Classification of PQ Stego-Images and F5 Stego-Images using SVM

Abstract

PQ and F5 are two typical steganography methods of JPEG images and have been used widely. To compare the robustness of the above two algorithms, to withstand steganalytic attack a classification algorithm based on sensitive features is presented. SVM is used as a classifier using sensitive features extracted from two domains DCT and DWT. A comparison between the two types of features is also shown. Experimental results show that the PQ method can withstand steganalytic attack by a margin of 30% accuracy as compared to F5, hence PQ is more reliable for

4 Figures and Tables

Cite this paper

@inproceedings{Chhikara2013ClassificationOP, title={Classification of PQ Stego-Images and F5 Stego-Images using SVM}, author={Rita Rana Chhikara and Deepika Bansal}, year={2013} }