It has been over a decade since the "Eigenfaces" approach to automatic face recognition, and other appearance-based methods, made an impression on the computer vision research community and helped spur interest in vision systems being used to support biometrics and human-computer interface. In this paper I give a personal view of the original motivation for the work, some of the strengths and limitation of the approach, and progress in the years since. Appearance-based approaches to recognition complement feature- or shape-based approaches, and a practical face recognition system should have elements of both. Eigenfaces is not a general approach to recognition, but rather one tool out of many to be applied and evaluated in the appropriate context.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Matthew TURK, "A Random Walk through Eigenspace" in IEICE TRANSACTIONS on Information,
vol. E84-D, no. 12, pp. 1586-1595, December 2001, doi: .
Abstract: It has been over a decade since the "Eigenfaces" approach to automatic face recognition, and other appearance-based methods, made an impression on the computer vision research community and helped spur interest in vision systems being used to support biometrics and human-computer interface. In this paper I give a personal view of the original motivation for the work, some of the strengths and limitation of the approach, and progress in the years since. Appearance-based approaches to recognition complement feature- or shape-based approaches, and a practical face recognition system should have elements of both. Eigenfaces is not a general approach to recognition, but rather one tool out of many to be applied and evaluated in the appropriate context.
URL: https://global.ieice.org/en_transactions/information/10.1587/e84-d_12_1586/_p
Copy
@ARTICLE{e84-d_12_1586,
author={Matthew TURK, },
journal={IEICE TRANSACTIONS on Information},
title={A Random Walk through Eigenspace},
year={2001},
volume={E84-D},
number={12},
pages={1586-1595},
abstract={It has been over a decade since the "Eigenfaces" approach to automatic face recognition, and other appearance-based methods, made an impression on the computer vision research community and helped spur interest in vision systems being used to support biometrics and human-computer interface. In this paper I give a personal view of the original motivation for the work, some of the strengths and limitation of the approach, and progress in the years since. Appearance-based approaches to recognition complement feature- or shape-based approaches, and a practical face recognition system should have elements of both. Eigenfaces is not a general approach to recognition, but rather one tool out of many to be applied and evaluated in the appropriate context.},
keywords={},
doi={},
ISSN={},
month={December},}
Copy
TY - JOUR
TI - A Random Walk through Eigenspace
T2 - IEICE TRANSACTIONS on Information
SP - 1586
EP - 1595
AU - Matthew TURK
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E84-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2001
AB - It has been over a decade since the "Eigenfaces" approach to automatic face recognition, and other appearance-based methods, made an impression on the computer vision research community and helped spur interest in vision systems being used to support biometrics and human-computer interface. In this paper I give a personal view of the original motivation for the work, some of the strengths and limitation of the approach, and progress in the years since. Appearance-based approaches to recognition complement feature- or shape-based approaches, and a practical face recognition system should have elements of both. Eigenfaces is not a general approach to recognition, but rather one tool out of many to be applied and evaluated in the appropriate context.
ER -