Steganalysis by ensemble classifiers with boosting by regression, and post-selection of features

In this paper we extend the state-of-the-art steganalysis tool developed by Kodovský and Fridrich: the Kodovský's ensemble classifiers. We propose to boost the weak classifiers composing the Kodovsk ý classifier. For this, we minimize the probability of error thanks to a regression approach of low complexity. We also propose a post-selection of features, achieved after the learning step of all the weak classifiers. For each weak classifier, we identify a subset of features reducing the probability of error. Both proposals are of negligeable complexity compared to the complexity of the Kodovský classifier. Moreover, these two proposals significantly increase the performance of classification.