process. According to the present invention, the texture primitive period extraction scheme is optimized, and the extreme value weight analysis is adopted to remove the interferential extreme value point so as to increase the period extraction accuracy; offline training on the standard flaw-free image is matched, the bi-layer classification mechanism in the online detection process is established, and detection accuracy is substantially improved while the real-time property is ensured; and requirements of high real-time property and high accuracy of the loom pattern cloth during the online detection process can be completely met.

Description

technical field [0001] The invention relates to the field of on-line detection of looms in the weaving process of patterned cloth by using machine vision, specifically refers to a kind of loom that is applied to industrial sites and has high real-time requirements and stops in time when defects occur in the process of weaving complex patterned cloths image processing method. Background technique [0002] With the improvement of people's requirements for cloth quality, cloth inspection is becoming more and more important. Traditional manual inspection technology is costly, slow, and human eyes are prone to fatigue after long-term work, resulting in false inspections, and it is easy to cause accidents where the loom is still working due to defects. The decline in cloth quality has also brought greater pressure on factories that strictly control production costs and improve product quality in the modern economic market. In the weaving process, the loom can intelligently detect...

AI Technical Summary

Problems solved by technology

The reason is that, on the one hand, it is difficult to detect this kind of cloth. Cloths with small textures can eliminate the influence of small textures through frequency domain methods such as Gabor or wavelet transform, and then separate the defective areas by setting thresholds, while it is difficult to eliminate texture information on cloths with large texture patterns. On the one hand, the pattern cloth is diverse and the transformation is complex, and it is difficult to design a specific pattern detection scheme to form a unified detection scheme that can be adapted to other patterns

Images