Nakshatra-Drishti: A Supervised Learning Approach for Low Light Image Enhancement Using Convolutional Neural Networks

Abstract

Images captured under low-light conditions pose significant challenges for subsequent analysis due to degradation in quality, including noise, loss of scene content, inaccurate colour, and contrast information. In this paper, we propose a supervised learning-based convolutional neural network (CNN) model, Nakshatra-Drishti, specifically designed for enhancing low-light images, videos, and real-time camera feeds. The model is trained on paired datasets and extensively evaluated on various benchmarks, demonstrating remarkable results. We also introduce a user-friendly web-based software application that enhances image perception in poorly illuminated environments, facilitating more effective artificial intelligence analysis and decision-making processes.