Supervised and Unsupervised Neural Network Methods applied to Textile Quality Control based on Improved Wavelet Feature Extraction Techniques

This paper aims at investigating novel solutions to the problem of textile defect detection from images, that can find applications in building robust quality control vision based systems in textile production. The proposed solutions focus on detecting defects from the textural properties of their corresponding wavelet transformed images. More specifically a novel methodology is investigated for discriminating defects in textile images by applying supervised and unsupervised neural classification techniques, employing multilayer perceptrons (MLP) trained with the on-line backpropagation algorithm and Kohonen’s Self-Organizing Feature Maps (SOFM) respectively. These parallel techniques are applied to innovative wavelet based feature vectors. These vectors are extracted from the wavelet transformed original images using the cooccurrence matrices framework and SVD analysis. The results of the proposed methodology are illustrated in defective textile images where the defective areas are recognized with about 98.5% accuracy.