电子学报2011，Vol.39Issue(5)：1007-1012,6.
基于标记分水岭和区域合并的彩色图像分割
Color Image Segmentation Based on Marked-Watershed and Region-Merger
摘要
Abstract
A color image segmentation algorithm combined marker-based watershed and region merger was proposed in this paper to deal with over-segmentation. Firstly,it extracted minima-marker adaprtively according to the information of local minima of gradient, and watershed the marked gradient image to get the pre-segmentation result. Then, it modified region distance according to real sense of region-similarity of human-vision, and defined an integration distance measurerment considering color distance,color difference and edge information, which would lead the pre-segmentation regions to merge to a final segmentation result. The experimental results indicate that the proposed algorithm can well suppress the over-segmentation and obtain a satisfactory result, which owns a lower Local Consistency Error and are more accordant to the human-vision segmentation.关键词
彩色图像分割/分水岭/标记提取/扩展最小变换/区域合并Key words
color image segmentation/watershed/marker-extraction/H-minima transfonnation/region merger分类
信息技术与安全科学引用本文复制引用
余旺盛,侯志强,宋建军..基于标记分水岭和区域合并的彩色图像分割[J].电子学报,2011,39(5):1007-1012,6.基金项目
国家自然科学基金(No.60805015) （No.60805015）
