Computational models of visual object recognition

Abstract

Visual object recognition constitutes a prime example of a cognitive task that seems to be almost instantaneous and effortless for humans, yet involves formidable challenges for computers. We open our eyes and by shifting our gaze we can under most circumstances, easily identify the people around us, navigate through the environment, and recognize a large number of objects. The intricate neuronal circuitry behind this process is intensely studied using a combination of neurophysiological recordings and computational models. Here, we summarize some of the initial steps toward a theoretical understanding of the computational principles behind transformation-invariant visual recognition in the primate cortex.