S
Subhasis Chaudhuri
Researcher at Indian Institute of Technology Bombay
Publications - 354
Citations - 9284
Subhasis Chaudhuri is an academic researcher from Indian Institute of Technology Bombay. The author has contributed to research in topics: Image restoration & Haptic technology. The author has an hindex of 44, co-authored 343 publications receiving 8437 citations. Previous affiliations of Subhasis Chaudhuri include Indian Institute of Technology Indore & Indian Institutes of Technology.
Papers
More filters
Journal ArticleDOI
Video-based Vehicle Detection and Classification in Heterogeneous Traffic Conditions using a Novel Kernel Classifier
TL;DR: A combination of interest point detectors and low-level shape detectors as features was found to produce accurate and consistent results in the detection and classification of different categories of vehicles in a heterogeneous traffic video.
Posted Content
PerceptNet: Learning Perceptual Similarity of Haptic Textures in Presence of Unorderable Triplets
TL;DR: In this article, a deep neural network is trained on non-numerical comparisons of triplets of signals, using a novel triplet loss that considers both types of triplet that are easy to order (inequality constraints), as well as those that are unorderable/ambiguous (equality constraints).
Journal ArticleDOI
CILEA-NET: Curriculum-Based Incremental Learning Framework for Remote Sensing Image Classification
TL;DR: In this paper, a curriculum-based incremental learning framework for remote sensing image classification is proposed, which includes new classes in the already trained model to avoid catastrophic forgetting for the old while ensuring improved generalization for the newly added classes.
Journal ArticleDOI
Segmentation and region of interest based image retrieval in low depth of field observations
Rajashekhara,Subhasis Chaudhuri +1 more
TL;DR: The histogram of the local contrast at each pixel is computed and model it as a mixture of two exponential distributions - one for the focused and the other for the defocused region and the parameters of these distributions are estimated using the EM algorithm.
Proceedings ArticleDOI
Photometric stereo under blurred observations
TL;DR: The surface gradients and the albedo are modeled as separate Markov random fields (MRF) and a suitable regularization scheme is used to estimate the different fields as well as the blur parameter.