DocumentCode :
457132
Title :
A Geometric Active Contour Framework using Multi-Cue and Local Feature
Author :
Li, Zhenglong ; Liu, Qingshan ; Lu, Hanqing
Author_Institution :
Inst. of Autom., Chinese Acad. of Sci., Beijing
Volume :
2
fYear :
0
fDate :
0-0 0
Firstpage :
113
Lastpage :
116
Abstract :
There exist two key issues in the traditional geometric active contour (GAC): only single cue based driven force and edge leakage. In this paper, we propose two new GACs, i.e., multi-Cue based GAC (MC-GAC) and local-feature based GAC (LF-GAC), to deal with these two problems respectively. In MC-GAC, a multi-cue based force is generated by introducing the customized vector flow into the model. To utilize local feature information, LF-GAC is developed, in which local edge information is considered to produce continuous edge. Further, we unify these two GACs into a novel general GAC framework. Extensive experiments showed the advantages of the proposed method
Keywords :
computational geometry; edge detection; feature extraction; customized vector flow; edge information; edge leakage; geometric active contour framework; local feature information; multicue based force; multicue feature; Active contours; Automation; Bidirectional control; Computer vision; Equations; Laboratories; Level set; Motion estimation; Pattern recognition; Tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
Conference_Location :
Hong Kong
ISSN :
1051-4651
Print_ISBN :
0-7695-2521-0
Type :
conf
DOI :
10.1109/ICPR.2006.72
Filename :
1699160
Link To Document :
بازگشت