K
Kaushik Mitra
Researcher at Indian Institute of Technology Madras
Publications - 101
Citations - 1498
Kaushik Mitra is an academic researcher from Indian Institute of Technology Madras. The author has contributed to research in topics: Computer science & Qubit. The author has an hindex of 18, co-authored 91 publications receiving 1173 citations. Previous affiliations of Kaushik Mitra include University of Maryland, College Park & Rice University.
Papers
More filters
Proceedings ArticleDOI
Light field denoising, light field superresolution and stereo camera based refocussing using a GMM light field patch prior
TL;DR: This work proposes a patch based approach, where it is shown that the light field patches with the same disparity value lie on a low-dimensional subspace and that the dimensionality of such subspaces varies quadratically with the disparity value.
Proceedings ArticleDOI
Improving resolution and depth-of-field of light field cameras using a hybrid imaging system
TL;DR: This work proposes a simple patch-based algorithm to super-resolve the low-resolution views of the light field using the high- resolution patches captured using a high-resolution SLR camera.
Book ChapterDOI
Joint Optic Disc and Cup Segmentation Using Fully Convolutional and Adversarial Networks
TL;DR: This work proposes a novel improved architecture building upon FCNs by using the concept of residual learning and learns a mapping between the retinal images and the corresponding segmentation map using fully convolutional and adversarial networks.
Proceedings ArticleDOI
A hierarchical approach for human age estimation
TL;DR: This work proposes a hierarchical approach to age estimation from face images, where face images are divided into various age groups and then a separate regression model is learned for each group.
Journal ArticleDOI
Blur and Illumination Robust Face Recognition via Set-Theoretic Characterization
TL;DR: It is shown that the set of all images obtained by blurring a given image forms a convex set, and a blur and illumination-robust algorithm is proposed whose main step involves solving simple convex optimization problems.