GVU Technical Report Number: GIT-GVU-04-29

Title: Grammatical Methods in Computer Vision: An Overview

Authors: Gaurav Chanda, Frank Dellaert

Abstract:
We review various methods and applications that have used grammars for solving inference problems in computer vision and pattern recognition. Grammars have been useful because they are intuitively simple to understand, and have very elegant representations. Their ability to model semantic interpretations of patterns, both spatial and temporal, have made them extremely popular in the research community. In this paper, we attempt to give an overview of what syntactic methods exist in the literature, and how they have been used as tools for pattern modeling and recognition. We also describe several practical applications, which have used them with great success.

Keywords: Context free grammars, attribute grammars, parsing, graph grammars, array grammars, picture language, stochastic grammars, shape grammars

You can access this technical report via: PDF, Postscript