EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Efficient Image Retrieval Using Hierarchical K-Means Clustering

Dayoung Park, Youngbae Hwang iD

Sensors · 09.04.2024 · 24 (8) · 2401

DOI: 10.3390/s24082401 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 09.04.2024. Verfasst von Dayoung Park und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Control and Robot Engineering, Chungbuk National University, Cheongju 28644, Republic of Korea. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute for Information and Communications Technology Promotion, Korea Institute of Science & Technology Information, Grand Information Technology Research Support Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The objective of content-based image retrieval (CBIR) is to locate samples from a database that are akin to a query, relying on the content embedded within the images. A contemporary strategy involves calculating the similarity between compact vectors by encoding both the query and the database images as global descriptors. In this work, we propose an image retrieval method by using hierarchical K-means clustering to efficiently organize the image descriptors within the database, which aims to optimize the subsequent retrieval process. Then, we compute the similarity between the descriptor set within the leaf nodes and the query descriptor to rank them accordingly. Three tree search algorithms are presented to enable a trade-off between search accuracy and speed that allows for substantial gains at the expense of a slightly reduced retrieval accuracy. Our proposed method demonstrates enhancement in image retrieval speed when applied to the CLIP-based model, UNICOM, designed for category-level retrieval, as well as the CNN-based R-GeM model, tailored for particular object retrieval by validating its effectiveness across various domains and backbones. We achieve an 18-times speed improvement while preserving over 99% accuracy when applied to the In-Shop dataset, the largest dataset in the experiments.

Schlagwörter

Stichwörter der Autor:innen

CBIRefficiencyhierarchical clusteringimage retrievaltree search

Autor:innen und Institutionen

  • Department of Control and Robot Engineering, Chungbuk National University, Cheongju 28644, Republic of Korea.

ORCID-Profile: Youngbae Hwang

Förderung

  • Institute for Information and Communications Technology Promotion
  • Korea Institute of Science & Technology Information
  • Grand Information Technology Research Support Program
  • Institute of Information & Communications Technology Planning & Evaluation (IITP)
  • Korea Institute of Science and Technology (KISTI)

Zitieren

APA

Park, D., & Hwang, Y. (2024). Efficient Image Retrieval Using Hierarchical K-Means Clustering. Sensors, 24(8), 2401. https://doi.org/10.3390/s24082401

Vancouver

Park D, Hwang Y. Efficient Image Retrieval Using Hierarchical K-Means Clustering. Sensors. 2024;24(8):2401. doi:10.3390/s24082401

BibTeX
@article{Park2024,
  author = {Park, Dayoung and Hwang, Youngbae},
  title = {Efficient Image Retrieval Using Hierarchical K-Means Clustering},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {8},
  pages = {2401},
  doi = {10.3390/s24082401}
}
Kostenlos starten →