Water Flow Based Complex Feature Extraction
A new general framework for shape extraction is presented, based on the paradigm of water flow. The mechanism embodies the fluidity of water and hence can detect complex shapes. A new snake-like force functional combining edge-based and region-based forces produces capability for both range and accuracy. Properties analogous to surface tension and adhesion are also applied so that the smoothness of the evolving contour and the ability to flow into narrow branches can be controlled. The method has been assessed on synthetic and natural images, and shows encouraging detection performance and ability to handle noise, consistent with properties included in its formulation.
KeywordsActive Contour Topological Change Image Force Impulsive Noise Gradient Vector Flow
Unable to display preview. Download preview PDF.
- 2.Cohen, L.D., Cohen, I.: Finite element methods for active models and balloons for 2-D and 3-D images. IEEE Trans. PAMI 15, 1131–1147 (1993)Google Scholar
- 6.McInerney, T., Terzopoulos, D.: Topologically adaptive snakes. In: Int’l. Conf. Computer Vision 1995, pp. 840–845 (1995)Google Scholar
- 8.Malladi, R., et al.: Shape modeling with front propagation: A level set approach. IEEE Trans. PAMI 17, 158–174Google Scholar
- 9.Adams, R., Bischof, L.: Seeded region growing. IEEE Trans. PAMI 16(6), 641–647Google Scholar
- 10.Zhu, S.C., Yuille, A.: Region competition: unifying snakes, region growing, and Bayes/MDL for multi-band image segmentation. IEEE Trans. PAMI 18(9), 884–900Google Scholar
- 11.Kiran, V., Bora, P.K.: Watersnake: integrating the watershed and the active contour algorithms. In: TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region, October 2003, vol. 2, pp. 868–871 (2003)Google Scholar