Classification of yarn interlacement pattern in fabrics using least square support vector machines

Abstract

The purpose of this paper is to suggest an effective and reliable tool that can read through fabric images in the quest of deciphering yarn interlacement patterns by means of Least-Square Support Vector Machines (LS-SVM). A LS-SVM based binary pattern recognition system is formulated for identifying two modes of yarn interlacements viz., warp over weft or warp under weft and accuracy of the classifier was assessed by k-fold cross validation techniques. A comparative study establishes that LS-SVM shows better result than the standard SVM while classifying yarn interlacement patterns in fabrics. The proposed method has the potential to classify yarn interlacement patterns with possibility of extending it to design- decoding of diverse fabrics.