Share Email Print
cover

Optical Engineering

Segmenting foreground from similarly colored background
Author(s): Xiang Zhang; Jie Yang; Zhi Liu; Xiangyang Wang
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Color similarity between foreground and background causes many foreground segmentation algorithms to fail. In this paper, a new algorithm is presented to segment foreground from similarly colored background. First, model precision and model recall are presented to quantify the model accuracy of various foreground models. Model accuracy tests show that the more accurate the foreground model is, the more accurate the segmentation is. Second, a new foreground model, which is more accurate than the general foreground model, is the developed by blending in different historical segmentations. Finally, the foreground is segmented using the new foreground model combined with a likelihood modification technique. Experimental results on typical sequences show that many foreground pixels misclassified by previous algorithms can be correctly classified by the new algorithm

Paper Details

Date Published: 1 July 2008
PDF: 11 pages
Opt. Eng. 47(7) 077002 doi: 10.1117/1.2955819
Published in: Optical Engineering Volume 47, Issue 7
Show Author Affiliations
Xiang Zhang, Shanghai Jiaotong Univ. (China)
Jie Yang, Shanghai Jiaotong Univ. (China)
Zhi Liu, Shanghai Univ. (China)
Xiangyang Wang, Shanghai Univ. (China)


© SPIE. Terms of Use
Back to Top