Investigating Shape Representation in Area V4 with HMAX

Motivation: Based on the known properties of the neurons in the earlier information-processing areas, such as V1, it is possible to make a very quantitative model of how the visual cortex may be organized. In fact, Riesenhuber and Poggio’s HMAX model has been useful in making several physiologically consistent predictions about the properties of the visual cortex [4]. The HMAX model can also be used to make testable conjectures about how the intermediate visual pathway may be organized and how features and shapes are represented in the visual cortex. Understanding the feature representations and neural mechanisms in the intermediate visual pathway may ultimately help to answer an even more difficult question of how the brain recognizes and classifies an object.