A Novel Approach for Generating Captions for Visuals Using Deep Learning

IJET Best Journal: A Novel Approach for Generating Captions for Visuals Using Deep Learning

International Journal of Engineering and Techniques – Volume 10 Issue 2, March 2024 | ISSN: 2395-1303

Visit IJET Journal Website

IJET Best Journal Science Computer Lab

Modern computer science lab environment – representative of IJET Best Journal research

IJET Best Journal Authors & Affiliations

  • Koteswara Rao Velpula, Assistant Professor, Department of CSE, Vasireddy Venkatadri Institute of Technology, Nambur, Guntur, Andhra Pradesh, Email: koteswararao@vvit.net
  • Mohan Kalyan Guntupalli, UG Student, Department of CSE, Vasireddy Venkatadri Institute of Technology, Nambur, Guntur, Andhra Pradesh, Email: 20BQ1A0567@vvit.net
  • Venkatesh Katuri, UG Student, Department of CSE, Vasireddy Venkatadri Institute of Technology, Nambur, Guntur, Andhra Pradesh, Email: 20BQ1A0598@vvit.net
  • Saidaiah Kandrakunta, UG Student, Department of CSE, Vasireddy Venkatadri Institute of Technology, Nambur, Guntur, Andhra Pradesh, Email: 20BQ1A0589@vvit.net

Abstract – IJET Best Journal

Visual captioning involves creating descriptions of what is happening in an image. It helps build descriptions that explain the content of images. This paper introduces an innovative approach to caption generation using deep learning, specifically utilizing Convolutional Neural Networks (CNNs) for extracting image features and Long Short-Term Memory (LSTM) networks for generating sequences. Additionally, we incorporate nucleus sampling, a probabilistic technique, to improve the diversity and quality of the generated captions, offering more insightful and contextually relevant descriptions for images. This paper marks a significant advancement in automatic image captioning, showcasing the effectiveness of deep learning techniques combined with sophisticated sampling strategies to produce compelling and informative image descriptions.

Keywords – IJET Best Journal

Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Nucleus Sampling, Natural Language Processing (NLP), Feature Extraction, Deep Learning, IJET Best Journal

References – IJET Best Journal

  1. Ansar Hani, Najiba Tagougui & Monji Kherallah ā€œImage Caption Generation Using A Deep Architectureā€, ACIT, 2019, DOI: 10.1109/ACIT47987.2019.8990998
  2. Chetan Amritkar, Vaishali Jabade ā€œImage Caption Generation using Deep Learning Techniqueā€, ICCUBEA, 2018, DOI: 10.1109/ICCUBEA.2018.8697360
  3. Seung-Ho Han and Ho-Jin Choi ā€œDomain-Specific Image Caption Generator with Semantic Ontologyā€, IEEE International Conference on Big Data and Smart Computing (BigComp), 2020, DOI: 10.1109/BigComp48618.2020.00-12
  4. Grishma Sharma, Priyanka Kalena, Nishi Malde, Aromal Nair, Saurabh Parkar ā€œVisual Image Caption Generator Using Deep Learningā€, ICAST, 2019, DOI: 10.2139/ssrn.3368837
  5. Aishwarya Maroju, Sneha Sri Doma, Lahari Chandarlapati ā€œImage Caption Generating Deep Learning Modelā€, IJERT, Vol. 10, Issue 9, September 2021, DOI: 10.17577/IJERTV10IS090120
  6. M. Sailaja, K. Harika, B. Sridhar, Rajan Singh, V. Charitha, Koppula Srinivas Rao, ā€œImage Caption Generator using Deep Learningā€, IEEE, 2022, DOI: 10.1109/ASSIC55218.2022.10088345
  7. Dhirendra Parate, Minu Choudhary ā€œImage Caption Generator using deep learning with Flickr Datasetā€, IJRTI, Volume 7, Issue 8, 2022
  8. Smriti Sehgal, Jyoti Sharma, Natasha Chaudhary, ā€œGenerating Image Captions based on Deep Learning and Natural language Processingā€, ICRITO, June 2020, DOI: 10.1109/ICRITO48877.2020.9197977
  9. K. Praveen Kumar, V. Prakash Reddy, G. Indra Karan Reddy, N.S. Ganesh, ā€œImage Caption Generator Using CNNā€, IJCRT, Volume 9, Issue 6, June 2021
  10. P. Srinivasa Rao, Thipireddy Pavankumar, Raghu Mukkera, Gopu Hruthik Kiran, Velisala Hariprasad, ā€œIMAGE CAPTION GENERATION USING DEEP LEARNING TECHNIQUEā€, IRJMETS, Volume 4, Issue 6, June 2022
  11. Palak Kabra, Mihir Gharat, Dhiraj Jha, Shailesh Sangle, ā€œImage Caption Generator Using Deep Learningā€, IJRASET, Volume 10, Issue 10, October 2022, DOI: 10.22214/ijraset.2022.47058
  12. Tarun Wadhwa, Harleen Virk, Dr. Jagannath Aghav, Savita Borole, ā€œImage Captioning using Deep Learningā€, IJRASET, Volume 8, Issue 6, June 2020, DOI: 10.22214/ijraset.2020.6232
  13. A. M. Chandrashekhar, Akash Raj K R, Preetham Jain, Vinayaka Bhat, Nagarjun P R, ā€œImage Captioning using Deep Learning for the Visually Impairedā€, IJRASET, Volume 9, Issue 7, July 2021, DOI: 10.22214/ijraset.2021.36267
  14. Anish Banda, Harshavardhan Manne, Rohan Garakurthi ā€œImage Captioning using CNN and LSTMā€, Volume 9, Issue 7, August 2021, DOI: 10.22214/ijraset.2021.37846
  15. Bhardwaj, P. (2024). The Impact of Remote Work on FinOps Culture. International Journal of Management, IT & Engineering, 14(9), 100–107. https://www.ijmra.us/2024ijmie_september.php

Submit Your Paper to IJET Best Journal

Are you ready to publish in the best engineering journal? Submit your manuscript to the International Journal of Engineering and Techniques (IJET) for peer review and global visibility. Email your paper to editorijetjournal@gmail.com.

For author guidelines and more information, visit the IJET Journal Website.

Resources & External Links – IJET Best Journal

Post Comment

Submit Paper