Mohammed Hafeez M K,
Ayishathul Misriya K S,
Fathima Haifa,
Fathimath Zaziba,
Khatheejathul Aifa,
- Professor Department of Computer Science and Engineering, P A College of Engineering, Mangalore Karnataka India
- Student Department of Computer Science and Engineering, P A College of Engineering, Mangalore Karnataka India
- Student Department of Computer Science and Engineering, P A College of Engineering, Mangalore Karnataka India
- Student Department of Computer Science and Engineering, P A College of Engineering, Mangalore Karnataka India
- Student Department of Computer Science and Engineering, P A College of Engineering, Mangalore Karnataka India
Abstract
Because of the exponential growth of digital content, sophisticated tools are required for effective data interpretation and administration.. This project harnesses the capabilities of the Gemini AI model developed by Google DeepMind to address the challenges of PDF summarization and image captioning. Gemini AI integrates cutting-edge algorithms, including transformer architectures, to process textual and visual data seamlessly. The project’s system architecture involves modules for text and image extraction, with a Frontend Interface and Backend Server for efficient processing. Results indicate its effectiveness in enhancing content understanding and retrieval.
Keywords: PDF, image captioning, google deep mind, docsnap, gemini AI model.
References
- Mahalakshmi, , & Fatima, N. S. (2022). “Summarization of text and image captioning in information retrieval using deep learning techniques”. IEEE Access, 10, 18289- 18297.
- Ghandi, Taraneh, Hamidreza Pourreza, and Hamidreza Mahyar. “Deep learning approaches on image captioning: A review.” ACM Computing Surveys 56.3 (2023): 1-39.
- Inayathulla, Mohammed. “Image Caption Generation using Deep Learning For Video Summarization Applications.” International Journal of Advanced Computer Science & Applications 15.1 (2024).
- Xu, M., Rahman, H. A., & Li, F. (2023). Automated Generation of Chinese Text-Image Summaries Using Deep Learning Techniques. Traitement du Signal, 40(6).
- Gangathimmappa, M., Subramani, N., Sambath, V., Ramanujam, R. A. M., Sammeta, N., & Marimuthu, M. (2023). Deep learning enabled cross‐lingual search with metaheuristic web based query optimization model for multi‐document summarization. Concurrency and Computation: Practice and Experience, 35(2), e7476.
- Honda, Ukyo, Taro Watanabe, and Yuji Matsumoto. “Switching to discriminative image captioning by relieving a bottleneck of reinforcement learning.” In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 1124-1134. 2023.
- Wei, Haiyang, et al. “The synergy of double attention: Combine sentence-level and word-level attention for image captioning.” Computer Vision and Image Understanding 201 (2020): 103068.
- Huang, Chieh-Yang, et al. “Summaries as captions: Generating figure captions for scientific documents with automated text summarization.” arXiv preprint arXiv:2302.12324 (2023).
- Li, Jiesi, et al. “Image Captioning with multi-level similarity-guided semantic ” Visual Informatics 5.4 (2021): 41-48.
- Li, Guodun, et “Similar scenes arouse similar emotions: Parallel data augmentation for stylized image captioning.” Proceedings of the 29th ACM International Conference on Multimedia. 2021.
- Sakkaravarthy Iyyappan, K., and S. Balasundaram. “A novel multi document summarization with document- elements augmentation for learning materials using concept based ILP and clustering methods.” International Journal of Computers and Applications 46.2 (2024): 78-89.
Journal of Instrumentation Technology & Innovations
Volume | |
Received | June 28, 2024 |
Accepted | July 2, 2024 |
Published | July 16, 2024 |