Comparative evaluation of spatial context techniques for semantic image analysis

Abstract

In this paper, two approaches to utilizing contextual information in semantic image analysis are presented and comparatively evaluated. Both approaches make use of spatial context in the form of fuzzy directional relations. The first one is based on a Genetic Algorithm (GA), which is employed in order to decide upon the optimal semantic image interpretation by treating semantic image analysis as a global optimization problem. On the other hand, the second method follows a Binary Integer Programming (BIP) technique for estimating the optimal solution. Both spatial context techniques are evaluated with several different combinations of classifiers and low-level features, in order to demonstrate the improvements attained using spatial context in a number of different image analysis schemes.