Accurate Image Retrieval with Unsupervised 2-Stage k-NN Re-Ranking

Accurate Image Retrieval with Unsupervised 2-Stage k-NN Re-Ranking

Dawei Li, Mooi Choo Chuah
Copyright: © 2016 |Volume: 7 |Issue: 1 |Pages: 19
ISSN: 1947-8534|EISSN: 1947-8542|EISBN13: 9781466690448|DOI: 10.4018/IJMDEM.2016010103
Cite Article Cite Article

MLA

Li, Dawei, and Mooi Choo Chuah. "Accurate Image Retrieval with Unsupervised 2-Stage k-NN Re-Ranking." IJMDEM vol.7, no.1 2016: pp.41-59. http://doi.org/10.4018/IJMDEM.2016010103

APA

Li, D. & Chuah, M. C. (2016). Accurate Image Retrieval with Unsupervised 2-Stage k-NN Re-Ranking. International Journal of Multimedia Data Engineering and Management (IJMDEM), 7(1), 41-59. http://doi.org/10.4018/IJMDEM.2016010103

Chicago

Li, Dawei, and Mooi Choo Chuah. "Accurate Image Retrieval with Unsupervised 2-Stage k-NN Re-Ranking," International Journal of Multimedia Data Engineering and Management (IJMDEM) 7, no.1: 41-59. http://doi.org/10.4018/IJMDEM.2016010103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Many state-of-the-art image retrieval systems include a re-ranking step to refine the suggested initial ranking list so as to improve the retrieval accuracy. In this paper, we present a novel 2-stage k-NN re-ranking algorithm. In stage one, we generate an expanded list of candidate database images for re-ranking so that lower ranked ground truth images will be included and re-ranked. In stage two, we re-rank the list of candidate images using a confidence score which is calculated based on, rRBO, a new proposed ranking list similarity measure. In addition, we propose the rLoCATe image feature, which captures robust color and texture information on salient image patches, and shows superior performance in the image retrieval task. We evaluate the proposed re-ranking algorithm on various initial ranking lists created using both SIFT and rLoCATe on two popular benchmark datasets along with a large-scale one million distraction dataset. The results show that our proposed algorithm is not sensitive for different parameter configurations and it outperforms existing k-NN re-ranking methods.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.