Differential Evolution Optimization of 3D Topological Active Volumes
The Topological Active Volumes is an active model focused on 3D segmentation tasks. It provides information about the surfaces and the inside of the detected objects in the scene. The segmentation process turns into a minimization task of the energy functions which control the model deformation. We used Differential Evolution as an alternative evolutionary method that minimizes the decisions of the designer with respect to other evolutionary methods such as genetic algorithms. Moreover, we hybridized Differential Evolution with a greedy search to integrate the advantages of global and local searches at the same time that the segmentation speed is improved. Moreover, we included in the local search the possibility of topological changes to perform a better adjustment in complex surfaces.
KeywordsDeformable contours Genetic algorithms Differential evolution Image segmentation
Unable to display preview. Download preview PDF.
- 1.Tsumiyama, K.S.Y., Yamamoto, K.: Active net: Active net model for region extraction. IPSJ SIG notes 89(96), 1–8 (1989)Google Scholar
- 3.Barreira, N., Penedo, M.G.: Topological Active Volumes. EURASIP Journal on Applied Signal Processing 13(1), 1937–1947 (2005)Google Scholar
- 4.Ballerini, L.: Medical image segmentation using genetic snakes. In: Proceedings of SPIE: Application and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation II, vol. 3812, pp. 13–23 (1999)Google Scholar
- 5.Séguier, R., Cladel, N.: Genetic snakes: Application on lipreading. In: International Conference on Artificial Neural Networks and Genetic Algorithms (2003)Google Scholar
- 7.Bro-Nielsen, M.: Active nets and cubes. Technical Report 13, IMM, Technical University of Denmark (1994)Google Scholar
- 8.Novo, J., Barreira, N., Santos, J., Penedo, M.G.: Topological active volumes optimization with genetic approaches. In: XII Conference of the Spanish Association for the Artificial Intelligence, vol. 2, pp. 41–50 (2007)Google Scholar