|
|
|
| Localized Graph-cuts Based Multiphase Active Contour Model for Image Segmentation |
| Kong Ding-ke Wang Guo-zhao |
| Institute of Computer Graphics and Image Processing, Department of Mathematics, Zhejiang University, Hangzhou 310027, China |
|
|
|
|
Abstract Geometric active contour is used as a powerful tool to address image segmentation problems. Recently, a new region-based active contour model based on pairwise similarity between pixels, i.e., Graph Portioning Active Contours (GPAC) is presented, and well adapted to segment images with intensity homogeneity. However, it only takes spectral similarity as the cost function between vertices, and can not obtain satisfactory segmentation results for low contrast images with weak boundaries. In order to overcoming this limitation of GPAC model, a novel localized graph-cuts based multiphase active contours model using geodesic kernel based cost function is proposed. Experimental results of natural images verify that the model is efficient and accurate.
|
|
Received: 25 August 2009
|
|
|
|
Corresponding Authors:
Kong Ding-ke
E-mail: dinckong@gmail.com
|
|
|
|
|
|
|
2010, Vol. 32 
