An information theory perspective on computational vision

Abstract

This paper introduces computer vision from an information theory perspective. We discuss how vision can be thought of as a decoding problem where the goal is to find the most efficient encoding of the visual scene. This requires probabilistic models which are capable of capturing the complexity and ambiguities of natural images. We start by describing classic Markov Random Field (MRF) models of images. We stress the importance of having efficient inference and learning algorithms for these models and emphasize those approaches which use concepts from information theory. Next we introduce more powerful image models that have recently been developed and which are better able to deal with the complexities of natural images. These models use stochastic grammars and hierarchical representations. They are trained using images from increasingly large databases. Finally, we described how techniques from information theory can be used to analyze vision models and measure the effectiveness of different visual cues.

Key words： computer vision; pattern recognition; information theory; minimum description length; Markov random field (MRF) model; stochastic grammars