Binary online learned descriptors

File Description SizeFormat 
mikolajczyk.pdfFile embargoed until 01 January 100001.63 MBAdobe PDF    Request a copy
Title: Binary online learned descriptors
Author(s): Mikolajczyk, KM
Baltnas, V
Item Type: Journal Article
Abstract: 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.
Publication Date: 31-Dec-2017
Date of Acceptance: 9-Feb-2017
URI: http://hdl.handle.net/10044/1/44750
ISSN: 2160-9292
Publisher: IEEE
Journal / Book Title: IEEE transactions on Pattern Analysis and Machine Intelligence
Copyright Statement: This paper is embargoed until publication.
Sponsor/Funder: Engineering & Physical Science Research Council (E
Engineering & Physical Science Research Council (EPSRC)
Funder's Grant Number: EP/N007743/1
EP/K01904X/2
Publication Status: Accepted
Embargo Date: publication subject to indefinite embargo
Appears in Collections:Faculty of Engineering
Electrical and Electronic Engineering



Items in Spiral are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons