Boosting of Maximal Figure of Merit Classifiers for Automatic Image Annotation

Visual information contained in a scene is very complex and can be represented with multiple features describing aspects of the entire information. In this paper we propose a boosting approach to automatic image annotation by building strong classifiers based on multiple collections of weak concept classifiers with each collection focused on a single visual feature. The weak classifiers are trained with a maximal figure-of-merit learning approach. By exploiting multiple features the boosting procedure allows to build classifiers able to pick the most discriminative feature for the specific annotation task.