Evaluating Wrinkled Fabrics with Image Analysis and Neural Networks

Abstract

Gray scale image analysis is used to evaluate visual features of wrinkles in plain fabrics made from cotton, linen, rayon, wool. silk, and polyester. The angular second moment, contrast, correlation, and entropy extracted from the gray level co-occurrence matrix are measured as visual feature parameters. The fractal dimension is determined from fractal analysis of the relief of the curved surface of the gray level image. These image information parameters are useful for visual evaluations of wrinkled fabrics. In this study, a visual evaluation system using neural networks is discussed. A high performance neuron training algorithm with a Kalman filter is introduced to tune the network in order to maximize the accuracy of the visual evaluation system. The trained neural network model is successfully implemented to show the feasibility of neural network applications for objective visual evaluation of wrinkled fabrics.