Color image segmentation

Yining Deng, B. S. Manjunath and Hyundoo Shin*
Department of Electrical and Computer Engineering
University of California, Santa Barbara, CA 93106-9560
*Samsung Electronics Inc.
{deng, manj, hdshin} [at]


In this work, a new approach to fully automatic color image segmentation, called JSEG, is presented. First, col-ors in the image are quantized to several representing classes that can be used to differentiate regions in the image. Then, image pixel colors are replaced by their cor-responding color class labels, thus forming a class-map of the image. A criterion for "good" segmentation using this class-map is proposed. Applying the criterion to local win-dows in the class-map results in the "J-image", in which high and low values correspond to possible region bound-aries and region centers, respectively. A region growing method is then used to segment the image based on the multi-scale J-images. Experiments show that JSEG pro-vides good segmentation results on a variety of images.
[PDF] [BibTex]
Y. Deng, B. S.Manjunath and H.Shin,
IEEE Computer Society Conference on Computer Vision and Pattern Recognition CVPR'99, vol. 2, pp. 446-51, Fort Collins, CO, Jun. 1999.
Node ID: 285 , DB ID: 81 , VRLID: 68 , Lab: VRL , Target: Proceedings
Subject: [Detection on Images and Videos] « Look up more