EPFL | Biomedical Imaging Group

Stability and Convergence of the Level Set Method in Computer Vision

K.N. Chaudhury, K.R. Ramakrishnan

Pattern Recognition Letters, vol. 28, no. 7, pp. 884–893, May 2007.

Several computer vision problems, like segmentation, tracking and shape modeling, are increasingly being solved using level set methodologies. But the critical issues of stability and convergence have always been neglected in most of the level set implementations. This often leads to either complete breakdown or premature/delayed termination of the curve evolution process, resulting in unsatisfactory results. We present a generic convergence criterion and also a means of determining the optimal time-step involved in the numerical solution of the level set equation. The significant improvement in the performance of level set algorithms, as a result of the proposed changes, is demonstrated using object tracking and shape-contour extraction results.

@ARTICLE(http://bigwww.epfl.ch/publications/chaudhury0701.html,
AUTHOR="Chaudhury, K.N. and Ramakrishnan, K.R.",
TITLE="Stability and Convergence of the Level Set Method in Computer
	Vision",
JOURNAL="Pattern Recognition Letters",
YEAR="2007",
volume="28",
number="7",
pages="884--893",
month="May",
note="")

© 2007 Elsevier. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from Elsevier. This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.