Segmentation for Fabric Weave Pattern Using Empirical Mode Decomposition Based Histogram

Abstract

This paper is focused on the segmentation of the fabric weave patterns for the urgent requirement of fabric imitative design and redesign.The weave patterns related to the fabric yarn are determined by a new technology,which is called bidimensional mode decomposition based method. The proposed method first iteratively decompose the underlying fabric image into a number of intrinsic mode functions (IMFs). The first order IMF is applied to to calculate histogram and fabric weave pattern segmentation results are obtained by integrating corresponding threshold decision strategies such as double maxima algorithm or Otsu algorithm . In comparison with the original image-only based histogram segmentation method ,the presented method have a high precision. Simulation results show that BEMD based method is a promising approach for the segmentation of fabric weave pattern. DOI: http://dx.doi.org/10.11591/telkomnika.v11i4.2374