Symmetric Subspace Learning for Image Analysis

Konstantinos Papachristou; Anastasios Tefas; Ioannis Pitas

doi:10.1109/TIP.2014.2367321

Symmetric Subspace Learning for Image Analysis

Konstantinos Papachristou, Anastasios Tefas, Ioannis Pitas

Department of Electrical & Electronic Engineering

Research output: Contribution to journal › Article (Academic Journal) › peer-review

11 Citations (Scopus)

288 Downloads (Pure)

Abstract

Subspace Learning is one of the most useful tools for image analysis and recognition. A large number of such techniques has been proposed utilizing a-priori knowledge about the data. In this paper, new Subspace Learning techniques are presented that use symmetry constraints in their objective functions. The rational behind this idea is to exploit the apriori knowledge that geometrical symmetry appears in several types of data, such as images, objects, faces, etc. Experiments on artificial, facial expression recognition, face recognition and object categorization databases highlight the superiority and the robustness of the proposed techniques, in comparison to standard Subspace Learning techniques.

Original language	English
Pages (from-to)	5683-5697
Number of pages	15
Journal	IEEE Transactions on Image Processing
Volume	23
Issue number	12
DOIs	https://doi.org/10.1109/TIP.2014.2367321
Publication status	Published - 5 Nov 2014

Keywords

Subspace learning
symmetry constraints
principal component analysis (PCA)
Linear Discriminant analysis (LDA)
clustering based discriminant analysis (CDA)

Access to Document

10.1109/TIP.2014.2367321

Ioannis Pitas - Symmetric Subspace Learning for Image Analysis - 2014
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via Institute of Electrical and Electronic Engineers at http://dx.doi.org/10.1109/TIP.2014.2367321. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 1.55 MB

Fingerprint Dive into the research topics of 'Symmetric Subspace Learning for Image Analysis'. Together they form a unique fingerprint.

Cite this

@article{f20c14199e7d4a1a8db3a8a3a0dacdcc,

title = "Symmetric Subspace Learning for Image Analysis",

abstract = "Subspace Learning is one of the most useful tools for image analysis and recognition. A large number of such techniques has been proposed utilizing a-priori knowledge about the data. In this paper, new Subspace Learning techniques are presented that use symmetry constraints in their objective functions. The rational behind this idea is to exploit the apriori knowledge that geometrical symmetry appears in several types of data, such as images, objects, faces, etc. Experiments on artificial, facial expression recognition, face recognition and object categorization databases highlight the superiority and the robustness of the proposed techniques, in comparison to standard Subspace Learning techniques.",

keywords = "Subspace learning, symmetry constraints, principal component analysis (PCA), Linear Discriminant analysis (LDA), clustering based discriminant analysis (CDA)",

author = "Konstantinos Papachristou and Anastasios Tefas and Ioannis Pitas",

year = "2014",

month = nov,

day = "5",

doi = "10.1109/TIP.2014.2367321",

language = "English",

volume = "23",

pages = "5683--5697",

journal = "IEEE Transactions on Image Processing",

issn = "1057-7149",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

number = "12",

}

TY - JOUR

T1 - Symmetric Subspace Learning for Image Analysis

AU - Papachristou, Konstantinos

AU - Tefas, Anastasios

AU - Pitas, Ioannis

PY - 2014/11/5

Y1 - 2014/11/5

N2 - Subspace Learning is one of the most useful tools for image analysis and recognition. A large number of such techniques has been proposed utilizing a-priori knowledge about the data. In this paper, new Subspace Learning techniques are presented that use symmetry constraints in their objective functions. The rational behind this idea is to exploit the apriori knowledge that geometrical symmetry appears in several types of data, such as images, objects, faces, etc. Experiments on artificial, facial expression recognition, face recognition and object categorization databases highlight the superiority and the robustness of the proposed techniques, in comparison to standard Subspace Learning techniques.

AB - Subspace Learning is one of the most useful tools for image analysis and recognition. A large number of such techniques has been proposed utilizing a-priori knowledge about the data. In this paper, new Subspace Learning techniques are presented that use symmetry constraints in their objective functions. The rational behind this idea is to exploit the apriori knowledge that geometrical symmetry appears in several types of data, such as images, objects, faces, etc. Experiments on artificial, facial expression recognition, face recognition and object categorization databases highlight the superiority and the robustness of the proposed techniques, in comparison to standard Subspace Learning techniques.

KW - Subspace learning

KW - symmetry constraints

KW - principal component analysis (PCA)

KW - Linear Discriminant analysis (LDA)

KW - clustering based discriminant analysis (CDA)

U2 - 10.1109/TIP.2014.2367321

DO - 10.1109/TIP.2014.2367321

M3 - Article (Academic Journal)

C2 - 25376040

VL - 23

SP - 5683

EP - 5697

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 12

ER -