Saliency detection based on scale selectivity of human visual system

Authors:
Fang Fang;Laiyun Qing;Jun Miao;Xilin Chen;Wen Gao
Affiliations:
School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China;Graduate University of Chinese Academy of Science, Beijing, China;Key Laboratory of Intelligent Information Processing, Institute of Computing, Technology, Chinese Academy of Sciences, Beijing, China;Key Laboratory of Intelligent Information Processing, Institute of Computing, Technology, Chinese Academy of Sciences, Beijing, China;School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China
Venue:
ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I
Year:
2011

Citing 3
Cited 0

A Model of Saliency-Based Visual Attention for Rapid Scene Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Saliency, Scale and Image Description

International Journal of Computer Vision
Salient region detection and segmentation

ICVS'08 Proceedings of the 6th international conference on Computer vision systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

It is well known that visual attention and saliency mechanisms play an important role in human visual perception. This paper proposes a novel bottom-up saliency mechanism through scale space analysis. The research on human perception had shown that our ability to perceive a visual scene with different scales is described with the Contrast-Sensitivity Function (CSF). Motivated by this observation, we model the saliency as weighted average of the multi-scale analysis of the visual scene, where the weights of the middle spatial frequency bands are larger than others, following the CSF. This method is tested on natural images. The experimental results show that this approach is able to quickly extract salient regions which are consistent with human visual perception, both qualitatively and quantitatively.