Abstract
The accuracy of automatic face recognition systems depends on various factors among which robustness and accuracy of the face localization procedure, choice of an appropriate face-feature extraction procedure, as well as use of a suitable matching algorithm are the most important. Current systems perform relatively well whenever test images to be recognized are captured under conditions similar to those of the training images. However, they are not robust enough if there is a difference between test and training images. Changes in image characteristics such as noise, colour depth, background and compression all cause a drop in performance of even the best systems of today. At this point the main question is which image characteristics are the most important in terms of face recognition performance and how they affect the recognition accuracy. This paper addresses these issues and presents performance evaluation (Table 2.) of three popular subspace methods (PCA, LDA and ICA) using ten degraded versions of the XM2VTS face image database [10]. The presented experimental results show the effects of different changes in image characteristics on four score level fusion rules, namely, the maximum, minimum, sum and product rule. All of the feature extraction procedures as well as the fusion strategies are rather insensitive to the presence of noise, JPEG compression, colour depth reduction, and so forth, while on the other hand they all exhibit great sensitivity to degradations such as face occlusion and packet loss simulation
Links
BibTeX (Download)
@article{EV-Struc_2007,
title = {Impact of image degradations on the face recognition accuracy},
author = {Vitomir \v{S}truc and Nikola Pave\v{s}i\'{c}},
url = {http://luks.fe.uni-lj.si/nluks/wp-content/uploads/2016/09/EV2007.pdf},
year = {2007},
date = {2007-01-01},
journal = {Electrotechnical Review},
volume = {74},
number = {3},
pages = {145-150},
abstract = {The accuracy of automatic face recognition systems depends on various factors among which robustness and accuracy of the face localization procedure, choice of an appropriate face-feature extraction procedure, as well as use of a suitable matching algorithm are the most important. Current systems perform relatively well whenever test images to be recognized are captured under conditions similar to those of the training images. However, they are not robust enough if there is a difference between test and training images. Changes in image characteristics such as noise, colour depth, background and compression all cause a drop in performance of even the best systems of today. At this point the main question is which image characteristics are the most important in terms of face recognition performance and how they affect the recognition accuracy. This paper addresses these issues and presents performance evaluation (Table 2.) of three popular subspace methods (PCA, LDA and ICA) using ten degraded versions of the XM2VTS face image database [10]. The presented experimental results show the effects of different changes in image characteristics on four score level fusion rules, namely, the maximum, minimum, sum and product rule. All of the feature extraction procedures as well as the fusion strategies are rather insensitive to the presence of noise, JPEG compression, colour depth reduction, and so forth, while on the other hand they all exhibit great sensitivity to degradations such as face occlusion and packet loss simulation},
keywords = {biometrics, face recognition, ica, image degradations, lda, pca},
pubstate = {published},
tppubtype = {article}
}