Defect detection in fabrics using back propagation neural networks

Abstract

Defect detection in Fabrics plays an significant role in automatic defect detection system in textile industries. Identification of fabric fault mainly include three parts: The first, preprocessing with Frequency domain Butterworth Low pass Filter and Histogram Equalization. The second, texture features extraction of fabric with Gray Level Co-occurrence Matrix (GLCM).The GLCM characterizes the distribution of co-occurring pixel values in an image to be at a given offset, and then the statistical texture features are obtained from this GLCM. Third, the fault is identified using Back Propagation Neural Network with different combinations of GLCM features as an input.