M. Vinay
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
M. Vinay has a total of 60 co-authors. Here are the top co-authors by number of shared publications:
- Jayapriya Jayapal
Christ University
15 shared publications - S. Deepa
Christ University
4 shared publications - Blerta Prevalla Etemi
Rochester Institute of Technology
2 shared publications Blessy Louis
Christ University, India
2 shared publications- Debabrata Samanta
Rochester Institute of Technology
2 shared publications - Kokilavani Thangaraj
Christ University
2 shared publications
Latest Publications
- Open Access
- 24 July 2026
- Published by Elsevier in SSRN Electronic Journal
A Hybrid Non-local Ensemble (HNE) Framework for Robust Image Denoising under Uncertain Noise Conditions
With the rapid growth of image data across domains such as remote sensing, medical imaging, healthcare, and social media, there is an increasing need for robust image denoising techniques that can handle uncertain and varying noise conditions. While existing denoising methods are effective under controlled settings, many rely on fixed filtering strategies, prior assumptions, or training-dependent models that struggle to generalise to unknown noise environments. Consequently, they often fail to suppress noise effectively while preserving structural details in complex real-world scenarios.This paper proposes a Hybrid Non-local Ensemble (HNE) framework that integrates multi-view geometric transformations, non-local denoising, robust ensemble fusion, and local contrast restoration. The framework generates multiple transformed views of a noisy image to capture structural information from different orientations. Each transformed image is denoised independently using a non-local transform-domain filtering approach. The denoised outputs are then combined using a trimmed mean strategy to reduce outlier effects and produce a stable estimate. Finally, local contrast restoration enhances structural details based on local image statistics.Experimental results demonstrate that the proposed training-free framework outperforms TV, BM3D, NL-Ridge, and Plug-and-Play BM3D, achieving an SSIM of 0.9557 and a PSNR of 38.2633 dB.
- 24 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Hybrid Non-local Ensemble (HNE) Framework for Robust Image Denoising under Uncertain Noise Conditions
With the rapid growth of image data across domains such as remote sensing, medical imaging, healthcare, and social media, there is an increasing need for robust image denoising techniques that can handle uncertain and varying noise conditions. While existing denoising methods are effective under controlled settings, many rely on fixed filtering strategies, prior assumptions, or training-dependent models that struggle to generalise to unknown noise environments. Consequently, they often fail to suppress noise effectively while preserving structural details in complex real-world scenarios.This paper proposes a Hybrid Non-local Ensemble (HNE) framework that integrates multi-view geometric transformations, non-local denoising, robust ensemble fusion, and local contrast restoration. The framework generates multiple transformed views of a noisy image to capture structural information from different orientations. Each transformed image is denoised independently using a non-local transform-domain filtering approach. The denoised outputs are then combined using a trimmed mean strategy to reduce outlier effects and produce a stable estimate. Finally, local contrast restoration enhances structural details based on local image statistics.Experimental results demonstrate that the proposed training-free framework outperforms TV, BM3D, NL-Ridge, and Plug-and-Play BM3D, achieving an SSIM of 0.9557 and a PSNR of 38.2633 dB.
- 2 July 2026
- Published by Springer Nature
- p. 43-53
Early Detection of Mental Health Disorders: A Review of Innovations in AI-Driven Tools
- 2 July 2026
- Published by Springer Nature
- p. 43-53
Early Detection of Mental Health Disorders: A Review of Innovations in AI-Driven Tools
- 30 June 2026
- Published by IGI Global Scientific Publishing
- p. 191-222
An Explainable AI Architecture for Structured Visual Evidence Reasoning in Digital Forensic Investigations
The use of artificial intelligence in forensic investigations has improved the accuracy of evidence discovery. Nevertheless, most systems available now are primarily concerned with task-related automation like object detection and anomaly recognition. The classification results are not enough to provide meaningful investigative thinking. The structured interpretation is needed, and there must be explainable decision support. This chapter suggests a multidisciplinary AI-based approach to cogitating with visual forensic evidence in computerized research inquiries. The framework builds from the crime scene images and produces ranked hypotheses of reviews using an interpretable reasoning pipeline into structured representations. It combines the process of visual evidence detection, forensic pattern modeling, and semantic evidence representation into a single architecture. This strategy focuses on transparency, explicability, and confidence estimation to provide reliable AI-aided forensic analysis.
- 30 June 2026
- Published by IGI Global Scientific Publishing
- p. 191-222
An Explainable AI Architecture for Structured Visual Evidence Reasoning in Digital Forensic Investigations
The use of artificial intelligence in forensic investigations has improved the accuracy of evidence discovery. Nevertheless, most systems available now are primarily concerned with task-related automation like object detection and anomaly recognition. The classification results are not enough to provide meaningful investigative thinking. The structured interpretation is needed, and there must be explainable decision support. This chapter suggests a multidisciplinary AI-based approach to cogitating with visual forensic evidence in computerized research inquiries. The framework builds from the crime scene images and produces ranked hypotheses of reviews using an interpretable reasoning pipeline into structured representations. It combines the process of visual evidence detection, forensic pattern modeling, and semantic evidence representation into a single architecture. This strategy focuses on transparency, explicability, and confidence estimation to provide reliable AI-aided forensic analysis.
- 9 March 2026
- Published by Springer Nature in SN Computer Science
- Vol. 7 (3) , 263
Automated Classification of Medicinal Plants Using Lightweight Deep Learning and Transfer Learning
- 9 March 2026
- Published by Springer Nature in SN Computer Science
- Vol. 7 (3) , 263
Automated Classification of Medicinal Plants Using Lightweight Deep Learning and Transfer Learning
- 2 January 2026
- Published by Springer Nature
- p. 21-34
Navigating the Complexities of Indoor Air Quality: Critical Analysis of Key Pollutants and Monitoring Sites
- 2 January 2026
- Published by Springer Nature
- p. 21-34
Navigating the Complexities of Indoor Air Quality: Critical Analysis of Key Pollutants and Monitoring Sites
- 2 January 2026
- Published by Springer Nature
- p. 39-52
Bridging Signs to Sentences: Enhancing Sign Language Interpretation
- 2 January 2026
- Published by Springer Nature
- p. 39-52
Bridging Signs to Sentences: Enhancing Sign Language Interpretation
- Open Access
Enhancing image compression through a novel Structural Fidelity Weighted Ensemble (SFWE) model
- 19 October 2025
- Published by Springer Nature
- p. 1-10
Smart Finances: A Web-Based System for Personalized Financial Management
- 19 October 2025
- Published by Springer Nature
- p. 1-10
Smart Finances: A Web-Based System for Personalized Financial Management
- 1 October 2025
- Published by Springer Nature
- p. 259-269
Unveiling Sentiment Trends: An Approach to Utilize Machine Learning in Studying User Activities on New Social Applications
- 1 October 2025
- Published by Springer Nature
- p. 259-269
Unveiling Sentiment Trends: An Approach to Utilize Machine Learning in Studying User Activities on New Social Applications
- 30 August 2025
- Published by Springer Nature
- p. 135-147
Technological Innovation in Digital Payments: A Survey of Trends, Challenges, and Opportunities
- 30 August 2025
- Published by Springer Nature
- p. 135-147
Technological Innovation in Digital Payments: A Survey of Trends, Challenges, and Opportunities