Hemant Kumar Aggarwal

• Indraprastha Institute of Information Technology Delhi

In this work we propose a technique to remove sparse impulse noise from hyperspectral images. Our algorithm accounts for the spatial redundancy and spectral correlation of such images. The proposed method is based on the recently introduced Blind Compressed Sensing (BCS) framework, i.e. it empirically learns the spatial and spectral sparsifying dic...

This work proposes a new framework for deep learning that has been particularly tailored for hyperspectral image classification. We learn multiple levels of dictionaries in a robust fashion. The last layer is discriminative that learns a linear classifier. The training proceeds greedily, at a time a single level of dictionary is learnt and the coef...

This work proposes a new image analysis tool called Label Consistent Transform Learning (LCTL). Transform learning is a recent unsupervised representation learning approach; we add supervision by incorporating a label consistency constraint. The proposed technique is especially suited for hyper-spectral image classification problems owing to its ab...

This letter proposes a new image analysis tool called label-consistent transform learning. Transform learning is a recent unsupervised representation learning approach; we add supervision by incorporating a label consistency constraint. The proposed technique is especially suited for hyperspectral image classification problems owing to its ability...

This paper proposes a new framework for deep learning that has been particularly tailored for hyperspectral image classification. We learn multiple levels of dictionaries in a robust fashion. The last layer is discriminative that learns a linear classifier. The training proceeds greedily; at a time, a single level of dictionary is learned and the c...

In diffraction grating, at times, there are defective pixels on the focal plane array; this results in horizontal lines of corrupted pixels in some channels. Since only a few such pixels exist, the corruption/noise is sparse. Studies on sparse noise removal from hyperspectral noise are parsimonious. To remove such sparse noise, a prior work exploit...

Hyperspectral unmixing is the process of estimating constituent endmembers and their fractional abundances present at each pixel in a hyperspectral image. A hyperspectral image is often corrupted by several kinds of noise. This work addresses the hyperspectral unmixing problem in a general scenario that considers the presence of mixed noise. The un...

This letter introduces a hyperspectral denoising algorithm based on spatio-spectral total variation. The denoising problem has been formulated as a mixed noise reduction problem. A general noise model has been considered which accounts for not only Gaussian noise but also sparse noise. The inherent structure of hyperspectral images has been exploit...

This paper addresses the problem of impulse denoising from hyper-spectral images. Impulse noise is sparse; removing impulse noise requires minimizing an l1-norm data fidelity term. Prior studies have exploited the intra-band spatial correlation (leading to sparsity in transform domain) and inter-band spectral-correlation (joint-sparsity) of hyper-s...

In this work we propose a technique to remove sparse impulse noise from hyperspectral images. Our algorithm accounts for the spatial redundancy and spectral correlation of such images. The proposed method is based on the recently introduced Blind Compressed Sensing (BCS) framework, i.e. it empirically learns the spatial and spectral sparsifying dic...

This work proposes techniques for demosaicing multi-spectral images obtained from a single sensor architecture. This is a new problem. Compressed Sensing (CS) based formulations can recover images by exploiting the sparsity of the images in the wavelet domain. In this work, we improve upon existing techniques by accounting for the hierarchical (tre...

This paper proposes a technique for reducing impulse noise from corrupted hyperspectral images. We exploit the spatiospectral correlation present in hyperspectral images to sparsify the datacube. Since impulse noise is sparse, denoising is framed as an ℓ1-norm regularized ℓ1-norm data fidelity minimization problem. We derive an efficient split Breg...

This work proposes generalized synthesis and analysis prior algorithms using the split-Bregman technique for applications in impulse noise reduction. Impulse denoising is formulated as minimizing a Lp-regularized Lq-norm data mismatch term. The Lq-norm mismatch arises owing to the fact that the noise is sparse. The Lp-norm exploits the prior inform...

Multi-spectral images capture more information about a scene as compared to RGB images and have various scientific applications. But the high resolution multi-spectral cameras are very expensive which limits their wide applicability as compared to normal digital RGB cameras. In this paper a multi-spectral filter array design is proposed to capture...

The Kaczmarz algorithm is popular for iteratively solving an overdetermined system of linear equations. However the traditional Kaczmarz algorithm has a linear convergence rate,a randomized version of the Kaczmarz algorithm was shown to converge exponentially. Recently an algorithm for finding sparse solution to a linear system of equations has bee...

A generic-filter array design have been proposed to capture multi-spectral images using hypothetical single-sensor multi-spectral cameras. The design idea is based on uniform sampling of intensity values from each band irrespective of spectral properties of any particular band. A reconstruction technique have also been proposed to linearly interpol...

We have proposed a method by which compact and low-cost multi-spectral cameras can be designed based on the concept of single-sensor cameras. A filter pattern have been proposed to capture intensity values from multiple bands by using single-sensor. Our approach is based on representing central pixel in a window as a linear combination of neighbori...