A Model of Attention and Recognition by Information Maximization

ABSTRACT The perception of an image by a human observer is a highly selective procedure in which only a small subset of image locations is selected and processed by the precise and efficient neural machinery of foveal vision. To understand the principles behind this selection of the informative regions of images, we have developed a hybrid system, which consists of a combination of a top-down knowledge-based reasoning system with a low-level preprocessing by linear and nonlinear neural operators ( Schill, 1997 ; Schill et al., 2001) . In the analysis of a scene, the system generates a fixation sequence by calculating in each step which feature has to be selected next to reach a maximum of information gain. The information gain calculation is based on the Dempster-Shafer belief theory, which is also used to establish a hypothesis about the scene.

[1]  John K. Tsotsos,et al.  Modeling Visual Attention via Selective Tuning , 1995, Artif. Intell..

[2]  Rajesh P. N. Rao,et al.  Eye Movements in Visual Cognition: A Computational Study , 1997 .

[3]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[4]  Kerstin Schill.  Decision Support Systems with Adaptive Reasoning Strategies , 1997, Foundations of Computer Science: Potential - Theory - Cognition.

[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]  Gerhard Krieger,et al.  Scene analysis with saccadic eye movements: Top-down and bottom-up modeling , 2001, J. Electronic Imaging.

[7]  Gerhard Krieger,et al.  Nonlinear mechanisms and higher-order statistics in biological vision and electronic image processing: review and perspectives , 2001, J. Electronic Imaging.

[8]  Christof Koch,et al.  Feature combination strategies for saliency-based visual attention systems , 2001, J. Electronic Imaging.

[9]  I. Rybak,et al.  A model of attention-guided visual perception and recognition , 1998, Vision Research.

[10]  L. Stark,et al.  Scanpaths in saccadic eye movements while viewing and recognizing patterns. , 1971, Vision research.

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

[12]  Lawrence W. Stark,et al.  Top-down guided eye movements , 2001, IEEE Trans. Syst. Man Cybern. Part B.

[13]  Edward H. Shortliffe,et al.  A Method for Managing Evidential Reasoning in a Hierarchical Hypothesis Space , 1985, Artif. Intell..

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