• Publications
  • Influence
Hyperspectral Image Denoising Using Spatio-Spectral Total Variation
TLDR
This letter introduces a hyperspectral denoising algorithm based on spatio-spectral total variation that demonstrates the superiority of the proposed algorithm in terms of peak signal-to-noise ratio, structural similarity, and the visual quality.
Fast group sparse classification
  • A. Majumdar, R. Ward
  • Computer Science
    Canadian Journal of Electrical and Computer…
  • 23 January 2009
TLDR
This work shows that the FGSC has nearly the same accuracy (at 95% confidence level) as the GSC, but with much faster computational speed (nearly two orders of magnitude), and is robust to dimensionality reduction via random projection.
Classification via group sparsity promoting regularization
  • A. Majumdar, R. Ward
  • Computer Science
    IEEE International Conference on Acoustics…
  • 19 April 2009
TLDR
Two alternate regularization methods are proposed, Elastic Net and Sum-Over-l2-norm, which favor the selection of multiple correlated training samples to represent the test sample.
Detecting Silicone Mask-Based Presentation Attack via Deep Dictionary Learning
TLDR
This paper introduces the first-of-its-kind silicone mask attack database which contains 130 real and attacked videos to facilitate research in developing presentation attack detection algorithms for this challenging scenario.
Face Recognition by Curvelet Based Feature Extraction
TLDR
This paper proposes a new method for face recognition based on a multiresolution analysis tool called Digital Curvelet Transform, which takes the curvelet transforms of each of the original image and its quantized 4 bit and 2 bit representations to act as the feature set for classification.
Compressed sensing of color images
Single-sensor multi-spectral image demosaicing algorithm using learned interpolation weights
TLDR
A multi-spectral filter array design is proposed to capture multiple bands using the single-sensor architecture to help in reducing the cost and size of multi-Spectral cameras while simultaneously eliminating the image registration problem.
Pseudo-Fisherface method for single image per person face recognition
  • A. Majumdar, R. Ward
  • Computer Science
    IEEE International Conference on Acoustics…
  • 12 May 2008
TLDR
The problem of recognizing a face from a single sample available in a stored dataset is addressed by using the Fisherface method on a generic dataset and the recognition scheme is extended to multiscale transform domains like wavelet, curvelet and contourlet.
...
...