Hypergraph-based saliency map generation with potential region-of-interest approximation and validation

Abstract

A novel saliency model is proposed in this paper to automatically process images in the similar way as the human visual system which focuses on conspicuous regions that catch human beings’ attention. The model combines a hypergraph representation and a partitioning process with potential region-of-interest (p-ROI) approximation and validation. Experimental results demonstrate that the proposed method shows considerable improvement in the performance of saliency map generation.