East Asian J. Appl. Math., 2 (2012), pp. 150-169.
Published online: 2018-02
Cited by
- BibTex
- RIS
- TXT
Most image segmentation techniques efficiently segment images with prominent edges, but are less efficient for some images with low frequencies and overlapping regions of homogeneous intensities. A recently proposed selective segmentation model often works well, but not for such challenging images. In this paper, we introduce a new model using the coefficient of variation as a fidelity term, and our test results show it performs much better in these challenging cases.
}, issn = {2079-7370}, doi = {https://doi.org/10.4208/eajam.090312.190412a}, url = {http://global-sci.org/intro/article_detail/eajam/10872.html} }Most image segmentation techniques efficiently segment images with prominent edges, but are less efficient for some images with low frequencies and overlapping regions of homogeneous intensities. A recently proposed selective segmentation model often works well, but not for such challenging images. In this paper, we introduce a new model using the coefficient of variation as a fidelity term, and our test results show it performs much better in these challenging cases.