Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Enhancing instance search with weak geometric correlation consistency

Zhang, Zhenxing, Albatal, Rami orcid logoORCID: 0000-0002-9269-8578, Gurrin, Cathal orcid logoORCID: 0000-0003-2903-3968 and Smeaton, Alan F. orcid logoORCID: 0000-0003-1028-8389 (2016) Enhancing instance search with weak geometric correlation consistency. Neurocomputing, 236 . pp. 164-172. ISSN 0925-2312

Abstract
Finding object instances from within in large image collections is a challenging problem with many practical applications. Recent methods inspired by text retrieval have achieved good results, however a re-ranking stage based on spatial verification may still be required to boost performance. To improve the effectiveness of such instance retrieval systems while avoiding the computational complexity of a re-ranking stage, we explore the geometric correlations among local features, and we incorporate these correlations with each individual match to form a transformation consistency in rotation and scale space. This weak geometric correlation consistency can be used to effectively eliminate inconsistent feature matches in instance retrieval and can be applied to all candidate images at a low computational cost. Experimental results on three standard evaluation benchmarks show that the proposed approach results in a substantial performance improvement when compared with other state-of-the-art methods. In addition, the evaluation results from participating in the Instance Search Task in the TRECVid evaluation campaign also suggest that our proposed approach enhances retrieval performance for large scale video collections.
Metadata
Item Type:Article (Published)
Refereed:Yes
Uncontrolled Keywords:Multimedia Indexing; Information retrieval; Instance Search; Weak geometric correlation consistency
Subjects:Computer Science > Lifelog
Computer Science > Artificial intelligence
Computer Science > Multimedia systems
DCU Faculties and Centres:Research Initiatives and Centres > INSIGHT Centre for Data Analytics
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Publisher:Elsevier
Official URL:http://dx.doi.org/10.1016/j.neucom.2016.09.104
Copyright Information:© 2016 Elsevier
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Science Foundation Ireland. SFI/12/RC/2289, Norwegian Research Council. iAD project, grant number 174867
ID Code:21497
Deposited On:08 Dec 2016 09:21 by Alan Smeaton . Last Modified 15 Dec 2021 16:12
Documents

Full text available as:

[thumbnail of Paper_for_Neuralcomputing__Shared_.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
7MB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record