DocumentCode :
3154838
Title :
Procrustes — based shape prior for parametric active contours
Author :
Kamandar, Mehdi ; Seyedin, Seyed Alireza
Author_Institution :
Ferdowsi Univ. of Mashhad, Mashhad
fYear :
2007
fDate :
28-29 Dec. 2007
Firstpage :
135
Lastpage :
140
Abstract :
A novel method of parametric active contours with geometric shape prior is presented in this paper. The main idea of the method consists in minimizing an energy function that includes additional information on a shape reference called a prototype. Prior shape knowledge is introduced through a complete family of Euclidean invariants, computed from the similarity between shape of evolving contour and the prototype. This similarity is measured by full Procrustes distance. This extra knowledge enhances the model robustness to noise, occlusion and complex background. We use genetic algorithm to minimize energy function of this new type of snake that we call it Procrustes snake. The variational formulation of the proposed approach is described in details. We obtain promising results with synthetic and real images which show the power of our method for segmentation tasks.
Keywords :
genetic algorithms; image segmentation; Euclidean invariants; Procrustes; Procrustes snake; genetic algorithm; geometric shape; parametric active contours; prior shape knowledge; segmentation tasks; variational formulation; Active contours; Background noise; Bayesian methods; Genetic algorithms; Image segmentation; Minimization methods; Noise robustness; Noise shaping; Prototypes; Shape measurement; Genetic algorithm; Parametric active contours; Procrustes shape analysis; Shape prior; Snake;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Vision, 2007. ICMV 2007. International Conference on
Conference_Location :
Islamabad
Print_ISBN :
978-1-4244-1624-0
Electronic_ISBN :
978-1-4244-1625-7
Type :
conf
DOI :
10.1109/ICMV.2007.4469287
Filename :
4469287
Link To Document :
بازگشت