Sequential convex relaxation for mutual information-based unsupervised figure-ground segmentation

Kee Y, Souiai M, Cremers D, Kim J (2014)

Publication Type: Conference contribution

Publication year: 2014

Journal

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition IEEE Computer Society; 1999

Publisher: IEEE Computer Society

Pages Range: 4082-4089

Conference Proceedings Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Event location: Columbus, OH, USA

ISBN: 9781479951178

DOI: 10.1109/CVPR.2014.520

Abstract

We propose an optimization algorithm for mutual information-based unsupervised figure-ground separation. The algorithm jointly estimates the color distributions of the foreground and background, and separates them based on their mutual information with geometric regularity. To this end, we revisit the notion of mutual information and reformulate it in terms of the photometric variable and the indicator function; and propose a sequential convex optimization strategy for solving the nonconvex optimization problem that arises. By minimizing a sequence of convex sub-problems for the mutual-information-based nonconvex energy, we efficiently attain high quality solutions for challenging unsupervised figure-ground segmentation problems. We demonstrate the capacity of our approach in numerous experiments that show convincing fully unsupervised figure-ground separation, in terms of both segmentation quality and robustness to initialization.

Involved external institutions

Korea Advanced Institute of Science and Technology (KAIST) KR Korea, Republic of (KR) Technische Universität München (TUM) DE Germany (DE)

How to cite

APA:

Kee, Y., Souiai, M., Cremers, D., & Kim, J. (2014). Sequential convex relaxation for mutual information-based unsupervised figure-ground segmentation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 4082-4089). Columbus, OH, USA: IEEE Computer Society.

MLA:

Kee, Youngwook, et al. "Sequential convex relaxation for mutual information-based unsupervised figure-ground segmentation." Proceedings of the 27th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, OH, USA IEEE Computer Society, 2014. 4082-4089.

BibTeX: Download