The existing cosegmentation methods focus on exploiting inter-image information to extract a common object from a single image group. Observing that in many practical scenarios there often exist multiple image groups with distinct characteristics but related to the same common object, in this paper we propose a multi-group image cosegmentation framework, which not only discoveries inter-image information within each image group, but also transfers inter-group information among different image groups so as to produce more accurate object priors. Particularly, the multi-group cosegmentation task is formulated as an energy minimization problem, where we employ Markov random field (MRF) segmentation model and the dense correspondence model in the model design and adapt the Expectation-Maximization algorithm (EM) to solve the optimization. We apply the proposed framework on three practical scenarios including image complexity based cosegmentation, multiple training group cosegmentation and multiple noise image group cosegmentation. Experimental results on four benchmark datasets demonstrate that the proposed multi-group image cosegmentation framework is able to discover more accurate object priors and outperform state-of-the-art single-group image cosegmentation methods.
- Image segmentation
- Multiple group cosegmentation