纹理图像中重复纹理元素提取方法-OpenRepositoryofNational.PDF

ISSN 1673-9418 CODEN JKYTA8 E-mail: fcst@ Journal of Frontiers of Computer Science and Technology 1673-9418/2000/00(00)-0000-00 Tel: +86-10 doi: 10.3778/j.issn.1673-9418. 纹理图像中重复纹理元素提取方法 杨弄影, 李峰, 桂彦+ 长沙理工大学 计算机与通信工程学院，湖南 长沙 410114 Repeated Texture Elements Extraction from Texture Images YANG Nongying, LI Feng, GUI Yan + School of Computer Communication Engineering, Changsha University of Science Technology, Changsha, 410114, China +Corresponding author: E-mail: guiyan122@163.com YANG Nongying, LI Feng, GUI Yan. Repeated Texture Elements Extraction from Texture Images. Journal of Frontiers of Computer Science and Technology, 2015, 0(0): 1-000. Abstract: This paper presents an interactive element extraction method for texture image, which is able to simulta- neously cut out the repeated texture elements with much less user interaction. Firstly, texture image can be seg- mented into individual and connected sub-patches by using Mean Shift algorithm, and their connectivity can be con- structed by using Delaunay triangulation. Secondly, we redefine a robust measurement distance by considering color information and texture feature, which precisely captures all repeated texture elements with similar appearance. Fi- nally, we further modify the optimization model in order to achieve the best texture extraction. The proposed meth- od gets a great better extraction result for the texture image that has foreground and background with similar color, and improves the speed of image segmentation significantly. Key words: repeated texture elements; texture feature; similarity measurement; graphcut model 摘 要: 本文提出了一种交互式纹理图像中纹理元素提取算法，该算法能够在用户提供少量交互的情况下较 好地实现纹理图像中的重复纹理元素的同时提取。算法首先采用颜色聚类将纹理图像分割成独立且连通的子 块区域，并构建图像子块区域之间的连通关系；然后通过结合颜色