Application of wavelet transform in characterization of fabric texture

摘要

In this paper we present an opto-vision system for image processing of fabric texture using symlet wavelet transform to locate different types of defects in fabric and find the repeat texture of fabric without any priori information The system is also capable of characterizing the texture of fabric not having obvious repeat pattern. The proposed methodology is able to measure the warp, weft diameter and spacing per unit length per yarn and percentage of their coefficient of variation (C. V%) The two dimensional wavelet transform of the image can distinguish texture feature along with yarn spacing in the weave. The information obtained from the image processing is considered to be significant for purposes of textile design to obtain a basic knowledge as to the visual information contained therein.