EFFICIENT IMAGE SEGMENTATION FOR SEMANTIC OBJECT GENERATION

作     者：Chen Xiaotang Yu Yinglin (Dept. of Comm. & Info. Eng., South China Univ. of Technology, Guangzhou 510640) Chen Xiaotang Yu Yinglin (Dept. of Comm. & Info. Eng., South China Univ. of Technology, Guangzhou 510640)

作者机构：Dept. of Comm. & Info. Eng. South China Univ. of Technology Guangzhou 510640 

出 版 物：《Journal of Electronics(China)》 (电子科学学刊（英文版）)

年 卷 期：2002年第19卷第4期

页      面：420-425页

学科分类：0810[工学-信息与通信工程] 08[工学] 081001[工学-通信与信息系统] 

基　　金：Supported by Guangdong Natural Science Foundation(No.011628) 

主　　题：Image segmentation Semantic object Contour-preserving noise filtering Quasi-flat regions labeling Region merging 

摘      要：This letter presents an efficient and simple image segmentation method for semantic object spatial segmentation. First, the image is filtered using contour-preserving filters. Then it is quasi-flat labeled. The small regions near the contour are classified as uncertain regions and are eliminated by region growing and merging. Further region merging is used to reduce the region number. The simulation results show its efficiency and simplicity. It can preserve the semantic object shape while emphasize on the perceptual complex part of the object. So it conforms to the human visual perception very well.