You are not logged in.

Hallucinating optimal high-dimensional subspaces

Arandjelović,O 2014, Hallucinating optimal high-dimensional subspaces, Pattern Recognition, vol. 47, no. 8, pp. 2662-2672, doi: 10.1016/j.patcog.2014.02.006.

Attached Files
Name Description MIMEType Size Downloads

Title Hallucinating optimal high-dimensional subspaces
Author(s) Arandjelović,O
Journal name Pattern Recognition
Volume number 47
Issue number 8
Start page 2662
End page 2672
Total pages 11
Publisher Elsevier
Place of publication Amsterdam, Netherlands
Publication date 2014-08
ISSN 0031-3203
Keyword(s) Ambiguity
Constraint
Face
Projection
Similarity
SVD
Science & Technology
Technology
Computer Science, Artificial Intelligence
Engineering, Electrical & Electronic
Computer Science
Engineering
INVARIANT FACE RECOGNITION
GAUSSIAN MIXTURE-MODELS
LINEAR-SUBSPACES
IMAGES
OBJECT
POSE
Summary Linear subspace representations of appearance variation are pervasive in computer vision. This paper addresses the problem of robustly matching such subspaces (computing the similarity between them) when they are used to describe the scope of variations within sets of images of different (possibly greatly so) scales. A naïve solution of projecting the low-scale subspace into the high-scale image space is described first and subsequently shown to be inadequate, especially at large scale discrepancies. A successful approach is proposed instead. It consists of (i) an interpolated projection of the low-scale subspace into the high-scale space, which is followed by (ii) a rotation of this initial estimate within the bounds of the imposed "downsampling constraint". The optimal rotation is found in the closed-form which best aligns the high-scale reconstruction of the low-scale subspace with the reference it is compared to. The method is evaluated on the problem of matching sets of (i) face appearances under varying illumination and (ii) object appearances under varying viewpoint, using two large data sets. In comparison to the naïve matching, the proposed algorithm is shown to greatly increase the separation of between-class and within-class similarities, as well as produce far more meaningful modes of common appearance on which the match score is based. © 2014 Elsevier Ltd.
Language eng
DOI 10.1016/j.patcog.2014.02.006
Field of Research 080109 Pattern Recognition and Data Mining
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category C1 Refereed article in a scholarly journal
ERA Research output type C Journal article
Copyright notice ©2014, Elsevier
Persistent URL http://hdl.handle.net/10536/DRO/DU:30070815

Document type: Journal Article
Collection: Centre for Pattern Recognition and Data Analytics
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 3 times in TR Web of Science
Scopus Citation Count Cited 5 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 56 Abstract Views, 3 File Downloads  -  Detailed Statistics
Created: Tue, 17 Mar 2015, 10:22:30 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.