|
INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016 open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15 |
Imp Links for Author
Imp Links for Reviewer
Research Area
Subscribe IJSDR
Visitor Counter
Copyright Infringement Claims
Indexing Partner
|
Published Paper Details
|
|
| Paper Title: | ENHANCING TEXTUAL DESCRIPTION USING DEEP LEARNING WITH RC-GAN GENERATION |
| Authors Name: | A.Srujan Reddy , N. Venkata Mahesh Kumar Reddy , N.Bharath , S. Raaga Sindhu , R. Jagadeeswari |
| Unique Id: | IJSDR2404110 |
| Published In: | Volume 9 Issue 4, April-2024 |
| Abstract: | One method employed to create pixels representations corresponding to verbal descriptions is known as "text-to-image generation," impacting a broad spectrum of applications and research domains, including exploration, design, computer-aided drafting, image restoration, labelling, and portraiture. The primary challenge lies in consistently generating realistic photographs under specified conditions. Existing algorithms for script-to-image conversion often fail to accurately align images with the accompanying text descriptions. In our investigation, we addressed this challenge by devising a deep learning architecture named the recurrent convolutional generative adversarial network (RC-GAN) specifically fine-tuned for producing semantically concise snapshots. RC-GAN effectively translates conceptual visual elements from linguistic cues to pixel-level representations, bridging the gap between advancements in text and image modelling. To train our proposed model, we utilised various datasets, employing metrics such as inception score and peak signalto-noise ratio (PSNR) to analyse its performance. Empirical findings showcase an inception required score and a PSNR required measurement, indicating that our model can produce more realistic images from verbal descriptions. Our future endeavour involves training the proposed system on various datasets to further improve its capabilities. |
| Keywords: | Deep Learning (DL), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Generation of Image, Generative Adversarial Networks (GAN). |
| Cite Article: | "ENHANCING TEXTUAL DESCRIPTION USING DEEP LEARNING WITH RC-GAN GENERATION ", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.9, Issue 4, page no.787 - 792, April-2024, Available :http://www.ijsdr.org/papers/IJSDR2404110.pdf |
| Downloads: | 000338174 |
| Publication Details: | Published Paper ID: IJSDR2404110 Registration ID:210836 Published In: Volume 9 Issue 4, April-2024 DOI (Digital Object Identifier): Page No: 787 - 792 Publisher: IJSDR | www.ijsdr.org ISSN Number: 2455-2631 |
|
Click Here to Download This Article |
|
| Article Preview | |
|
|
|
Major Indexing from www.ijsdr.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 |
Track Paper
Important Links
Conference Proposal
ISSN
 |
 |
DOI (A digital object identifier)
  Providing A digital object identifier by DOI How to GET DOI and Hard Copy Related |
Open Access License Policy
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
|
 |
 |
 |
Social Media
Indexing Partner |
|||
| Copyright © 2024 - All Rights Reserved - IJSDR | |||
Facebook Twitter Instagram LinkedIn