Two-dimensional heteroscedastic linear discriminant analysis for age-group classification

Kazuya Ueki, Teruhide Hayashida, Tetsunori Kobayashi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

This paper presents a novel LDA algorithm named 2DHLDA (2-Dimensional Heteroscedastic Linear Discriminant Analysis). The proposed algorithms are applied on age-group classification using facial images under various lighting conditions. 2DHLDA significantly overcomes the singularity problem, so-called 'Small Sample Size' problem (S3 problem), and the original feature space is split into useful dimensions and nuisance dimensions to reduce the influence of different lighting conditions. A two-phased dimensional reduction step, namely 2DHLDA+LDA, is used in our experiment. Our experimental results show that the new 2DHLDA-based approach improves classification accuracy more than the conventional 1D and 2D-based approaches.

Original languageEnglish
Title of host publicationProceedings - 18th International Conference on Pattern Recognition, ICPR 2006
Pages585-588
Number of pages4
DOIs
Publication statusPublished - 2006 Dec 1
Event18th International Conference on Pattern Recognition, ICPR 2006 - Hong Kong, China
Duration: 2006 Aug 202006 Aug 24

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume2
ISSN (Print)1051-4651

Other

Other18th International Conference on Pattern Recognition, ICPR 2006
CountryChina
CityHong Kong
Period06/8/2006/8/24

    Fingerprint

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Ueki, K., Hayashida, T., & Kobayashi, T. (2006). Two-dimensional heteroscedastic linear discriminant analysis for age-group classification. In Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006 (pp. 585-588). [1699273] (Proceedings - International Conference on Pattern Recognition; Vol. 2). https://doi.org/10.1109/ICPR.2006.1138