Image segmentation with patch-pair density priors

In this paper, we investigate how an unlabeled image corpus can facilitate the segmentation of any given image. A simple yet efficient multi-task joint sparse representation model is presented to augment the patch-pair similarities by harnessing the newly discovered patch-pair density priors. First, each image is over-segmented as a set of patches, and the adjacent patch-pair density priors, statistically calculated from the unlabeled image corpus, bring an intuitively explainable and informative observation that kindred patchpairs generally have higher densities than inhomogeneous patchpairs. Then for each adjacent patch-pair within the given image, high-density biased multi-task joint sparse reconstruction is pursued such that 1) both individual patches and patch-pair can be reconstructed with few patch-pairs from the unlabeled image corpus, and 2) the patch-pairs selected for reconstruction are high-density biased, namely, preferring patch-pairs belonging to the same semantic regio...

• Type: Journal
• Year: 2010
• Where: MM
• Authors: Xiaobai Liu, Jiashi Feng, Shuicheng Yan, Hai Jin
• Keywords: Image, MM 2010, Multi-task Joint Sparse, Multimedia, Unlabeled Image Corpus