Material Science and Technology
Deep Learning Based Low Light Image Enhancement for Improved Visibility
Challenges abound in capturing and processing images under low light conditions, resulting in diminished image quality characterized by reduced visibility and heightened noise levels. Conventional methods for enhancing low light images typically involve manual image processing techniques like histogram equalization, contrast stretching, and noise reduction filters. While these approaches may offer some enhancement, they often fall short in achieving visually pleasing and authentic results. Their lack of adaptability and limited capacity to discern intricate patterns from data renders them less effective in handling diverse low light scenarios. The imperative for an advanced low light image enhancement technique stems from the extensive utilization of imaging devices in low light environments across various sectors such as surveillance, automotive, and photography. These industries heavily rely on cameras to capture images in challenging lighting conditions. By enhancing visibility and overall image quality in low light settings, the accuracy and dependability of image-based systems can be significantly bolstered. Hence, there is a pressing need for an intelligent approach capable of learning and adapting from data to overcome the shortcomings of traditional methods. In recent years, deep learning has emerged as a promising solution for numerous computer vision tasks, including image enhancement. This project endeavours to explore and propose a deep learning-based approach to mitigate the challenges associated with low light image enhancement, thereby enhancing visibility. By leveraging deep learning, this approach surmounts the constraints of conventional techniques by autonomously capturing intricate patterns and features within low light images. This adaptability empowers the model to generalize effectively across various low light scenarios, resulting in enhancements that are visually appealing and true to life.
Keywords: Low Light Image Enhancement, Deep Learning, Image Enhancement, Low Light Vision, Dark Image Processing, Low light image restoration, neural networks for low light, enhancing visibility in low light image, denoising, image dehazing, noise reduction.
10.10543/f0299.2024.
How to cite
1Mohammed Talha Tabrez,2Dr. R. Santoshkumar.(2024)Deep Learning Based Low Light Image Enhancement for Improved Visibility.mst,53-57.Retrieved from /mst/article_view.php?ctype=a&id=42347
Issue
Vol.23 No.04 APRIL
Section
Articles
Search
