RT Journal Article
A1 Abhishek Dutta
AD Faculty of EEMCS, University of Twente, P.O. Box 217, 7500 AE, Enschede, Netherlands
A1 Manuel Günther
AD Centre du Parc, Idiap Research Institute, Rue Marconi 19, P.O. Box 592, CH 1920, Martigny, Switzerland
A1 Laurent El Shafey
AD Centre du Parc, Idiap Research Institute, Rue Marconi 19, P.O. Box 592, CH 1920, Martigny, Switzerland
A1 Sébastien Marcel
AD Centre du Parc, Idiap Research Institute, Rue Marconi 19, P.O. Box 592, CH 1920, Martigny, Switzerland
A1 Raymond Veldhuis
AD Faculty of EEMCS, University of Twente, P.O. Box 217, 7500 AE, Enschede, Netherlands
A1 Luuk Spreeuwers
AD Faculty of EEMCS, University of Twente, P.O. Box 217, 7500 AE, Enschede, Netherlands

PB iet
T1 Impact of eye detection error on face recognition performance
JN IET Biometrics
VO 4
IS 3
SP 137
OP 150
AB The locations of the eyes are the most commonly used features to perform face normalisation (i.e. alignment of facial features), which is an essential preprocessing stage of many face recognition systems. In this study, the authors study the sensitivity of open source implementations of five face recognition algorithms to misalignment caused by eye localisation errors. They investigate the ambiguity in the location of the eyes by comparing the difference between two independent manual eye annotations. They also study the error characteristics of automatic eye detectors present in two commercial face recognition systems. Furthermore, they explore the impact of using different eye detectors for training/enrolment and query phases of a face recognition system. These experiments provide an insight into the influence of eye localisation errors on the performance of face recognition systems and recommend a strategy for the design of training and test sets of a face recognition algorithm.
K1 automatic eye detectors
K1 open source implementations
K1 facial feature alignment
K1 face recognition performance
K1 error characteristics
K1 eye detection
K1 commercial face recognition systems
K1 query phases
K1 face normalisation
K1 manual eye annotations
K1 face recognition algorithms
K1 eye localisation errors
DO https://doi.org/10.1049/iet-bmt.2014.0037
UL https://digital-library.theiet.org/;jsessionid=1dggvcav63iij.x-iet-live-01content/journals/10.1049/iet-bmt.2014.0037
LA English
SN 2047-4938
YR 2015
OL EN