I. A. Rybak 1, V. I. Gusakova 2, A. V. Golovan 3,
L. N. Podladchikova 2, and N. A. Shevtsova 4

1 E. I. du Pont de Nemours & Co., Central Research Department, Experimental Station
E-328/B31 Wilmington, DE 19880-0328, USA
2 A. B. Kogan Research Institute for Neurocybernetics, Rostov State University,
194/1 Stachka Ave., Rostov-on-Don 344090, Russia
3 MBTI, George Mason University, Fairfax, VA 22030, USA
4 Institute of Advanced Computer Studies, University of Maryland,
College Park, MD 20742, USA


A model of visual perception and recognition is described. The model contains: (i) a low-level subsystem which performs both a fovea-like transformation and detection of primary features (edges), and (ii) a high-level subsystem which includes separated what (sensory memory) and where (motor memory) structures. Image recognition occurs during the execution of a "behavioral recognition program" formed during the primary viewing of the image. The recognition program contains both programmed movements of an attention window (stored in the motor memory) and predicted image fragments (stored in the sensory memory) for each consecutive fixation. The model shows the ability to recognize complex images (e.g. faces) invariantly with respect to shift, rotation and scale.

Keywords: Visual perception, Invariant recognition, Attention, Eye movements, Scanpath

[Full paper]

Back to Publication List