A Goal-Directed Visual Perception System Using Object-Based Top-Down Attention

—The tendency of the human being to apply the selective attention mechanism so as to determine about a truly intelligent perception system, which has the cognitive capability of learning and thinking about how to perceive the environment on its own. There are two attention mechanisms involved one of which is the top–down and the other bottom–up that correspond to the goal-directed and automatic perceptual behaviors, respectively. In this paper we review an artificial system with goal-directed visual perception approach and which uses the object-based top–down visual attention mechanism. This system will able us to determine the perception to an object of interest according to the current task, context and learned knowledge. This system can be mainly divided into three successive stages: first one is preattentive processing, second one top–down attentional selection and last is post-attentive perception. In first stage that is preattentive processing we consider an input scene which gets divided into what we say similar proto-objects, out of these one is then selected by applying the top–down attention and finally it is sent to the post-attentive perception stage for analysis and final outcome.