University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Binary Online Learned Descriptors

Tang, Hongying, Balntas, V and Mikolajczyk, Krystian (2017) Binary Online Learned Descriptors IEEE Transactions on Pattern Analysis and Machine Intelligence, 40 (3). pp. 555-567.

07882718.pdf - Accepted version Manuscript

Download (1MB) | Preview


We propose a novel approach to generate a binary descriptor optimized for each image patch independently. The approach is inspired by the linear discriminant embedding that simultaneously increases inter and decreases intra class distances. A set of discriminative and uncorrelated binary tests is established from all possible tests in an offline training process. The patch adapted descriptors are then efficiently built online from a subset of features which lead to lower intra-class distances and thus, to a more robust descriptor. We perform experiments on three widely used benchmarks and demonstrate improvements in matching performance, and illustrate that per-patch optimization outperforms global optimization.

Item Type: Article
Subjects : Computing Science
Divisions : Faculty of Engineering and Physical Sciences > Computing Science
Authors :
Balntas, V
Date : 20 March 2017
Funders : EPSRC
DOI : 10.1109/TPAMI.2017.2679193
Copyright Disclaimer : 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
Uncontrolled Keywords : Learning feature descriptors, binary descriptors, feature matching, image matching
Related URLs :
Depositing User : Symplectic Elements
Date Deposited : 01 Mar 2017 14:50
Last Modified : 11 Dec 2018 11:22

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800