Modeling of a neural network system for active visual perception and recognition

In the modern view of the problem, invariant object recognition is provided by the following: (i) separated processing of “what” (object features) and “where” (spatial features) information at high levels of the visual system; (ii) mechanisms of visual attention using “where” information; (iii) representation of “what” information in an object-based frame of reference (OFR). However, most recent models of vision based on OFR have demonstrated the ability of invariant recognition of only simple objects like letters or binary objects without background, i.e. objects to which a frame of reference is easily attached. In contrast, the authors have based their model not on OFR, but on scanpath theory and on a feature-based frame of reference (FFR), connected with the basic feature (edge) at each fixation point. This has allowed the authors to consider some behavior aspects of vision and has provided for their model the ability for invariant representation and recognition of complex objects in gray-level images