J. Anita Christaline ¹, R. Ramesh ², D. Vaishali ¹

Affiliations
1 Department of ECE, SRM University, SRM Nagar, Potheri, Kattankulathur, Chennai - 603203, Tamil Nadu, IN
2 Department of ECE, Saveetha Engineering College, Saveetha Nagar, Thandalam, Chennai - 602105, Tamil Nadu, IN

Abstract

Acquiring the best image features that best distinguishes a stego and clean image is a challenge in image steganalysis. Though higher order models acquire all these features, they pose problems due to computational complexity in terms of time and space. This demands optimization of the feature sets. Compared to the existing statistical feature optimization techniques, genetic algorithm based optimization techniques are evolving to be more promising. The existing deterministic methods of optimization have the limitation of converging into local minima as compared to the evolutionary methods which tend to converge to the global minima. Objectives: This paper intends to review the various genetic algorithm based feature optimization techniques applicable for image steganalysis of JPEG images and identify the best algorithm that converges to global minima. Method/Analysis: The methods analysed include the stochastic (metaheuristic) algorithms that make use of the random behaviour of plants and animals. The Antlion behaviour based optimization technique (ALO) has been implemented and analysed for JPEG stego images. The movement of ants are modelled as random walk and the traps built by antlions are assumed proportional to their fitness. The antlions shoot sand outwards to pull the ants inside the pits. This causes sliding down of the ants into the pits to the most minimum position. The coding of the optimization is implemented in Matlab with images taken from the standard BOSS database. Findings: The feature set after feature extraction has a dimension of 2000 × 48600 with 1000 cover and 1000 clean images. Considering these vectors as the initial positions of the ants in the Ant Lion Optimizer, for a payload of 0.5 in embedding logic the classification accuracies are studied. The convergence of this optimizer is proved according to the convergence curve for 300 iterations. After optimization, the reduced feature set is used to classify the image as cover or stego image. SVM, MLP and the fusion classifiers - Bayes, Decision template and Dempster Schafer are used. For low levels of embedding changes, the classification by MLP and Fusion schemes is good. For medium and high levels of embedding changes, the classification by Fusion schemes alone is good. It has been identified that the proposed steganalyser gives best results for Bayes fusion classification (69%) scheme when Antlion behaviour is used as optimizer. Applications/Improvements: This research has implemented a novel method of image feature optimization that improves steganalysis. The optimized feature set is 100 times less in dimension assuring reduced computational complexity in time and space. Improved version of this research may include a different selection mechanism or using a different optimization function.

Keywords

Bio-Inspired Algorithms, Evolutionary Algorithm, Fusion Classifiers, Stochastic Optimization, Swarm

Full Text

   

D. Vaishali ¹, R. Ramesh ², J. Anita Christaline ¹

Affiliations
1 Department of Electronics and Communication Engineering, SRM University, Chennai, Tamil Nadu, IN
2 Department of Electronics and Communication Engineering, Saveetha Engineering College, Thandalam, Tamil Nadu, IN

Abstract

Objective: Cancer diagnostic using clinical pathology have been proved as a standard method in which histologist/ pathologist examines biopsy sample for cell morphology and tissue distribution. Pathologist detects random growth and random placements in tissue samples. These diagnostics are very subjective and based on experience/knowledge base of pathologists. This work presents the use of 2D Autoregressive And Moving Average (ARMA) model in computer assisted automatic cancer detection. Analysis: ARMA model parameters have been considered for representing entire histopathology image. These features have further used for analysis and classification. Parameter estimation has been carried out by Yule walker Least Square (LS) method. Histology images have been classified into healthy and malignant images according to ARMA parameters. K- Fole cross validation has been performed with Linear Kernel support vector machine classifier for classification. Findings: As an outcomes of this experimentation, it is proven that ARMA model parameters works as an excellent discriminating features. These ARMA features are capable of extracting hidden information of the underlying cancer decease. This study also presents the role of neighborhood pixel in image analysis and classification. Improvement: This work have described innovative way of using ARMA features in histopathology imagery and can be implemented in computer assisted diagnosis.

Keywords

Autoregressive Model and Moving Average (ARMA), Markov Random Field model (MRF), Model Based Study, Quarter Plane (QP), Support Vector Machine Minimum (SVM), Texture Analysis, Yule Walker Least Square (YWLS).

Full Text