Enlarge the training set based on inter-class relationship for face recognition from one image per person

In some large-scale face recognition task, such as driver license identification and law enforcement, the training set only contains one image per person. This situation is referred to as one sample problem. Because many face recognition techniques implicitly assume that several (at least two) image...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2013-07, Vol.8 (7), p.e68539-e68539
Main Authors: Li, Qin, Wang, Hua Jing, You, Jane, Li, Zhao Ming, Li, Jin Xue
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Analysis
Applied mathematics
Biometry
Classification
Computer Science
Discriminant Analysis
Engineering
Expansion
Face
Face recognition
Facial recognition technology
Feature extraction
Humans
Identification
Laboratories
Mathematics
Methods
Object recognition
Pattern recognition
Pattern Recognition, Automated - methods
Principal Component Analysis
Principal components analysis
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In some large-scale face recognition task, such as driver license identification and law enforcement, the training set only contains one image per person. This situation is referred to as one sample problem. Because many face recognition techniques implicitly assume that several (at least two) images per person are available for training, they cannot deal with the one sample problem. This paper investigates principal component analysis (PCA), Fisher linear discriminant analysis (LDA), and locality preserving projections (LPP) and shows why they cannot perform well in one sample problem. After that, this paper presents four reasons that make one sample problem itself difficult: the small sample size problem; the lack of representative samples; the underestimated intra-class variation; and the overestimated inter-class variation. Based on the analysis, this paper proposes to enlarge the training set based on the inter-class relationship. This paper also extends LDA and LPP to extract features from the enlarged training set. The experimental results show the effectiveness of the proposed method.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0068539