Suresh N. Mali

Robust and secured image-adaptive data hiding

Rapid growth in the demand and consumption of digital information in past decade has led to valid concerns over issues such as content security, authenticity and digital right management. Imperceptible data hiding in digital images is an excellent example of demonstration of handling these issues. Classical Cryptography is related with concealing the content of messages, whereas, Steganography is related with concealing the existence of communication by hiding the messages in cover. This paper presents a robust and secured method of embedding high volume of text information in digital Cover-images without incurring any perceptual distortion. It is robust against intentional or unintentional attacks such as image compression, tampering, resizing, filtering and Additive White Gaussian Noise (AWGN). The schemes available in the literature can deal with these attacks individually, whereas the proposed work is a single methodology that can survive all these attacks. Image Adaptive Energy Thresholding (AET) is used while selecting the embedding locations in frequency domain. Coding framework with Class Dependent Coding Scheme (CDCS) along with redundancy and interleaving of embedded information gives enhancement in data hiding capacity. Perceptual quality of images after data hiding has been tested using Peak Signal to Noise Ratio (PSNR) whereas statistical variations in selected Image Quality Measures (IQMs) are observed with respect to Steganalysis. The results have been compared with existing algorithms like STOOL in spatial domain, COX in DCT domain and CDMA in DWT domain.

MEO based secured, robust, high capacity and perceptual quality image watermarking in DWT-SVD domain.

The aim of this paper is to present multiobjective evolutionary optimizer (MEO) based highly secured and strongly robust image watermarking technique using discrete wavelet transform (DWT) and singular value decomposition (SVD). Many researchers have failed to achieve optimization of perceptual quality and robustness with high capacity watermark embedding. Here, we achieved optimized peak signal to noise ratio (PSNR) and normalized correlation (NC) using MEO. Strong security is implemented through eight different security levels including watermark scrambling by Fibonacci-Lucas transformation (FLT). Haar wavelet is selected for DWT decomposition to compare practical performance of wavelets from different wavelet families. The technique is non-blind and tested with cover images of size 512x512 and grey scale watermark of size 256x256. The achieved perceptual quality in terms of PSNR is 79.8611dBs for Lena, 87.8446 dBs for peppers and 93.2853 dBs for lake images by varying scale factor K1 from 1 to 5. All candidate images used for testing namely Lena, peppers and lake images show exact recovery of watermark giving NC equals to 1. The robustness is tested against variety of attacks on watermarked image. The experimental demonstration proved that proposed method gives NC more than 0.96 for majority of attacks under consideration. The performance evaluation of this technique is found superior to all existing hybrid image watermarking techniques under consideration.

Identification of paddy varieties based on novel seed angle features

Explore a novel feature extraction method.Find whether the proposed features have high dominant power.Proposed features gave an accuracy of 97.6% as compared to Color-Shape-Texture. The purpose of this article was to explore a new feature extraction method for classifying paddy seeds using a feature extraction algorithm to achieve the Horizontal-Vertical and Front-Rear angles. The method used fusion of angle features for classification, which were then compared to features such as seed color, shape, and texture. Experiments show that the proposed features work better in classifying paddy seeds in comparison with some of the standard features, and that the proposed features have an excellent discriminating property for seeds. The discriminating power of these features was assessed using the neural network architectures for the unique identification of seeds of four Paddy (Rice) grains: viz. Karjat-6(K6), Karjat-2(K2), Ratnagiri-4(R4) and Ratnagiri-24(R24). The classification accuracies of Color-Shape-Texture obtained was 95.2% while the proposed method gave an accuracy of 97.6%.

Evaluation of Texture and Shape Features for Classification of Four Paddy Varieties

This research is aimed at evaluating the texture and shape features using the most commonly used neural network architectures for cereal grain classification. An evaluation of the classification accuracy of texture and shape features and neural network was done to classify four Paddy (rice) grains, namely, Karjat-6(K6), Ratnagiri-2(R2), Ratnagiri-4(R4), and Ratnagiri-24(R24). Algorithms were written to extract the features from the high-resolution images of kernels of four grain types and used as input features for classification. Different feature models were tested for their ability to classify these cereal grains. Effect of using different parameters on the accuracy of classification was studied. The most suitable feature from the features for accurate classification was identified. The shape feature set outperformed the texture feature set in almost all the instances of classification.

