You are here

Enhancing instance search with weak geometric correlation consistency

Authors: 

Zhenxing Zhang, Rami Albatal, Cathal Gurrin, Alan Smeaton

Publication Type: 
Refereed Original Article
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
Digital Object Identifer (DOI): 
10.1016/j.neucom.2016.09.104
Publication Status: 
Published
Date Accepted for Publication: 
Tuesday, 1 November, 2016
Publication Date: 
17/11/2016
Journal: 
Neurocomputing
Research Group: 
Institution: 
Dublin City University (DCU)
Open access repository: 
Yes