A Proposed Biologically Inspired Model for Object Recognition

Object recognition has attracted the attention of many researchers as it is
considered as one of the most important problems in computer vision. Two main
approaches have been utilized to develop object recognition solutions i.e. machine and
biological vision. Many algorithms have been developed in machine vision. Recently,
Biology has inspired computer scientist to map the features of the human and primate’s
visual systems into computational models. Some of these models are based on the feedforward
mechanism of information processing in cortex; however, the performance of
these models has been affected by the increase of clutter in the scene. Another
mechanism of information processing in cortex is called the feedback. This mechanism
has also been mapped into computational models. However, the results were also not
satisfying. In this paper an object recognition model based on the integration of the feedforward
and feedback functions in the visual cortex is proposed.