Graph Partitioning Active Contours (GPAC) for Image Segmentation

Baris Sumengen, B. S. Manjunath
Department of Electrical and Computer Engineering
University of California, Santa Barbara, CA
sumengen, manj [at]


In this paper we introduce new type of variational segmentation cost functions and associated active contour methods that are based on pairwise similarities or dissimilarities of the pixels. As a solution to a minimization problem, we introduce a new curve evolution framework, the graph partitioning active contours (GPAC). Using global features, our curve evolution is able to produce results close to the ideal minimization of such cost functions. New and efficient implementation techniques are also introduced in this paper. Our experiments show that GPAC solution is effective on natural images and computationally efficient. Experiments on gray scale, color, and texture images show promising segmentation results.
[PDF] [BibTex]
B. Sumengen and B. S. Manjunath,
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Apr. 2006.
Node ID: 410 , DB ID: 211 , VRLID: 150 , Lab: VRL , Target: Journal
Subject: [Detection on Images and Videos] « Look up more