Date of Submission

5-6-2025

Date of Award

1-13-2026

Institute Name (Publisher)

Indian Statistical Institute

Document Type

Doctoral Thesis

Degree Name

Doctor of Philosophy

Subject Name

Computer Science

Department

Computer Vision and Pattern Recognition Unit (CVPR-Kolkata)

Supervisor

Palit, Sarbani

Abstract (Summary of the Work)

This thesis investigates computational models and methodologies for restoring images degraded by challenging environmental conditions such as haze and underwater environments. It further explores the analysis and estimation of particulate matter (PM) concentration from both day and night scenes under varying weather conditions, using degraded visual data as a primary input. Each environment introduces distinct forms of visual degradation, making image restoration a critical challenge that directly impacts applications including visibility enhancement, weather analysis, particulate concentration estimation, and object detection. By addressing these challenges, this thesis aims to develop adaptable, data-driven solutions that enhance image clarity and improve information extraction across diverse environmental scenarios, thereby enabling more accurate interpretation and utilization of visual data

Control Number

TH672

DOI

https://dspace.isical.ac.in/items/7b967dfb-dc73-44f9-9d13-3c2dae516e0b

DSpace Identifier

http://hdl.handle.net/10263/7643

Download

Share

COinS