1 July 2008 Segmenting foreground from similarly colored background
Author Affiliations +
Optical Engineering, 47(7), 077002 (2008). doi:10.1117/1.2955819
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
Xiang Zhang, Jie Yang, Zhi Liu, Xiangyang Wang, "Segmenting foreground from similarly colored background," Optical Engineering 47(7), 077002 (1 July 2008). http://dx.doi.org/10.1117/1.2955819

Statistical modeling

Image segmentation

Performance modeling

Optical engineering

Statistical analysis

Data modeling

Detection and tracking algorithms


The JWST/NIRSpec instrument performance simulator
Proceedings of SPIE (July 09 2008)
Multitarget tracking system using texture
Proceedings of SPIE (January 10 1997)
Robust anatomy detection from CT topograms
Proceedings of SPIE (February 27 2009)

Back to Top