Dynamic Threshold for Image Retrieval

Conference proceedings article

Authors/Editors

Strategic Research Themes

Publication Details

Author list: Sithisint V.; Phuseansaart A.; Chanyarungroj J.; Ganokratanaa T.; Ketcham M.

Publisher: Springer

Publication year: 2025

Journal: Lecture Notes in Computer Science (0302-9743)

Start page: 446

End page: 454

Number of pages: 9

ISBN: 978-981966388-0

ISSN: 0302-9743

URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-105008647820&doi=10.1007%2f978-981-96-6389-7_41&partnerID=40&md5=a34fa49df91123e6344a7240dd05aa5d

Languages: English-Great Britain (EN-GB)

View on publisher site

Abstract

Content-based image retrieval (CBIR) with a static threshold often encounters limitations due to the varying characteristics of queries in different image galleries. In this paper, we propose an approach to address this challenge by introducing dynamic threshold determination for image retrieval. Our method dynamically adjusts the threshold for each gallery based on the distribution of galleries close to that gallery in feature space. By tailoring the threshold to the specific characteristics of each gallery, our approach aims to enhance retrieval accuracy and relevance. We evaluate our method using the ROxford dataset and compare it with the best static threshold. Our approach yields significant enhancements in macro F1 scores across diverse dataset complexities. In the ROxford (medium) scenario, we observed an 12.4% improvement over the static threshold baseline, while in the ROxford (hard) setting, we achieved a 6.41% enhancement. The LogoSearch dataset achieved a 2.72% enhancement. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

Keywords

No matching items found.