STEGANALYSIS BASED ON MOMENTS OF CHARACTERISTIC FUNCTIONS USING WAVELET DECOMPOSITION, PREDICTION-ERROR IMAGE, AND NEURAL NETWORK (WedAmOR8)

Author(s) : Yun Shi (New Jersey Institute of Technology, United States of America) Guorong Xuan (Tongji University, China) Dekun Zou (New Jersey Institute of Technology, United States of America) Jianjiong Gao (Tongji University, China) Chengyun Yang (Tongji University, China) Zhenping Zhang (Tongji University, China) Peiqi Chai (Tongji University, China) Wen Chen (New Jersey Institute of Technology, United States of America) Chunhua Chen (New Jersey Institute of Technology, United States of America)

Abstract : In this paper, a general blind steganalysis system is proposed, in which the statistical moments of characteristic functions of the prediction-error image, the test image, and their wavelet subbands are selected as features. Artificial neural network is utilized as the classifier. The performance of the proposed steganalysis system is significantly superior to the prior arts.

Menu