Low Light Image Enhancement (LLIE) – Nakshatra Drishti Deep Learning Model

Nitesh Kumar; Abhimanyu

doi:10.36948/ijfmr.2024.v06i02.16479

Low Light Image Enhancement (LLIE) – Nakshatra Drishti Deep Learning Model

Author(s)	Nitesh Kumar, Abhimanyu
Country	India
Abstract	Images when captured under low light or insufficient illumination and limited exposure time or in darkness or under inevitable environmental or technical constraints are difficult to recognize and becomes challenging to derive valuable intelligence out of it. The quality of such images are badly degraded due to noise, buried scene content, inaccurate color and contrast information thereby posing significant difficulty in performing various analysis operation upon it like object detection , change detection, tracking, face recognition, disguise recognition. Figure 1 shows some examples of the degradations induced by images captured under low light condition. To resolve the problem this problem we propose a highly effective supervised learning based convolutional neural network model dubbed Nakshatra-Drishti Low-light image enhancement (LLIE) deep learning model that produces powerful results on enhancing low light image, video and real-time live camera feed all integrated under a single umbrella. Our deep learning model has been supervised and trained on paired dataset and has been extensively tested on various benchmarks and has demonstrated outstanding results. A set of carefully formulated loss functions to measure enhancement quality and optimizing the learning process of deep learning model has been adopted alongwith noise function to remove various types of noises that degrades the image quality under dark light condition. Our user-friendly web-based software application aims at improving the perception or interpretability of an image captured in an environment with poor illumination on which further Artificial intelligence analysis can be effectively performed that helps in better decision making and reducing OODA loop.
Keywords	LLIE , Nakshatra-Drishti deep learning model , web based integrated software application
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 6, Issue 2, March-April 2024
Published On	2024-04-05
Cite This	Low Light Image Enhancement (LLIE) – Nakshatra Drishti Deep Learning Model - Nitesh Kumar, Abhimanyu - IJFMR Volume 6, Issue 2, March-April 2024. DOI 10.36948/ijfmr.2024.v06i02.16479
DOI	https://doi.org/10.36948/ijfmr.2024.v06i02.16479
Short DOI	https://doi.org/gtp8jd

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Copyright Permission Form and Undertaking Form Cover Page Vol 6 Isu 2 Cover Page Vol 6 Isu 1 Cover Page Vol 5 Isu 6 Research Paper Format

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-5948-55	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Low Light Image Enhancement (LLIE) – Nakshatra Drishti Deep Learning Model

Share this