Abstract:With massive feature set and high-dimensional sample set,steganalysis has a increasingly demanding for classifiers.Based on ensemble classifier,a kind of selective ensemble classifier for universal steganalysis was proposed.At first,some base learners were generated based on the random forest and then some of them were wept out using GASEN(genetic algorithm based selective ensemble) algorithm.At last,remaining base classifiers were given different weights according to the optimal weight vector from genetic optimization to get used to the weighted vote integration. Experiments showed that the elective ensemble classifier performed better than existing single classifier. Compared with the existing ensemble classifier, especially in the case of larger base classifiers or higher number of features, the computational complexity was slightly increased, but the error rate reduced effectively.