Mehul S. Raval

Multiresolution Image Fusion: Use of Compressive Sensing and Graph Cuts

In this paper, we propose a new approach for multiresolution fusion, i.e., obtaining a high spatial and spectral resolution multispectral (MS) image using the available low spatial resolution MS and the high spatial resolution Panchromatic (Pan) image. Our approach is based on the idea of compressive sensing (CS) and graph cuts. Assuming that both the MS and Pan images have the same sparseness, a close approximation to the MS image is obtained from the Pan image using the theory of compressive sensing and l1 minimization. We then use regularization framework to obtain fused image. The low resolution (LR) MS image is modeled as degraded and noisy version of fused image in which degradation matrix entires estimated using the close approximation are used. The regularization is carried out by using truncated quadratic smoothness prior which takes care of preservation of the discontinuities in the fused image. A suitable energy function is then formed consisting of data fitting term and prior term. Minimization of the energy function is carried out using a computationally efficient graph cuts optimization to obtain final fused image. Advantage of our approach is that the Pan and MS images need not be registered. This is because, we are not directly using the Pan digital numbers to derive the fused image. The effectiveness of the proposed method is illustrated by conducting experiments on real satellite images. Subjective and quantitative comparison of the proposed method with the state-of-the-art approaches indicates efficacy of our approach.

A Data-Driven Stochastic Approach for Unmixing Hyperspectral Imagery

In this paper, we propose a two-step Bayesian approach to handle the ill-posed nature of the unmixing problem for accurately estimating the abundances. The abundances are dependent on the scene contents and they represent mixing proportions of the endmembers over an area. In this work, a linear mixing model (LMM) is used for the image formation process in order to derive the data term. In the first step, a Huber-Markov random field (HMRF)-based prior distribution is assumed to model the dependencies within the abundances across the spectral space of the data. The threshold used in the HMRF prior is derived from an initial estimate of abundances obtained using the matched filters. This makes the HMRF prior data-driven, i.e., dHMRF. Final abundance maps are obtained in the second step within a maximum a posteriori probability (MAP) framework, and the objective function is optimized using the particle swarm optimization (PSO). Theoretical analysis is carried out to show the effectiveness of the proposed method. The approach is evaluated using the synthetic and real AVIRIS Cuprite data. The proposed method has the following advantages. 1) The estimated abundances are resistant to noise since they are based on an initial estimate that has high signal-to-noise ratio (SNR). 2) The variance in the abundance maps is well preserved since the threshold in the dHMRF is derived from the data.

Multilevel Semi-fragile Watermarking Technique for Improving Biometric Fingerprint System Security

Classical biometric system are prone to compromise at several points. Two of the vulnerable points are : 1. biometric database 2. biometric feature matcher subsystem. We propose a two level watermarking scheme to secure these vulnerable points. Watermark W1 is used for database authentication and made resistive to lossy compression. It is derived using block based singular values (SV’s) of a fingerprint image. W1 establish linkages between watermark and fingerprint image. Watermark W2 is used to secure feature matcher subsystem. It is computed using second and third order moments of the fingerprint image. W2 is made resistive to mild affine transformation and lossy compression to incorporate practical aspects of biometric fingerprint system. The proposed watermarking method not only provides protection to database and matcher subsystem, it also gives security against copy attack.

Image and Video Compression: Fundamentals, Techniques, and Applications

Image and video signals require large transmission bandwidth and storage, leading to high costs. The data must be compressed without a loss or with a small loss of quality. Thus, efficient image and video compression algorithms play a significant role in the storage and transmission of data. Image and Video Compression: Fundamentals, Techniques, and Applications explains the major techniques for image and video compression and demonstrates their practical implementation using MATLAB programs. Designed for students, researchers, and practicing engineers, the book presents both basic principles and real practical applications. In an accessible way, the book covers basic schemes for image and video compression, including lossless techniques and wavelet- and vector quantization-based image compression and digital video compression. The MATLAB programs enable readers to gain hands-on experience with the techniques. The authors provide quality metrics used to evaluate the performance of the compression algorithms. They also introduce the modern technique of compressed sensing, which retains the most important part of the signal while it is being sensed.

Multiresolution image fusion using compressive sensing and graph cuts

Multiresolution fusion refers to the enhancement of low spatial resolution (LR) of multispectral (MS) images to that of panchromatic (Pan) image without compromising on the spectral details. Many of the present day methods for multiresolution fusion require that the Pan and MS images are registered. In this paper we propose a new approach for multiresolution fusion which is based on the theory of compressive sensing and graph cuts. We first estimate a close approximation to the fused image by using the sparseness in the given Pan and MS images. Assuming that they have the same sparseness, the initial estimate of the fused image is obtained as the linear combination of the Pan blocks. The weights in the linear combination are estimated using the l1 minimization by making use of MS and the down sampled Pan image. The final solution is obtained by using a model based approach. The low resolution MS image is modeled as the degraded and noisy version of the fused image in which the degradation matrix entries are estimated by using the initial estimate and the MS image. Since the MS fusion is an ill-posed inverse problem, we use a regularization based approach to obtain the final solution. A truncated quadratic smoothness prior is used for the preservation of the discontinuities in the fused image. A suitable energy function is then formed which consists of data fitting term and the prior term and is minimized using a graph cuts based approach in order to obtain the fused image. The advantage of the proposed method is that it does not require the registration of Pan and MS data. The spectral characteristics are well preserved in the fused image since we are not directly operating on the Pan digital numbers. Effectiveness of the proposed method is illustrated by conducting experiments on synthetic as well as on real satellite images. Quantitative comparison of the proposed method in terms of Erreur Relative Globale Adimensionnelle de Synthase (ERGAS), Correlation Coefficient (CC), Relative Average Spectral Error (RASE) and Spectral Aangle Mapper (SAM) with the state of the art approaches indicate superiority of our approach.

