New improvement to range image segmentation algorithm

In this paper we presents a novel effective edge-based image segmentation algorithm for range images. It provides edge strength measures that have a straightforward geometric interpretation and supports a classification of edge points into several subtypes. We consider analysis of geometric properties of edge points as the key point to solve the problem of image segmentation. Experiments were performed in a popular range image database and the results were compared to three other traditional range image segmentation algorithms, demonstrating that it could achieve more edge information of the object and overcome the shortcoming of non-connected boundaries to a certain extent.
range image image segmentation segmentation algorithm
FAN Jianying ZHOU Yang WU Yan WANG Changjin WU Ying JIA Jia
Key Laboratory of Measurement-Control Technology & Instrument Harbin University of Science & Technology, Province of Heilongjiang College of Measurement-Control Technology & Communication Engineering, Harbin University of Science & Technology, Harbin 1500
国际会议
北京
英文
2007-08-05(万方平台首次上网日期,不代表论文的发表时间)