TY - JOUR
T1 - An experimental evaluation of three classifiers for use in self-updating face recognition systems
AU - Pavani, Sri Kaushik
AU - Sukno, Federico M.
AU - Delgado-Gomez, David
AU - Butakoff, Constantine
AU - Planes, Xavier
AU - Frangi, Alejandro F.
PY - 2012/6
Y1 - 2012/6
N2 - 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.
AB - 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.
KW - Adaptive systems
KW - Confidence measures
KW - Face recognition
KW - Self-update procedure
KW - Template update
UR - http://www.scopus.com/inward/record.url?scp=84861145410&partnerID=8YFLogxK
U2 - 10.1109/TIFS.2012.2186292
DO - 10.1109/TIFS.2012.2186292
M3 - Article
SN - 1556-6013
VL - 7
SP - 932
EP - 943
JO - IEEE Transactions on Information Forensics and Security
JF - IEEE Transactions on Information Forensics and Security
IS - 3
M1 - 6144728
ER -