Models of the Visual Cortex for Object Representation: Learning and Wired Approaches

摘要: Computational modeling now spans more than three decades. Biologically-plausible models are usually organized into a hierarchy that the brain in primates after carefully examining neurophysiological and psychophysical studies. Currently, these extract some values (corners, edges, textures, contours) from images then apply machine learning algorithms to learn objects or shapes. Are they really different classical, non-biologically-inspired, computer vision methods? What facts can we primate visual system other extensively used edge extraction by means of Gabor filters? Should work on representation along this before applying strategy? We review status computational for object recognition propose what be next challenges solve.