This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Mahesh Prajapati,
Vijay Bhandari,
Ritu Shrivastava,
- Student, Department of computer science & engineering, Sagar Institute of Research and Technology, Bhopal, Madhya Predesh, India
- Professor, Department of computer science & engineering, Sagar Institute of Research and Technology, Bhopal, Madhya Predesh, India
- Professor, Department of computer science & engineering, Sagar Institute of Research and Technology, Bhopal, Madhya Predesh, India
Abstract
Content-based image retrieval (CBIR) plays a vital role in computer vision, driven by the increasing need for fast and accurate image retrieval across fields like healthcare, e-commerce, and digital libraries. This paper offers a detailed review of CBIR methodologies, charting their progression from traditional feature extraction techniques, such as Local Binary Patterns (LBP), to contemporary deep learning-driven methods. The transformative impact of convolution neural networks (CNNs) is highlighted, emphasizing their ability to capture intricate, hierarchical features that address the semantic gap and enhance retrieval precision.
The paper evaluates various algorithms, examining their strengths and weaknesses while tackling key challenges like computational efficiency, scalability for large datasets, and the enduring semantic gap in interpreting image content. It explores emerging trends, including hybrid feature models, attention mechanisms, multi-modal learning, and transfer learning, showcasing their potential to overcome existing hurdles. Privacy-preserving methods like federated learning and domain-specific solutions, particularly in medical imaging, are also discussed for their practical relevance.
The real-world use of CBIR systems spans industries, from healthcare for diagnostic support to e-commerce for personalized recommendations and cultural heritage preservation, illustrating the method’s versatility. This review seeks to give researchers a comprehensive understanding of the CBIR field, highlighting critical research gaps and promising future directions. These include lightweight architectures for real-time applications, effective feature fusion techniques, and adaptive learning strategies tailored to specific domains.
Keywords: Content-Based Image Retrieval (CBIR), Feature Extraction, Deep Learning, Convolution Neural Networks (CNNs), Semantic Gap, application of CBIR
[This article belongs to Journal of Computer Technology & Applications (jocta)]
Mahesh Prajapati, Vijay Bhandari, Ritu Shrivastava. Recent Advances in Content-Based Image Retrieval: Techniques and Applications. Journal of Computer Technology & Applications. 2024; 16(01):-.
Mahesh Prajapati, Vijay Bhandari, Ritu Shrivastava. Recent Advances in Content-Based Image Retrieval: Techniques and Applications. Journal of Computer Technology & Applications. 2024; 16(01):-. Available from: https://journals.stmjournals.com/jocta/article=2024/view=190799
References
- Wu W, Chen Y, Xu J, Zhang Y. Attention-based convolutional neural networks for chinese relation extraction. InChinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data: 17th China National Conference, CCL 2018, and 6th International Symposium, NLP-NABD 2018, Changsha, China, October 19–21, 2018, Proceedings 17 2018 (pp. 147-158). Springer International Publishing.
- Cui H, Zhu L, Li J, Yang Y, Nie L. Scalable deep hashing for large-scale social image retrieval. IEEE Transactions on image processing. 2019 Sep 16;29:1271-84.
- Khan UA, Javed A, Ashraf R. An effective hybrid framework for content based image retrieval (CBIR). Multimedia Tools and Applications. 2021 Jul;80(17):26911-37.
- Xu Y, Zhang M, Yang X, Xu C. Exploring multi-modal contextual knowledge for open-vocabulary object detection. IEEE Transactions on Image Processing. 2024 Oct 29.
- Agrawal S, Chowdhary A, Agarwala S, Mayya V, Kamath S S. Content-based medical image retrieval system for lung diseases using deep CNNs. International Journal of Information Technology. 2022 Dec;14(7):3619-27.
- Li X, Yang J, Ma J. Recent developments of content-based image retrieval (CBIR). Neurocomputing. 2021 Sep 10;452:675-89.
- Khatami A, Khosravi A, Nguyen T, Lim CP, Nahavandi S. Medical image analysis using wavelet transform and deep belief networks. Expert Systems with Applications. 2017 Nov 15;86:190-8.
- Peng Z, Li Z, Zhang J, Li Y, Qi GJ, Tang J. Few-shot image recognition with knowledge transfer. InProceedings of the IEEE/CVF international conference on computer vision 2019 (pp. 441-449).
- Adnan M, Kalra S, Cresswell JC, Taylor GW, Tizhoosh HR. Federated learning and differential privacy for medical image analysis. Scientific reports. 2022 Feb 4;12(1):1953.
- Shamshad F, Khan S, Zamir SW, Khan MH, Hayat M, Khan FS, Fu H. Transformers in medical imaging: A survey. Medical Image Analysis. 2023 Aug 1;88:102802.
Journal of Computer Technology & Applications
Volume | 16 |
Issue | 01 |
Received | 04/12/2024 |
Accepted | 19/12/2024 |
Published | 24/12/2024 |