Paper Title
A Comparision Of Classification Algorithms For Active Learning Applied To Image Retrieval

Active learning when applied to content-based image retrieval (CBIR) systems is a challenging task. In an effort to effectively retrieve visual information, statistical learning plays a pivotal role. Active learning methods have been considered with increased interest in the statistical learning community. The aim of using active learning to CBIR is to retrieve large image categories with only a few training data. This paper provides algorithms within a statistical framework to extend active learning for content-based image retrieval .The classification framework is presented with experiments to compare several powerful classification techniques in this information retrieval context. In this paper we have focused on simple binary classification algorithms. Focusing on interactive methods, active learning strategy is then described. Experimental results on Corel database show the comparison of classification strategies to evaluate active learning contribution for CBIR.