BP neural network in classification of fabric defect based on particle swarm optimization

• Published in: 2008 International Conference on Wavelet Analysis and Pattern Recognition Vol. 1; pp. 216 - 220
• Main Authors: Su-Yi Liu, Le-Duo Zhang, Qian Wang, Jing-Jing Liu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.08.2008
• Subjects: Artificial neural networks; BP neural network; chain code; classification; Classification algorithms; Fabric defects; Fabrics; Image edge detection; Particle swarm optimization; Petroleum; Sobel Operator; Training
• ISBN: 9781424422388; 1424422388
• ISSN: 2158-5695
• DOI: 10.1109/ICWAPR.2008.4635779

Particle swarm optimization was applied in BP neural network training. It reasonably confirms threshold and connection weight of neural network, and improves capability of solving problems in realities. Meanwhile, PSO-BP neural network is applied into classification of fabric defect. The method of orthogonal wavelet transform was used to decompose monolayer from fabric image. And the sub-images of horizontal and vertical direction are extracted to represent respectively the textures of fabric in warp and weft. Compared classification of PSO-BP neural network to classification of BP neural network, it is shown that PSO-BP neural network achieves favorable results.