2025 Vol.8 Dec.N06

• Title: Design and Implementation of an Image Retrieval System in a Big Data Environment
• Name: Lei Xia,Weiwei Deng
• Company: Network & Information Center, Nanchang Normal College of Applied Technology, Nanchang, 330108, China
• Abstract:

  With the advent of the big data era, image data has experienced explosive growth, posing challenges such as large data scale, low value density, and high processing timeliness requirements for traditional image retrieval technologies. This study, based on the Jiangxi Provincial Department of Education Science and Technology Research Project "Research on the Design and Implementation of an Image Retrieval System in a Big Data Environment," proposes an image retrieval solution that integrates visual vocabulary hashing, social network user encoding, and transfer deep learning. By optimizing the discriminative power of visual vocabulary through linear discriminant analysis, generating community-aware user encoding using graph theory, and leveraging transfer learning to address insufficient training data, the proposed method demonstrates significant improvements. Experimental results show that the solution enhances retrieval accuracy by 10%–30% on public datasets compared to traditional methods and reduces retrieval time to 60% of that of conventional approaches, providing an effective solution for image retrieval in big data environments.

  
  

• Keyword: Image Retrieval; Big Data; Visual Vocabulary Hashing; User Encoding; Transfer Learning; Deep Learning
• DOI: 10.12250/jpciams2025091105
• Citation form: Lei Xia,Weiwei Deng.Design and Implementation of an Image Retrieval System in a Big Data Environment[J]. Computer Informatization and Mechanical System,2025,Vol.8,pp.

[1] SWAIN M J, BALLARD D H. Color indexing[J]. International Journal of Computer Vision, 1991, 7(1): 11-32.
[2] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[3] BAY H, ESS A, TUYTELAARS T, et al. Speeded-up robust features (SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3): 346-359.
[4] RUBLEE E, RABAUD V, KONOLIGE K, et al. ORB: An efficient alternative to SIFT or SURF[C]//Proceedings of the 2011 International Conference on Computer Vision. Barcelona: IEEE, 2011: 2564-2571.
[5] SALAKHUTDINOV R, HINTON G. Semantic hashing[J]. International Journal of Approximate Reasoning, 2009, 50(7): 969-978.