A Robust Local Model for Segmentation Based on Coefficient of Variation

Volume 5  Issue 1    2011


Author(s): Ocenasek Pavel, Hranac Jakub
Abstract Many image segmentation models work efficiently when segmenting images with prominent edges and regions but often we need to segment images with low contrast, unilluminated objects, inhomogeneity problems and images with overlapping region of almost homogeneous intensities. In fact these mentioned images pose challenges to the existing models. In this paper, we proposed a new variational model for image segmentation, based on a robust local statistical information. In contrast with the existing models, the experimental results validate that the new proposed model is robust in terms of accurate detection in such tough images.
Keywords Segmentation, Level Set, Functional Minimization, Coefficient of Variation (CoV ), Total Variation.
Year 2011
Volume 5
Issue 1
Type Research paper, manuscript, article
Journal Name Journal of Information & Communication Technology
Publisher Name ILMA University
Jel Classification -
ISSN no (E, Electronic) 2075-7239
ISSN no (P, Print) 2415-0169
Country Pakistan
City Karachi
Institution Type University
Journal Type Open Access
Manuscript Processing Blind Peer Reviewed
Format PDF
Paper Link https://jict.ilmauniversity.edu.pk/journal/jict/5.1/4.pdf
Page 30-39