Unsupervised segmentation based on robust estimation and color active contour models.

Lin Yang(1),(2), Peter Meer(1), David Foran(2)

(1)Department of Electrical and Computer Engineering
Rutgers University, Piscataway, NJ 08854, USA

(2)BioImaging Laboratory, Department of Pathology and Laboratory Medicine
UMDNJ-Robert Wood Johnson Medical School
Piscataway, NJ 08855, USA

One of the most commonly utilized clinical tests performed today is the routine evaluation of peripheral blood smears. In this paper, we investigate the design, development, and implementation of a robust color GVF active contour model for performing segmentation using a database of 1,791 imaged cells. The algorithms developed for this research operate in Luv color space and introduce a color gradient and L_{2}E robust estimation into the traditional GVF snake. The accuracy of the new model was compared with the segmentation results utilizing a mean-shift approach, the traditional color GVF snake and several other commonly utilized segmentation strategies. The unsupervised robust color snake with L_{2}E robust estimation was shown to provide results which were superior to the other unsupervised approaches and was comparable with supervised segmentation as judged by a panel of human experts.

IEEE Trans. on Information Technology in Biomedicine, 9, 475-486, 2005.

Return to Research: Content-based retrieval       Return to List of Publications
Download the paper