Security Enrichment in Intrusion Detection System Using Classifier Ensemble

In the era of Internet and with increasing number of people as its end users, a large number of attack categories are introduced daily. Hence, effective detection of various attacks with the help of Intrusion Detection Systems is an emerging trend in research these days. Existing studies show effectiveness of machine learning approaches in handling Intrusion Detection Systems. In this work, we aim to enhance detection rate of Intrusion Detection System by using machine learning technique. We propose a novel classifier ensemble based IDS that is constructed using hybrid approach which combines data level and feature level approach. Classifier ensembles combine the opinions of different experts and improve the intrusion detection rate. Experimental results show the improved detection rates of our system compared to reference technique.

Performance comparison of second order statistics texture features for variety identification of paddy seeds

The aim of this research was to evaluate the second order statistics texture features - grey level coocurrence matrix and grey level run length using the neural network architectures for cereal grain classification. For the purpose of classifying four paddy (rice) grains, viz. Karjat-6, Karjat-2, Ratnagiri-4 and Ratnagiri-24, an evaluation of the classification accuracy of texture features and neural network was done. To extract the features from the high-resolution images of kernels of four grain types, algorithms were written and these were used as input features for classification. Different feature models were observed for their capability to categorise these cereal grains. For the accurate classification, effect of using different features was studied and the most suitable feature from the feature set was also identified. The Texture-GLCM feature set outperformed the Texture-GLRL feature set in most of the instances of classification. Also the performance of three training functions viz. Levenberg-Marquardt (LM) backpropagation, resilient backpropogation (RP) and scaled conjugate gradient (SCG) training functions was compared and the most reliable training functions was identified from the three functions for accurate classification of four paddy varieties.

Design and Implementation of Invisible and Visible Color Image Watermarkingwith Netbeans IDE

of this paper is to present design and implementation of invisible and visible color image watermarking technique. The algorithms of individual category with implementations in Java Netbeans and test outcomes are presented to focus requirements in visible and invisible techniques. Though Matlab, Scilab, Octave are used for image processing, Net beans IDE is top of line Integrated Development Environment for Java development preferred for platform independent project development in industry and research work. The paper illustrates handling of visible text watermarking, visible logo watermarking and invisible watermarking with Java Netbeans implementation. The main objective of the paper is to focus on design and implementation with help of algorithms with test results presented here, instead of proving quality metrics of individual algorithm implemented in this paper. .

Information Hiding and Recovery using Reversible Embedding

The main objective of this work is to develop data embedding technique that not only embeds secret message, in the form of binary bit stream, to the host image without any auxiliary information or location map, but also extracts that embedded secret message at decoder and restores the original content of host image, which are manipulated after the embedding at encoder. This technique carried out in two phases, embedding and extraction, using min-max approach. This technique reduces extra overhead to embed extra information other than secret message.

Analysis of Blind Image Watermarking Algorithms

This paper presents an overview of blind image watermarking algorithms. In this paper, we analyzed these algorithms for different criteria like robustness, security, and imperceptibility. We also compared pros and cons of using blind method for embedding and extraction of watermark. Most of these algorithms are implemented using MATLAB 2011 and tested on the standard image dataset. We used true color images of size 256 × 256 and binary watermarks of size 32 × 32 for testing. This paper will help watermarking researcher to choose the particular algorithms depending on their need for the application they are working on.

VLSI-Based Data Hiding with Transform Domain Module Using FPGA

In this rapidly growing internet era, researchers are giving more and more attention toward robust, secure, and fast communication channels while hiding sensitive data. The concealment steps can be done through a spatial domain or the transform domain. This paper proposes a data hiding system with an adaptive Very Large-Scale Integration (VLSI) module to enhance the security and robustness of embedded data. The Field Programmable Gate Arrays (FPGA) implementation approach of data hiding technique provides not only pipelined and parallel operations, but also gives the perfect guard against malicious attacks. The proposed algorithm is implemented on a Xilinx Virtex 5 FPGA board. Further, the transform domain technique also optimizes memory space and reduces the execution time through pipelining. The performance of the implemented system is measured using different parameters like resource utilization, Mean Squared Error (MSE), and Peak Signal-to-Noise Ratio (PSNR).