The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Cela fait plus d'une décennie que l'approche « Eigenfaces » en matière de reconnaissance automatique des visages, ainsi que d'autres méthodes basées sur l'apparence, ont fait forte impression sur la communauté de recherche en vision par ordinateur et ont contribué à susciter l'intérêt pour les systèmes de vision utilisés pour prendre en charge la biométrie et l'interface homme-machine. . Dans cet article, je donne un point de vue personnel sur la motivation initiale du travail, certaines des forces et des limites de l'approche, ainsi que les progrès réalisés au cours des années qui ont suivi. Les approches de reconnaissance basées sur l'apparence complètent les approches basées sur les caractéristiques ou les formes, et un système pratique de reconnaissance faciale devrait comporter des éléments des deux. Eigenfaces n'est pas une approche générale de la reconnaissance, mais plutôt un outil parmi tant d'autres à appliquer et à évaluer dans le contexte approprié.
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.
Copier
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
Copier
@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},}
Copier
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 -