 |
International Journal for Research Trends and Innovation
International Peer Reviewed & Refereed Journals, Open Access Journal
ISSN Approved Journal No: 2456-3315 | Impact factor: 8.14 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
|
Issue: March 2026
Volume 11 | Issue 3
Review Result and Publication of Paper within : 2-3 days
Click Here For more DetailsFor Authors
Forms / Download
Published Issue Details
Editorial Board
Other IMP Links
Facts & Figure
Impact Factor : 8.14
Issue per Year : 12
Volume Published : 11
Issue Published : 118
Article Submitted : 21604
Article Published : 8531
Total Authors : 22438
Total Reviewer : 805
Total Countries : 159
Indexing Partner
Licence
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
|
Published Paper Details
|
|
| Paper Title: | Image Restoration using Super Resolution Generative Adversarial Network |
| Authors Name: | T.Kusuma , Sureshbabu Dhanalakshmi , T.Bhavana , Mr.V.P.Manikandan , Mr.A.Venkatesan |
| Download E-Certificate: | Download |
| Author Reg. ID: |
IJRTI_201687
|
| Published Paper Id: | IJRTI2503240 |
| Published In: | Volume 10 Issue 3, March-2025 |
| DOI: | |
| Abstract: | It can be challenging to extract valuable information from photographs taken with low-resolution cameras or images that have been deteriorated by noise, blur, or other factors. The ability of conventional image restoration methods to return photos to their original quality is constrained. Thus, there is a need for more sophisticated methods that can improve the quality of restored photos. The goal of this project is to create an image restoration model that can improve low-resolution or degraded photos utilizing post-processing methods along with SRGAN. The project's objective is to build the SRGAN model followed by post-processing methods for image restoration. This project will also investigate how various characteristics, like the size of the training dataset, the number of layers in the network, and the post-processing methods employed, affect the performance of the model. The initiative will aid in the creation of more sophisticated picture restoration methods that may be applied to a variety of situations, including surveillance, remote sensing, and medical imaging. SRGAN with two models, where these two separate models are pitted against each other simultaneously during training: a generator and discriminator model both attempt to outsmart one another. The Generator takes input data containing a low-resolution version of an image, then up samples it which outputs a high-resolution image. The Discriminator attempts to distinguish between real/fake output generated by G so as D's success rate progresses more accurate results are achieved through feedback loops affecting G till desired accuracy goals have been set. During the training, A high-resolution image (HR) is down sampled to a low-resolution image (LR). A GAN generator up samples LR images to super-resolution images (SR). We use a discriminator to distinguish the HR images and backpropagate the GAN loss to train the discriminator and the generator. This advanced Machine Learning technique uses both generators and discriminators and also uses the pre trained weights called as VGG19 in order to discern between high-resolution original photos and their generated counterparts. As opposed to simply upscaling blurred photos often seen with conventional methods like nearest neighbour interpolation, these AI models produce results that are much closer to the quality as perceived by humans making them perfect for applications such as picture enhancement or dealing with poor digital zoom performance due lack of details produced when enlarging digital images artificially. |
| Keywords: | SRGAN, Image restoration, SRCNN, Generator, Discriminator, VGG19, Unsharp masking, Contrast stretching. |
| Cite Article: | "Image Restoration using Super Resolution Generative Adversarial Network", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2455-2631, Vol.10, Issue 3, page no.c272-c277, March-2025, Available :http://www.ijrti.org/papers/IJRTI2503240.pdf |
| Downloads: | 000539 |
| ISSN: |
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016 An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator |
| Publication Details: |
Published Paper ID: IJRTI2503240
Registration ID:201687
Published In: Volume 10 Issue 3, March-2025
DOI (Digital Object Identifier):
Page No: c272-c277 Country: Chittoor, Andhra Pradesh, India Research Area: Engineering Publisher : IJ Publication Published Paper URL : https://www.ijrti.org/viewpaperforall?paper=IJRTI2503240 Published Paper PDF: https://www.ijrti.org/papers/IJRTI2503240 |
| Share Article: | |
|
Click Here to Download This Article |
|
| Article Preview | |
|
|
|
Major Indexing from www.ijrti.org
| Google Scholar | ResearcherID Thomson Reuters | Mendeley : reference manager | Academia.edu |
| arXiv.org : cornell university library | Research Gate | CiteSeerX | DOAJ : Directory of Open Access Journals |
| DRJI | Index Copernicus International | Scribd | DocStoc |
ISSN Details
 |
 |
|
ISSN: 2456-3315
Impact Factor: 8.14 and ISSN APPROVED,
Journal Starting Year (ESTD) : 2016
DOI (A digital object identifier)
| Providing A digital object identifier by DOI.ONE How to Get DOI? |
Conference
Open Access License Policy
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Important Details
Join RMS/Earn 300
WhatsApp
Click Here
Click Here
Indexing Partner |
|||
| Copyright © 2026 - All Rights Reserved - IJRTI | |||