Content-based image retrieval using transfer learning and vector database
Content-based image retrieval (CBIR) systems are essential for efficiently searching large image datasets using image features instead of text annotations. Major challenges include extracting effective feature representations to improve accuracy, as well as indexing them to improve the retrieval spe...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/120456/ http://psasir.upm.edu.my/id/eprint/120456/1/120456.pdf |
| _version_ | 1848868187968372736 |
|---|---|
| author | Shuo, Li Affendey, Lilly Suriani Sidi, Fatimah |
| author_facet | Shuo, Li Affendey, Lilly Suriani Sidi, Fatimah |
| author_sort | Shuo, Li |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | Content-based image retrieval (CBIR) systems are essential for efficiently searching large image datasets using image features instead of text annotations. Major challenges include extracting effective feature representations to improve accuracy, as well as indexing them to improve the retrieval speed. The use of pre-trained deep learning models to extract features has elicited interest from researchers. In addition, the emergence of open-source vector databases allows efficient vector indexing which significantly increases the speed of similarity search. This paper introduces a novel CBIR system that combines transfer learning with vector databases to improve retrieval speed and accuracy. Using a pre-trained VGG-16 model, we extract high-dimensional feature vectors from images, which are stored and retrieved using the Milvus vector database. Our approach significantly reduces retrieval time, achieving real-time responses while maintaining high precision and recall. Experiments conducted on ImageClef, ImageNet, and Corel-1k datasets demonstrate the system’s effectiveness in large-scale image retrieval tasks, outperforming traditional methods in both speed and accuracy. © (2024), (Science and Information Organization). All rights reserved. |
| first_indexed | 2025-11-15T14:48:25Z |
| format | Article |
| id | upm-120456 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T14:48:25Z |
| publishDate | 2022 |
| publisher | Elsevier |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1204562025-10-02T07:51:23Z http://psasir.upm.edu.my/id/eprint/120456/ Content-based image retrieval using transfer learning and vector database Shuo, Li Affendey, Lilly Suriani Sidi, Fatimah Content-based image retrieval (CBIR) systems are essential for efficiently searching large image datasets using image features instead of text annotations. Major challenges include extracting effective feature representations to improve accuracy, as well as indexing them to improve the retrieval speed. The use of pre-trained deep learning models to extract features has elicited interest from researchers. In addition, the emergence of open-source vector databases allows efficient vector indexing which significantly increases the speed of similarity search. This paper introduces a novel CBIR system that combines transfer learning with vector databases to improve retrieval speed and accuracy. Using a pre-trained VGG-16 model, we extract high-dimensional feature vectors from images, which are stored and retrieved using the Milvus vector database. Our approach significantly reduces retrieval time, achieving real-time responses while maintaining high precision and recall. Experiments conducted on ImageClef, ImageNet, and Corel-1k datasets demonstrate the system’s effectiveness in large-scale image retrieval tasks, outperforming traditional methods in both speed and accuracy. © (2024), (Science and Information Organization). All rights reserved. Elsevier 2022 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/120456/1/120456.pdf Shuo, Li and Affendey, Lilly Suriani and Sidi, Fatimah (2022) Content-based image retrieval using transfer learning and vector database. SSRN Electronic Journal, 15 (9). pp. 1-9. ISSN 1556-5068 https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4111257 10.2139/ssrn.4111257 |
| spellingShingle | Shuo, Li Affendey, Lilly Suriani Sidi, Fatimah Content-based image retrieval using transfer learning and vector database |
| title | Content-based image retrieval using transfer learning and vector database |
| title_full | Content-based image retrieval using transfer learning and vector database |
| title_fullStr | Content-based image retrieval using transfer learning and vector database |
| title_full_unstemmed | Content-based image retrieval using transfer learning and vector database |
| title_short | Content-based image retrieval using transfer learning and vector database |
| title_sort | content-based image retrieval using transfer learning and vector database |
| url | http://psasir.upm.edu.my/id/eprint/120456/ http://psasir.upm.edu.my/id/eprint/120456/ http://psasir.upm.edu.my/id/eprint/120456/ http://psasir.upm.edu.my/id/eprint/120456/1/120456.pdf |