Momentum Based Optimization Methods for Level Set Segmentation
2009 (English)In: Momentum Based Optimization Methods for Level Set Segmentation: Second International Conference, SSVM 2009, Voss, Norway, June 1-5, 2009. Proceedings / [ed] Gerhard Goos, Juris Hartmanis, and Jan van Leeuwen, Berlin: Springer Berlin/Heidelberg, 2009, 124-136 p.Conference paper (Refereed)
Segmentation of images is often posed as a variational problem. As such, it is solved by formulating an energy functional depending on a contour and other image derived terms. The solution of the segmentation problem is the contour which extremizes this functional. The standard way of solving this optimization problem is by gradient descent search in the solution space, which typically suffers from many unwanted local optima and poor convergence. Classically, these problems have been circumvented by modifying the energy functional. In contrast, the focus of this paper is on alternative methods for optimization. Inspired by ideas from the machine learning community, we propose segmentation based on gradient descent with momentum. Our results show that typical models hampered by local optima solutions can be further improved by this approach. We illustrate the performance improvements using the level set framework.
Place, publisher, year, edition, pages
Berlin: Springer Berlin/Heidelberg, 2009. 124-136 p.
Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 5567
Medical Laboratory and Measurements Technologies
IdentifiersURN: urn:nbn:se:liu:diva-21037DOI: 10.1007/978-3-642-02256-2_11ISI: 000270543900011ISBN: 3-642-02255-3ISBN: 978-3-642-02255-5ISBN: e-978-3-642-02256-2OAI: oai:DiVA.org:liu-21037DiVA: diva2:240452
Second International Conference, SSVM 2009, June 1-5, Voss, Norway
Original Publication: Gunnar Läthén, Thord Andersson, Reiner Lenz and Magnus Borga, Momentum Based Optimization Methods for Level Set Segmentation, 2009, Lecture Notes in Computer Science 5567: Scale Space and Variational Methods in Computer Vision, 124-136. http://dx.doi.org/10.1007/978-3-642-02256-2_11 Copyright: Springer http://www.springerlink.com/2009-09-282009-09-282016-08-31Bibliographically approved