A Secure Steganographic Technique for Blind Steganalysis Resistance

A simple yet effective tactic for secure steganography is proposed in this paper that can resist the blind steganalysis. In this method author derives a matrix based on the image content and thus providing the security. This matrix is used by Quantization Index Modulation (QIM) based encoder and decoder. The embedding location of data is also randomized so as to immobilize the self calibration process. It is shown that detection rate of steganalysis scheme to proposed method is close to arbitrary speculation.

Fuzzy Neural Based Copyright Protection Scheme for Superresolution

Superresolution is an algorithmic approach, for constructing high resolution de-noised image from its low resolution and noisier version. A new method to address the problem of copyright violation for super resolution is presented in this paper. The goal is to design an improved watermarking technique, while minimizing distortion in the super resolved image. The approach employs, fuzzy logic to build the perceptual mask, embeds watermark in the low frequency coefficients for robustness with edge preservation and use neural network at the receiver. Novelty lies in providing copyright protection jointly to the low resolution and the super resolved images. The distortion due to watermark insertion is compensated by: 1. use of fuzzy perceptual mask tuned to human visual system, 2. use of trained neural network estimator during watermark extraction, 3. utilize image degradation model during watermark extraction. Effectiveness of the proposed approach is shown by conducting the experiments on natural images and comparing it with the state of the art techniques.

Identifying Vandalized Regions in Facial Images of Statues for Inpainting

Historical monuments are considered as one of the key aspects for modern communities. Unfortunately, due to a variety of factors the monuments get damaged. One may think of digitally undoing the damage to the monuments by inpainting, a process to fill-in missing regions in an image. A majority of inpainting techniques reported in the literature require manual selection of the regions to be inpainted. In this paper, we propose a novel method that automates the process of identifying the damage to visually dominant regions viz. eyes, nose and lips in face image of statues, for the purpose of inpainting. First, a bilateral symmetry based method is used to identify the eyes, nose and lips. Textons features are then extracted from each of these regions in a multi-resolution framework to characterize both the regular and irregular textures. These textons are matched with those extracted from a training set of true vandalized and non-vandalized regions, in order to classify the region under consideration. If the region is found to be vandalized, the best matching non-vandalized region from the training set is used to inpaint the identified region using the Poisson image editing method. Experiments conducted on face images of statues downloaded from the Internet, give promising results.

Reversible watermarking technique to enhance security of a biometric authentication system

For every biometric template protecting technique, non-reversibility, accuracy, and revocability are essential features. Several template protecting techniques like bio-hash or biometric crypto system are used to transform raw biometric features into alternative form known as protected template [2]. As the protected templates are non-reversible, biometric verification is done in a transform domain. Tampered or stolen protected template may cause false validation; therefore its authentication in the database is essential. Reversible watermarking technique provides one such effective mechanism. Watermark protected templates are stored in the database at the time of its enrollment. During verification phase, incoming query template is compared with many database templates until a match is established. This verification technique increase complexity and burden on a biometric authentication system. In this paper, we propose a tag based template searching in reversible watermarking technique to check authenticity and reduce burden on biometric authentication system. In the proposal, rotation, scale and translation (RST) invariant features of biometric image are used for tagging the data. Watermark reversibility in the proposed method ensures that its presence do not affect native biometric authentication. Moreover presence of watermark in the biometric template provides security against replay attack.

Secure and robust watermarking technique

Digital image-watermarking can be casted as an optimization problem with solution satisfying fidelity, robustness and security constraints. Most of discrete wavelet transform (DWT) and singular value decomposition (SVD) based approaches highlights tradeoff between fidelity and robustness with lesser discussion on security. In this paper, authors propose a novel watermarking approach based on DWT and SVD to satisfy all the three constraints. In this approach watermark is customized using singular values (SV) computed on DWT sub-band of cover image. Unlike other algorithms, watermark is not inserted into SVs of DWT sub-band. While doing singular value decomposition on cover image, SVs of watermark replaces the SVs of the DWT sub-band. Signatures of orthogonal matrices associated with SVs of watermark are then computed and inserted into third level LL and HH band of cover image. Before watermark extraction these signatures can be used for authentication of the orthogonal matrices. Signature authentication improves security of the algorithm. Experimental results are provided to show that new watermarking method performs well under all three constraints.