Los Alamos National Laboratory
Phone| Search
T-5 HomeResearchPublications › chartrand-2008-faster
› Contact › People › Research
› Projects › Highlights › Publications
› Jobs › Visitor Info

Cite Details

Rick Chartrand and Valentina Staneva, "A faster-converging algorithm for image segmentation with a modified Chan-Vese model", in International Conference on Image Processing, Computer Vision, and Pattern Recognition (IPCV), 2008

Abstract

We propose an algorithm for segmentation of grayscale images. Our algorithm computes a solution to the convex, unconstrained minimization problem proposed by T. Chan, S. Esedog̅lu, and M. Nikolova, which is closely related to the Chan-Vese level set algorithm for the Mumford-Shah segmentation model. Up to now this problem has been solved with a gradient descent method. Our approach is a quasi-Newton method based on the lagged diffusivity algorithm of C. Vogel and M. Oman for minimizing the total-variation functional for image denoising of S, Osher, W. Rudin, and E. Fatemi. Our results show that our algorithm requires a much smaller number of iterations and less time to converge than gradient descent, and is able to segment noisy images correctly.

BibTeX Entry

@inproceedings{chartrand-2008-faster,
author = {Rick Chartrand and Valentina Staneva},
title = {A faster-converging algorithm for image segmentation with a modified Chan-Vese model},
year = {2008},
urlpdf = {http://math.lanl.gov/Research/Publications/Docs/chartrand-2008-faster.pdf},
booktitle = {International Conference on Image Processing, Computer Vision, and Pattern Recognition (IPCV)}
}