Title :
Enhanced Figure-Ground Classification With Background Prior Propagation
Author :
Yisong Chen ; Chan, Antoni B.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Peking Univ., Beijing, China
Abstract :
We present an adaptive figure-ground segmentation algorithm that is capable of extracting foreground objects in a generic environment. Starting from an interactively assigned background mask, an initial background prior is defined and multiple soft-label partitions are generated from different foreground priors by progressive patch merging. These partitions are fused to produce a foreground probability map. The probability map is then binarized via threshold sweeping to create multiple hard-label candidates. A set of segmentation hypotheses is formed using different evaluation scores. From this set, the hypothesis with maximal local stability is propagated as the new background prior, and the segmentation process is repeated until convergence. Similarity voting is used to select a winner set, and the corresponding hypotheses are fused to yield the final segmentation result. Experiments indicate that our method performs at or above the current state-of-the-art on several data sets, with particular success on challenging scenes that contain irregular or multiple-connected foregrounds.
Keywords :
feature extraction; image classification; image segmentation; statistical analysis; adaptive figure-ground segmentation algorithm; background mask; background prior; background prior propagation; enhanced figure-ground classification; evaluation scores; foreground object extraction; foreground probability map; progressive patch merging; segmentation hypothesis; similarity voting; soft-label partition; threshold sweeping; Algorithm design and analysis; Bandwidth; Classification algorithms; Covariance matrices; Image color analysis; Image segmentation; Partitioning algorithms; Image segmentation; multiple hypotheses fusion; similarity voting;
Journal_Title :
Image Processing, IEEE Transactions on
DOI :
10.1109/TIP.2015.2389612