Saliency based on cortex-like mechanisms

Abstract

A visual attention system should preferentially locate the most informative spots in complex environments. Feature-integration theory of attention plays an important role in bottom-up computational model for visual attention. This point extremely decreases the detection accuracy and also impacts the performance of the automatic visual attention model. To improve the accuracy of saliency detection in human visual attention, we propose a model based on cortex-like mechanisms. Saliency Criteria are obtained from two pathways: Shannon's entropy and sparse representation. And our model not only substantiates the bottom-up model proposed by Itti and HMAX model by Paggio, but also enriches the theory of saliency detection. We demonstrate that the proposed model achieves superior accuracy in comparison to the classical approach in static saliency map generation on real data of natural scenes and psychology stimuli patterns.

Keywords:

• bottom-up model
• HMAX model
• cortex-like mechanisms
• ICA
• Shannon entropy

2010 AMS Subject Classifications :

• 68T10
• 68T45
• 68U10

Acknowledgements

We want to thank the helpful comments and suggestions from the anonymous reviewers. This research was supported by the National Natural Science Foundation of China (41031064, 60902082), the Ocean Public Welfare Scientific Research Project, State Oceanic Administration of China (No. 201005017), the Fundamental Research Funds for the Central Universities (JY10000902016) and Natural Science Basic Research Plan in Shaanxi Province of China (No.2011JQ8019).