Abstract:

Aim at the problem of low detection efficiency and fabric jittering due to high production rate, when texture fabric defects are automatically detected. A textured fabric defect detection was presented based on a windowed hop-step morphological algorithm. Firstly, window sugnebtatuib and preprocessing on images were carried out, and then the image textuer features of the textured fabric were analyzed. Secondly morphological operators were designed for corrosion operation. Finally, the defect size and location are determined by connected domain analysis. Experimental simulation and practical application show that this algorithm can solve the problem of the images of uneven light and shade caused by the cloth trembling effectively, and the algorithm can detect the presence of detect in the fabric texture including warp and weft defects, holes, stains, thread defects and other defects. The detection algorithm has high stability and reliability so that can meet the actual production demand. The detection speed is superior to the speed of FFT feature point algorithm and traditional morphological algorithm. The real-time detection speed is more than 80m/min, and the size of the flaw detection accuracy is 0.1mm.

Key words: textured fabric, morphological, hop-step algorithm, defec detection