Non-local spatial redundancy reduction for bottom-up saliency estimation

• Published in: Journal of visual communication and image representation Vol. 23; no. 7; pp. 1158 - 1166
• Main Authors: Wu, Jinjian, Qi, Fei, Shi, Guangming, Lu, Yongheng
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.10.2012
• Subjects: Bottom-up visual saliency; Entropy; Filtering; Human visual system; Image structure; Non-local; Reduction; Redundancy; Redundancy reduction; Representations; Self-similarity; Statistics; Visual; Visual attention; Redundancy reduction; Non-local; Image structure; Entropy; Human visual system; Visual attention; Self-similarity; Bottom-up visual saliency
• ISSN: 1047-3203; 1095-9076
• DOI: 10.1016/j.jvcir.2012.07.010

► The bottom-up visual saliency is estimated by spatial redundancy reduction. ► A non-local scheme is proposed to measure the spatial redundancy. ► The model is adaptive to both natural and conceptual images. In this paper we present a redundancy reduction based approach for computational bottom-up visual saliency estimation. In contrast to conventional methods, our approach determines the saliency by filtering out redundant contents instead of measuring their significance. To analyze the redundancy of self-repeating spatial structures, we propose a non-local self-similarity based procedure. The result redundancy coefficient is used to compensate the Shannon entropy, which is based on statistics of pixel intensities, to generate the bottom-up saliency map of the visual input. Experimental results on three publicly available databases demonstrate that the proposed model is highly consistent with the subjective visual attention.