Title :
An active contour model for selective segmentation
Author_Institution :
Inst. of Appl. Phys. & Comput. Math., Beijing, China
Abstract :
In this paper, we develop a new active contour model for image selective segmentation. The model adopts cascade anisotropic diffusion preprocessing and a selective term in level set function. Cascade anisotropic diffusion filtering is powerful and flexible to enhance image for various segmentation tasks. The selective term in level set function can evolve a single curve to capture a selective segmentation region which we are interested in. This is useful for intentional segmentation tasks. We can also realize the multi-region segmentation by varying selecting term conditions. Furthermore, we saliently speed the process of the new algorithm by using AOS scheme in cascade anisotropic diffusion filtering and discarding mean curvature motion in level set function. We illustrate the performance of our segmentation method on images generated by different modalities.
Keywords :
filtering theory; image segmentation; active contour model; additive operator splitting; cascade anisotropic diffusion filtering; cascade anisotropic diffusion preprocessing; image selective segmentation; level set function; mean curvature motion; multi-region segmentation; Active contours; Anisotropic magnetoresistance; Data analysis; Filtering algorithms; Image edge detection; Image generation; Image segmentation; Level set; Nonlinear equations; Physics computing;
Conference_Titel :
Computer Graphics, Imaging and Vision: New Trends, 2005. International Conference on
Print_ISBN :
0-7695-2392-7
DOI :
10.1109/CGIV.2005.15