期刊
COMPUTERS & GEOSCIENCES
卷 49, 期 -, 页码 238-247出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.cageo.2012.06.007
关键词
Variogram properties; Experimental semi-variogram and covariogram; Structural property and statistical property; Variance distance; Image segmentation
资金
- Changzhou Key Lab of Software Technology and Applications, China
Inspired by Krige' variogram and the multi-channel filtering theory for human vision information processing, this paper proposes a novel algorithm for segmenting the textures based on experimental semi-variogram function (ESVF), which can simultaneously describe structural property and statistical property of textures. The single variogram function value (SVFV) and the variance distance obtained by ESVF are used as texture feature description for segmenting textures. The feasibility and effectiveness of the proposed method are demonstrated by testing on some texture images. The computational complexity of the proposed approach depends neither on the number of the textures nor on the number of the gray levels, and only on the size of the image blocks. We have proved theoretically that the algorithm has the advantages of direction invariability and a higher sensitivity to different textures and can detect almost all kinds of the boundaries of the shape textures. Experimental results on the Brodatz texture databases show that the performance of this algorithm is superior to the traditional techniques such as texture spectrum, SIFT, kappa-mean method, and Gabor filters. The proposed approach is found to be robust, efficient, and satisfactory. Crown Copyright (C) 2012 Published by Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据