Making large-scale support vector machine learning practical
Advances in kernel methods
Detecting Hidden Messages Using Higher-Order Statistics and Support Vector Machines
IH '02 Revised Papers from the 5th International Workshop on Information Hiding
DCT-based watermark recovering without resorting to the uncorrupted original image
ICIP '97 Proceedings of the 1997 International Conference on Image Processing (ICIP '97) 3-Volume Set-Volume 1 - Volume 1
Blind Image Steganalysis Based on Statistical Analysis of Empirical Matrix
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Defending against statistical steganalysis
SSYM'01 Proceedings of the 10th conference on USENIX Security Symposium - Volume 10
Score normalization in multimodal biometric systems
Pattern Recognition
IH'05 Proceedings of the 7th international conference on Information Hiding
Improving steganalysis by fusion techniques: a case study with image steganography
Transactions on Data Hiding and Multimedia Security I
Steganalysis for Markov cover data with applications to images
IEEE Transactions on Information Forensics and Security
Secure spread spectrum watermarking for multimedia
IEEE Transactions on Image Processing
Digital image splicing detection based on Markov features in DCT and DWT domain
Pattern Recognition
A comprehensive study on third order statistical features for image splicing detection
IWDW'11 Proceedings of the 10th international conference on Digital-Forensics and Watermarking
Hi-index | 0.00 |
In this paper, a feature-level fusion based approach is proposed for blind image steganalysis. We choose three types of typical higher-order statistics as the candidate features for fusion and make use of the Boosting Feature Selection (BFS) algorithm as the fusion tool to select a subset of these candidate features as the new fusion feature vector for blind image steganalysis. Support vector machines are then used as the classifier. Experimental results show that the fusion based approach increases the blind detection accuracy and also provides a good generality by identifying an untrained stego-algorithm. Moreover, we evaluate the performance of our candidate features for fusion by making some analysis of the components of the fusion feature vector in our experiments.