Proceedings of the International Conference on Advances and Applications in Artificial Intelligence (ICAAAI 2025)

<Previous Article In Volume
Next Article In Volume>

Comparative Study of Deep Learning Algorithms For Image Caption Generation

Authors
Valavala S. S. S. R. Manikumar1, *, G. Bharathi Mohan2
1Department Of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Chennai, India
2Department Of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeetham, Chennai, India
*Corresponding author. Email: manikumarvalavala672003@gmail.com
Corresponding Author
Valavala S. S. S. R. Manikumar
Available Online 22 June 2025.
DOI
10.2991/978-94-6463-738-0_14How to use a DOI?
Keywords
Image Captioning; Deep Learning; Inception V3; ResNet 50; BiLSTM; LSTM
Abstract

In the recent times, image captioning had achieved widespread interest in the field of natural language processing. With the booming advancements in deep learning, there is a huge scope for the development in image captioning using deep learning. The proposed research addresses the challenges faced by researchers like generalization and variable embedding sizes by holding a comparative analysis of deep learning algorithms for image caption generation. In the proposed research work, transfer learning and Recurrent Neural Networks (RNN) have been used for autonomous generation of image captions. Pre-trained Inception V3 and RESNET 50 models were used to extract image feature vectors and GloVe 6B 200D was used to create embedding of the captions. A merge model had been proposed to integrate the intricacies of captions and images. The proposed model is trained on Flick 8k dataset and a combo of Inception V3 and BiLSTM had achieved a BLEU score of 0.576470.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International Conference on Advances and Applications in Artificial Intelligence (ICAAAI 2025)
Series
Advances in Intelligent Systems Research
Publication Date
22 June 2025
ISBN
978-94-6463-738-0
ISSN
1951-6851
DOI
10.2991/978-94-6463-738-0_14How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Valavala S. S. S. R. Manikumar
AU  - G. Bharathi Mohan
PY  - 2025
DA  - 2025/06/22
TI  - Comparative Study of Deep Learning Algorithms For Image Caption Generation
BT  - Proceedings of the International Conference on Advances and Applications in Artificial Intelligence (ICAAAI 2025)
PB  - Atlantis Press
SP  - 160
EP  - 178
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-738-0_14
DO  - 10.2991/978-94-6463-738-0_14
ID  - Manikumar2025
ER  -