Manjunath V. Joshi

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.

Auto-inpainting heritage scenes: a complete framework for detecting and infilling cracks in images and videos with quantitative assessment

The need for preservation of cultural heritage has necessitated the research on digitally repairing the photographs of damaged monuments. In this paper, we first propose a technique for automatically detecting the cracked regions in photographs of monuments. Unlike the usual practice of manually selecting the mask for inpainting, the detected regions are supplied to an inpainting algorithm. Thus, the process of digitally repairing the cracked regions that physical objects have, using inpainting, is completely automated. The detection of cracked regions is based on comparison of patches, for which we use a measure derived from the edit distance, which is a popular string metric used in the area of text mining. Further, we extend this method to perform inpainting of video frames by making use of the scale-invariant feature transform and homography. We consider the camera to move while capturing video of the heritage site, as such videos are typically captured by novices, hobbyists and tourists. Finally, we also propose a video quality measure to quantify the temporal consistency of the inpainted video. Experiments have been carried out on videos captured from the heritage site at Hampi, India.

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.

A learning based approach for dense stereo matching with IGMRF prior

In this paper, we propose a learning based approach for solving the problem of dense stereo matching problem using edge preserving regularization prior. Given the test stereo pair and a training database consisting of disparity maps estimated using multiple views stereo images and their corresponding ground truths, we obtain the disparity map for the test set. We first obtain an initial disparity estimate by learning the disparities from the available database. A new learning based approach is proposed for obtaining the initial estimate that uses the estimated and the true disparities. Since the disparity estimation is an ill posed problem, we obtain the final disparity map using a regularization framework. The prior model for the disparity map is chosen as an Inhomogeneous Gaussian Markov Random Field (IGMRF). Assuming that the spatial variations among the disparity values captured in an initial estimate correspond to the variations in true disparities, we obtain the IGMRF parameters at every pixel location using the initial estimate. A graph cuts based method is used to optimize the energy function in order to obtain the global minimum. Experimental results on the standard dataset demonstrate the effectiveness of the proposed approach.

Digital Heritage Reconstruction Using Super-resolution and Inpainting

Abstract Heritage sites across the world have witnessed a number of natural calamities, sabotage and damage from visitors, resulting in their present ruined condition. Many sites are now restricted to reduce the risk of further damage. Yet these masterpieces are significant cultural icons and critical markers of past civilizations that future generations need to see. A digitally reconstructed heritage site could diminish further harm by using immersive navigation or walkthrough systems for virtual environments. An exciting key element for the viewer is observing fine details of the historic work and viewing monuments in their undamaged form. This book presents image super-resolution methods and techniques for automatically detecting and inpainting damaged regions in heritage monuments, in order to provide an enhanced visual experience. The book presents techniques to obtain higher resolution photographs of the digitally reconstructed monuments, and the resulting images can serve as input to immersive walk...

Image Denoising using Tight-Frame Dual-Tree Complex Wavelet Transform

In this paper, we propose a new approach to design the 1D biorthogonal filters of dual-tree complex wavelet transform (DTCWT) in order to have almost tight-frame characteristics. The proposed approach involves use of triplet halfband filter bank (THFB) and optimization of free variables obtained using factorization of generalized halfband polynomial (GHBP) to design the filters of two trees of DTCWT. The wavelet functions associated with these trees exhibit better analyticity in terms of qualitative and quantitative measures. Transform-based image denoising using the proposed filters shows comparable performance to the best performing orthogonal wavelet filters.

Design of Biorthogonal Wavelet Filters of DTCWT Using Factorization of Halfband Polynomials

In this paper, we propose a new approach for designing the biorthogonal wavelet filters (BWFs) of Dual-Tree Complex Wavelet Transform (DTCWT). Proposed approach provides an effective way to handle the frequency response characteristics of these filters. This is done by optimizing the free variables obtained using factorization of generalized halfband polynomial (GHBP). The designed filters using proposed approach have better frequency response characteristics than those obtained by using binomial spectral factorization approach. Also, their associated wavelets show improved analyticity in terms of qualitative and quantitative measures. Transform-based image denoising using the proposed filters shows better visual as well as quantitative performance.

A learned sparseness and IGMRF-based regularization framework for dense disparity estimation using unsupervised feature learning

In this work, we propose a new approach for dense disparity estimation in a global energy minimization framework. We propose to use a feature matching cost which is defined using the learned hierarchical features of given left and right stereo images and we combine it with the pixel-based intensity matching cost in our energy function. Hierarchical features are learned using the deep deconvolutional network which is trained in an unsupervised way using a database consisting of large number of stereo images. In order to perform the regularization, we propose to use the inhomogeneous Gaussian Markov random field (IGMRF) and sparsity priors in our energy function. A sparse autoencoder-based approach is proposed for learning and inferring the sparse representation of disparities. The IGMRF prior captures the smoothness as well as preserves sharp discontinuities while the sparsity prior captures the sparseness in the disparity map. Finally, an iterative two-phase algorithm is proposed to estimate the dense disparity map where in phase one, sparse representation of disparities are inferred from the trained sparse autoencoder, and IGMRF parameters are computed, keeping the disparity map fixed and in phase two, the disparity map is refined by minimizing the energy function using graph cuts, with other parameters fixed. Experimental results on the Middlebury stereo benchmarks demonstrate the effectiveness of the proposed approach.

Dense disparity estimation based on feature matching and IGMRF regularization

In this paper, we propose a new approach for dense disparity estimation in a global energy minimization framework. We combine the feature matching cost defined using the learned hierarchical features of given left and right stereo images, with the pixel-based intensity matching cost to form the data term. The features are learned in an unsupervised way using the deep deconvolutional network. Our regularization term consists of an inhomogeneous Gaussian markov random field (IGMRF) prior that captures the smoothness as well as preserves sharp discontinuities in the disparity map. An iterative two phase algorithm is proposed to minimize the energy function in order to estimate the dense disparity map. In phase one, IGMRF parameters are computed, keeping the disparity map fixed, and in phase two, the disparity map is refined by minimizing the energy function using graph cuts, with other parameters fixed. Experimental results on the Middlebury stereo benchmarks demonstrate the effectiveness of the proposed approach.

A regularization framework for stereo matching using IGMRF prior and sparseness learned from autoencoder

In this work, we propose to use an Inhomogeneous Gaussian Markov Random Field (IGMRF) and sparsity based priors in a regularization framework in order to estimate the dense disparity map. The IGMRF prior captures the smoothness as well as preserves sharp discontinuities and the sparsity prior captures the sparseness in the disparity map. We present a sparse autoencoder based approach for learning and inferring the sparse representation of disparities. An iterative two phase algorithm is proposed to solve our energy minimization problem. Experimental results on the standard datasets demonstrate the effectiveness of the proposed approach.