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
Este artigo propõe um novo método de reconhecimento facial baseado na projeção mútua de distribuições de características. O método proposto introduz uma nova medição robusta entre duas distribuições de características. Esta medição é calculada por uma média harmônica de dois valores de distância obtidos pela projeção de cada valor médio na distribuição de características oposta. O método proposto não requer análise de autovalores dos dois subespaços. Este método foi aplicado à tarefa de reconhecimento facial de sequência temporal de imagens. Resultados experimentais demonstram que o custo computacional foi melhorado sem degradação do desempenho de identificação em comparação com o método convencional.
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.
Copiar
Akira INOUE, Atsushi SATO, "Face Recognition Based on Mutual Projection of Feature Distributions" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 7, pp. 1878-1884, July 2008, doi: 10.1093/ietisy/e91-d.7.1878.
Abstract: This paper proposes a new face recognition method based on mutual projection of feature distributions. The proposed method introduces a new robust measurement between two feature distributions. This measurement is computed by a harmonic mean of two distance values obtained by projection of each mean value into the opposite feature distribution. The proposed method does not require eigenvalue analysis of the two subspaces. This method was applied to face recognition task of temporal image sequence. Experimental results demonstrate that the computational cost was improved without degradation of identification performance in comparison with the conventional method.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.7.1878/_p
Copiar
@ARTICLE{e91-d_7_1878,
author={Akira INOUE, Atsushi SATO, },
journal={IEICE TRANSACTIONS on Information},
title={Face Recognition Based on Mutual Projection of Feature Distributions},
year={2008},
volume={E91-D},
number={7},
pages={1878-1884},
abstract={This paper proposes a new face recognition method based on mutual projection of feature distributions. The proposed method introduces a new robust measurement between two feature distributions. This measurement is computed by a harmonic mean of two distance values obtained by projection of each mean value into the opposite feature distribution. The proposed method does not require eigenvalue analysis of the two subspaces. This method was applied to face recognition task of temporal image sequence. Experimental results demonstrate that the computational cost was improved without degradation of identification performance in comparison with the conventional method.},
keywords={},
doi={10.1093/ietisy/e91-d.7.1878},
ISSN={1745-1361},
month={July},}
Copiar
TY - JOUR
TI - Face Recognition Based on Mutual Projection of Feature Distributions
T2 - IEICE TRANSACTIONS on Information
SP - 1878
EP - 1884
AU - Akira INOUE
AU - Atsushi SATO
PY - 2008
DO - 10.1093/ietisy/e91-d.7.1878
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2008
AB - This paper proposes a new face recognition method based on mutual projection of feature distributions. The proposed method introduces a new robust measurement between two feature distributions. This measurement is computed by a harmonic mean of two distance values obtained by projection of each mean value into the opposite feature distribution. The proposed method does not require eigenvalue analysis of the two subspaces. This method was applied to face recognition task of temporal image sequence. Experimental results demonstrate that the computational cost was improved without degradation of identification performance in comparison with the conventional method.
ER -