A comparison between various classification methods for image classification stage in CBIR

This paper´s objective is to investigate and compare classification performances for different methods (Radial Basis Function networks, Support Vector Machines neural networks, Naïve Bayes and Decision Trees). The purpose of this comparison is to choose the best solution in terms of performance/computation to be included in an integrated framework for semantic image analysis that is suitable for content-based image retrieval by combining classical descriptors with classification algorithms.