Issue No. 10 - October (2006 vol. 28)
Gang Hua , IEEE
Zicheng Liu , IEEE
Zhengyou Zhang , IEEE
Ying Wu , IEEE
We propose a novel global-local variational energy to automatically extract objects of interest from images. Previous formulations only incorporate local region potentials, which are sensitive to incorrectly classified pixels during iteration. We introduce a global likelihood potential to achieve better estimation of the foreground and background models and, thus, better extraction results. Extensive experiments demonstrate its efficacy.
Variational energy, level set, semisupervised learning.
Z. Liu, Z. Zhang, G. Hua and Y. Wu, "Iterative Local-Global Energy Minimization for Automatic Extraction of Objects of Interest," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 28, no. , pp. 1701-1706, 2006.