Share Email Print
cover

Proceedings Paper

Multi-region level set image segmentation based on image energy separation model
Author(s): Xue-Min Yin; Hong Yan; Yu-Hua Yao; Jian-Ping Guo; Chong-Fa Zhong; Zhe Zhang; Yi Wei
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper presents a multi-region level set image segmentation method based on image energy separation model. The image feature is extracted by using the image energy decomposition method. We represent the regions by the level set functions with constraint. The coupled Partial Differential Equations (PDE) related to the minimization of the functional are considered through a dynamical scheme. A modified region competition factor is adopted to speed up the cure evolution functions, it also guarantees no vacuum and non-overlapping between the neighbor regions. Several experiments are conducted on both synthetic images and natural image. The results illustrate that the proposed multiregion segmentation method is fast and less sensitive to the initializations.

Paper Details

Date Published: 19 July 2013
PDF: 7 pages
Proc. SPIE 8878, Fifth International Conference on Digital Image Processing (ICDIP 2013), 887825 (19 July 2013); doi: 10.1117/12.2030891
Show Author Affiliations
Xue-Min Yin, Astronaut Research and Training Ctr. of China (China)
Hong Yan, Astronaut Research and Training Ctr. of China (China)
Yu-Hua Yao, Astronaut Research and Training Ctr. of China (China)
Jian-Ping Guo, Astronaut Research and Training Ctr. of China (China)
Chong-Fa Zhong, Astronaut Research and Training Ctr. of China (China)
Zhe Zhang, Astronaut Research and Training Ctr. of China (China)
Yi Wei, Astronaut Research and Training Ctr. of China (China)


Published in SPIE Proceedings Vol. 8878:
Fifth International Conference on Digital Image Processing (ICDIP 2013)
Yulin Wang; Xie Yi, Editor(s)

© SPIE. Terms of Use
Back to Top