We show that the proposed steganalyzer outperforms a state-of-the-art steganalyzer by testing our approach with many different image databases, having a total of 20000 images. POMM generalizes the concept of local neighborhood directionality by using a partial order underlying the pixel locations. ![]() Based on our experimental observation, we then propose a new modeling technique for steganalysis by developing a Partially Ordered Markov Model (POMM) (23) to JPEG images more » and use its properties to train a Support Vector Machine. ![]() We show that using our approach, reduced-feature steganalyzers can be obtained that perform as well as the original steganalyzer. We apply this technique to state-of-the-art steganalyzer proposed by Tom´as Pevn´y (54) to understand the feature space complexity and effectiveness of features for steganalysis. Many successful steganalysis algorithms use a large number of features relative to the size of the training set and suffer from a ”curse of dimensionality”: large number of feature values relative to training data size. Our approach is two fold: first, we propose a new feature reduction technique by applying Mahalanobis distance to rank the features for steganalysis. JPEG image steganalysis is generally addressed by representing an image with lower-dimensional features such as statistical properties, and then training a classifier on the feature set to differentiate between an innocent and stego image. This research focuses on steganalysis of JPEG images, because of its ubiquitous nature and low bandwidth requirement for storage and transmission. ![]() Steganalysis deals with identifying the instances of medium(s) which carry a message for communication by concealing their exisitence.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |