D. Vaishali

Image steganographic techniques with improved embedding capacity and robustness

Secured data transmission over computer networks can be achieved through steganography. In specific, Image Steganography entails the opportunity of hide any secret information into images. This paper presents the implementation of two image steganographic techniques in MATLAB. The first is a filter method to embed text information into image and new methods have been demonstrated to increase the information embedding capacity in the same domain. The second method is the wavelet transform method which proves to be more secured than any other method of image steganography.

Critical review of image steganalysis techniques

Steganography is the art of covert communication aims at hiding information onto a digital cover media. The choice of the cover medium could be audio, image or video files. Owing to the illegal use of such secret communications, steganalysis the art of code breaking steganography has gained momentum. This paper presents the recent trends in image steganalysis techniques. The two prominent methods have been identified as embedding specific and universal blind steganalysis. As universal blind steganalysis does not demand the prior knowledge of the embedding method, it has become the choice of many steganalysers. It has been identified that universal steganalysis is a two class classification problem and could be implemented with statistical analyses or computational intelligence. As this classification depends on the chosen feature set or the image model, this paper has detailed the feature-based image steganalysis techniques. The curse of dimensionality increased computational time of the chosen feature sets compel the use of statistical feature reduction methods. Hence, the features set optimisation technique have been reviewed in detail.

2 D autoregressive model for texture analysis and synthesis

Spatial autoregressive (AR) models have been extensively used to represent texture images in machine learning applications. This work emphasizes the contribution of 2D autoregressive models for analysis and synthesis of textural images. Autoregressive model parameters as a feature set of texture image represent texture and used for synthesis. Yule walker Least Square (LS) method has used for parameter estimation. The test statistics for choice of proper neighbourhood (N) has also been suggested. The Brodatz texture image album has chosen for the experimentation. Parameters have estimated from the textures. The test statistics decides the best neighbourhood or proper order of the model. The synthesized texture image and the original texture image have compared for perceptual similarities. It is been inferred that the proper neighbourhood for a given texture is unique and solely depends on the properties of the texture.