A Saliency Map Model for Color Images using Statistical Information and Local Competitive Relations of Extracted Features

Biological systems appear to employ a serial strategy by which an attentional spotlight rapidly selects circumscribed regions in the scene, rather than attempting to fully interpret visual scenes in a parallel manner for further analysis. In this paper, we propose a biologically motivated saliency map model and applied our system to locating candidate regions of interest on various images for further detailed analysis. In proposed model, several basic features are extracted directly from visual stimuli, and these features are integrated based on their statistical information and local competitive relations. Through integration process, unnecessary features for detecting the salient object are spontaneously decreased while useful features are enhanced. The performance of the model is evaluated over various color images of synthetic and complex real images.

[1]  P. A. Sandon.  Simulating Visual Attention , 1990, Journal of Cognitive Neuroscience.

[2]  A. L. Yarbus,et al.  Eye Movements and Vision , 1967, Springer US.

[3]  S Ullman,et al.  Shifts in selective visual attention: towards the underlying neural circuitry. , 1985, Human neurobiology.

[4]  Thierry Pun,et al.  Integration of bottom-up and top-down cues for visual attention using non-linear relaxation , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[5]  D. V. van Essen,et al.  A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information , 1993, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[6]  K. Cave.  The FeatureGate model of visual selection , 1999, Psychological research.

[7]  A. L. I︠A︡rbus.  Eye Movements and Vision , 1967 .

[8]  C. Colby,et al.  The Neuroanatomy and Neurophysiology of Attention , 1991 .

[9]  Gordon Cheng,et al.  Development of a Biologically Inspired Real-Time Visual Attention System , 2000, Biologically Motivated Computer Vision.

[10]  Jeremy M Wolfe,et al.  Modeling the role of parallel processing in visual search , 1990, Cognitive Psychology.

[11]  A. Treisman,et al.  A feature-integration theory of attention , 1980, Cognitive Psychology.

[12]  C. Koch,et al.  A saliency-based search mechanism for overt and covert shifts of visual attention , 2000, Vision Research.

[13]  Yoshiki Uchikawa,et al.  Active vision inspired by mammalian fixation mechanism , 1994, IROS.

[14]  PIERRE VAN DE LAAR,et al.  Task-Dependent Learning of Attention , 1997, Neural Networks.

[15]  David Chapman,et al.  Vision, instruction, and action , 1990 .

[16]  W. D. Ross,et al.  Incremental Art: A Neural Network System for Recognition by Incremental Feature Extraction , 1994 .