Paper Info
Title
An Experimental Evaluation of Three Classifiers for Use in Self-Updating Face Recognition Systems
Abstract
Previous studies have shown that the accuracy of Face Recognition Systems (FRSs) decreases with the time elapsed between enrollment and testing. The main reason for the decrease is the changes in appearance of the user due to factors such as ageing, beard growth, sun-tan etc. Self-update procedure, where the system learns the biometric characteristics of the user every time he/she interacts with it, can be used to automatically update the system. However, a commonly acknowledged problem is the corruption of biometric traits due to misclassification. In this article, we test FRS, based on three classification algorithms, on two challenging databases, GEFA and YT, with 14 279 and 31 951 images, respectively. Our results suggest that complex, state-of-the-art classifiers that make use of user-specific models, need not be the best choice for use in self updating systems. In other words, tolerance to corrupted training data decreases as the complexity of the classifier increases.
Year
DOI
Venue
2012
10.1109/TIFS.2012.2186292
IEEE Transactions on Information Forensics and Security
Keywords
Field
DocType
adaptive system,training data,databases,adaptive systems,learning artificial intelligence,ageing,aging,face,accuracy,face recognition,image classification,classification algorithms
Confidence measures,Computer science,Artificial intelligence,Classifier (linguistics),Contextual image classification,Training set,Facial recognition system,Computer vision,Pattern recognition,Adaptive system,Biometrics,Statistical classification,Machine learning
Journal
Volume
Issue
ISSN
7
3
1556-6013
Citations 
PageRank 
References 
2
0.37
32
Authors
6
Name
Order
Citations
PageRank
Sri-Kaushik Pavani11498.30
Federico Sukno2747.06
David Delgado Gomez3629.67
Constantine Butakoff433632.52
Xavier Planes5343.75
Alejandro F. Frangi64333309.21