M.N.Srikanta Swamy

Professor

Concordia University

Canada

Research Interests

Explore related searches

Professors in Canada Professors in Medical Imaging Medical Imaging professors in Canada

Contact this professor

ORCID

Google Scholar

About

Professor M.N. Srikanta Swamy is a faculty member at Concordia University in Canada. His research encompasses various aspects of deep learning and image processing, with recent publications focusing on convolutional neural networks, enhancement techniques for images, and applications in medical imaging. His work also includes exploring kernel machines and advanced methods for image denoising and super resolution.

M.N.Srikanta Swamy

Research Interests

Explore related searches

Contact this professor

About

Articles (16)

A Lightweight Deep Convolutional Neural Network Extracting Local and Global Contextual Features for the Classification of Alzheimer's Disease Using Structural MRI

ACLI: A CNN Pruning Framework Leveraging Adjacent Convolutional Layer Interdependence and $\gamma$-Weakly Submodularity

UADiff: A Deep Underwater Image Enhancement Network Using Generative Diffusion Prior and Uncertainty-Aware Learning

A Very Fast and Robust Method for Refinement of Putative Matches of Features in MIS Images for Robotic-Assisted Surgery

DMML: Deep Multi-Prior and Multi-Discriminator Learning for Underwater Image Enhancement

Exploring Kernel Machines and Support Vector Machines: Principles, Techniques, and Future Directions

Low-rank with sparsity constraints for image denoising

Single image denoising via multi-scale weighted group sparse coding

FPNet: A Deep Light-Weight Interpretable Neural Network Using Forward Prediction Filtering for Efficient Single Image Super Resolution

SRNMSM: A Deep Light-Weight Image Super Resolution Network Using Multi-Scale Spatial and Morphological Feature Generating Residual Blocks

A Low-Complexity Modified ThiNet Algorithm for Pruning Convolutional Neural Networks

Ultralight-weight Three-Prior Convolutional Neural Network for Single Image Super Resolution

SRNHARB: A deep light-weight image super resolution network using hybrid activation residual blocks

An improved scheme for multifeature-based foreground detection using challenging conditions

UPDResNN: A Deep Light-Weight Image Upsampling and Deblurring Residual Neural Network

GAN based efficient foreground extraction and HGWOSA based optimization for video synopsis generation

Collaborators (1)

Kim Khoa Nguyen

How do I reach out?

Meet Kite AI