GLCM TEXTURE BASED FRACTAL METHOD FOR EVALUATING FABRIC SURFACE ROUGHNESS

The aim of our research is to be able to determine the tactile feeling of fabrics, sold over the web, by using inexpensive technologies. A Grey Level Co-occurrence Matrix (GLCM) texture based fractal method is proposed to objectively evaluate the surface roughness of fabric images. The fractal dimension, which has been proved as a descriptor of tactile surface roughness, is calculated from the texture features extracted from GLCMs. The proposed method has been implemented in Matlab and tested by using woven fabric images which are randomly chosen from clothes. Two types of the fractal dimension estimation methods: the box counting method and the power spectrum method are used for roughness evaluation. The power spectrum method is demonstrated to be more robust than the box counting method. The major results of our fabric roughness evaluation show that the GLCM can represent a meaningful descriptive basis of fabric textures and fractal dimension of the GLCM textures have the ability to evaluate the actual fabric surface roughness.