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
Une nouvelle méthode d'estimation de l'âge est présentée qui améliore les performances en fusionnant des informations complémentaires acquises à partir des caractéristiques globales et locales du visage. Analyse bidimensionnelle bidirectionnelle en composantes principales ((2D)2PCA) est utilisé pour la réduction de dimensionnalité et la construction d’espaces de fonctionnalités individuels. Chaque espace de fonctionnalités apporte une valeur de confiance qui est calculée par des machines vectorielles de support (SVM). Les valeurs de confiance de tous les traits du visage sont ensuite fusionnées pour l'estimation finale de l'âge. Les résultats expérimentaux démontrent que la fusion de plusieurs traits du visage peut permettre d’obtenir des gains de précision significatifs par rapport à n’importe quel trait unique. Enfin, nous proposons une méthode de fusion qui améliore encore la précision.
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
Li LU, Pengfei SHI, "Fusion of Multiple Facial Features for Age Estimation" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 9, pp. 1815-1818, September 2009, doi: 10.1587/transinf.E92.D.1815.
Abstract: A novel age estimation method is presented which improves performance by fusing complementary information acquired from global and local features of the face. Two-directional two-dimensional principal component analysis ((2D)2PCA) is used for dimensionality reduction and construction of individual feature spaces. Each feature space contributes a confidence value which is calculated by Support vector machines (SVMs). The confidence values of all the facial features are then fused for final age estimation. Experimental results demonstrate that fusing multiple facial features can achieve significant accuracy gains over any single feature. Finally, we propose a fusion method that further improves accuracy.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.1815/_p
Copier
@ARTICLE{e92-d_9_1815,
author={Li LU, Pengfei SHI, },
journal={IEICE TRANSACTIONS on Information},
title={Fusion of Multiple Facial Features for Age Estimation},
year={2009},
volume={E92-D},
number={9},
pages={1815-1818},
abstract={A novel age estimation method is presented which improves performance by fusing complementary information acquired from global and local features of the face. Two-directional two-dimensional principal component analysis ((2D)2PCA) is used for dimensionality reduction and construction of individual feature spaces. Each feature space contributes a confidence value which is calculated by Support vector machines (SVMs). The confidence values of all the facial features are then fused for final age estimation. Experimental results demonstrate that fusing multiple facial features can achieve significant accuracy gains over any single feature. Finally, we propose a fusion method that further improves accuracy.},
keywords={},
doi={10.1587/transinf.E92.D.1815},
ISSN={1745-1361},
month={September},}
Copier
TY - JOUR
TI - Fusion of Multiple Facial Features for Age Estimation
T2 - IEICE TRANSACTIONS on Information
SP - 1815
EP - 1818
AU - Li LU
AU - Pengfei SHI
PY - 2009
DO - 10.1587/transinf.E92.D.1815
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2009
AB - A novel age estimation method is presented which improves performance by fusing complementary information acquired from global and local features of the face. Two-directional two-dimensional principal component analysis ((2D)2PCA) is used for dimensionality reduction and construction of individual feature spaces. Each feature space contributes a confidence value which is calculated by Support vector machines (SVMs). The confidence values of all the facial features are then fused for final age estimation. Experimental results demonstrate that fusing multiple facial features can achieve significant accuracy gains over any single feature. Finally, we propose a fusion method that further improves accuracy.
ER -