Color Texture Segmentation for Clothing Based on Finite Prolate Spheroidal Sequences

Abstract

One of the most difficult tasks in computer-aided fashion design is to separate the clothing of interest on a model from backgrounds such that changes can be done on the clothing. These exist folds, shadows, diverse textures ets. on the clothing which make the segmentation work difficult. In this paper, a color texture segmentation method for clothing segmentation is proposed. Color quantization is first performed to reduce the number of colors and shandow/highlight effects on the image. The color texture features are then extracted based on the finite prolate spheroidal sequences (FPSS). By these features, a hierarchical coarse- to -fine segmentation method is used to separate the clothing from backgrounds. Finally, post-processing is applied to obtain a smooth clothing boundary. The experimental results achieved are satisfactory.