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
O reconhecimento facial é uma das áreas de pesquisa mais ativas no reconhecimento de padrões, não apenas porque o rosto é uma característica biométrica humana do ser humano, mas também porque existem muitas aplicações potenciais do reconhecimento facial que vão desde interações humano-computador até autenticação, segurança e vigilância. Este artigo apresenta uma abordagem para pose de reconhecimento de imagem de rosto humano invariante. O esquema proposto é baseado na análise de transformadas discretas de cosseno (DCT) e transformadas wavelet discretas (DWT) de imagens faciais. A partir dos coeficientes de domínio DCT e DWT, que descrevem as informações faciais, construímos um vetor de características compacto e significativo, usando medidas estatísticas simples e quantização. Este vetor de recursos é chamado de recursos de frequência dominante híbrida. Em seguida, aplicamos uma combinação dos L2 e Lq métrica para classificar os recursos de frequência dominante híbrida para a classe de uma pessoa. O objetivo do sistema proposto é superar a alta necessidade de espaço de memória, a alta carga computacional e os problemas de retreinamento dos métodos anteriores. O sistema proposto é testado usando vários bancos de dados de faces e os resultados experimentais são comparados com um método Eigenface bem conhecido. O método proposto apresenta bom desempenho, robustez, estabilidade e precisão sem necessitar de normalização geométrica. Além disso, o método proposto possui baixo custo computacional, requer pouco espaço de memória e pode superar problemas de retreinamento.
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
I Gede Pasek Suta WIJAYA, Keiichi UCHIMURA, Zhencheng HU, "Pose Invariant Face Recognition Based on Hybrid Dominant Frequency Features" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 8, pp. 2153-2162, August 2008, doi: 10.1093/ietisy/e91-d.8.2153.
Abstract: Face recognition is one of the most active research areas in pattern recognition, not only because the face is a human biometric characteristics of human being but also because there are many potential applications of the face recognition which range from human-computer interactions to authentication, security, and surveillance. This paper presents an approach to pose invariant human face image recognition. The proposed scheme is based on the analysis of discrete cosine transforms (DCT) and discrete wavelet transforms (DWT) of face images. From both the DCT and DWT domain coefficients, which describe the facial information, we build compact and meaningful features vector, using simple statistical measures and quantization. This feature vector is called as the hybrid dominant frequency features. Then, we apply a combination of the L2 and Lq metric to classify the hybrid dominant frequency features to a person's class. The aim of the proposed system is to overcome the high memory space requirement, the high computational load, and the retraining problems of previous methods. The proposed system is tested using several face databases and the experimental results are compared to a well-known Eigenface method. The proposed method shows good performance, robustness, stability, and accuracy without requiring geometrical normalization. Furthermore, the purposed method has low computational cost, requires little memory space, and can overcome retraining problem.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.8.2153/_p
Copiar
@ARTICLE{e91-d_8_2153,
author={I Gede Pasek Suta WIJAYA, Keiichi UCHIMURA, Zhencheng HU, },
journal={IEICE TRANSACTIONS on Information},
title={Pose Invariant Face Recognition Based on Hybrid Dominant Frequency Features},
year={2008},
volume={E91-D},
number={8},
pages={2153-2162},
abstract={Face recognition is one of the most active research areas in pattern recognition, not only because the face is a human biometric characteristics of human being but also because there are many potential applications of the face recognition which range from human-computer interactions to authentication, security, and surveillance. This paper presents an approach to pose invariant human face image recognition. The proposed scheme is based on the analysis of discrete cosine transforms (DCT) and discrete wavelet transforms (DWT) of face images. From both the DCT and DWT domain coefficients, which describe the facial information, we build compact and meaningful features vector, using simple statistical measures and quantization. This feature vector is called as the hybrid dominant frequency features. Then, we apply a combination of the L2 and Lq metric to classify the hybrid dominant frequency features to a person's class. The aim of the proposed system is to overcome the high memory space requirement, the high computational load, and the retraining problems of previous methods. The proposed system is tested using several face databases and the experimental results are compared to a well-known Eigenface method. The proposed method shows good performance, robustness, stability, and accuracy without requiring geometrical normalization. Furthermore, the purposed method has low computational cost, requires little memory space, and can overcome retraining problem.},
keywords={},
doi={10.1093/ietisy/e91-d.8.2153},
ISSN={1745-1361},
month={August},}
Copiar
TY - JOUR
TI - Pose Invariant Face Recognition Based on Hybrid Dominant Frequency Features
T2 - IEICE TRANSACTIONS on Information
SP - 2153
EP - 2162
AU - I Gede Pasek Suta WIJAYA
AU - Keiichi UCHIMURA
AU - Zhencheng HU
PY - 2008
DO - 10.1093/ietisy/e91-d.8.2153
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2008
AB - Face recognition is one of the most active research areas in pattern recognition, not only because the face is a human biometric characteristics of human being but also because there are many potential applications of the face recognition which range from human-computer interactions to authentication, security, and surveillance. This paper presents an approach to pose invariant human face image recognition. The proposed scheme is based on the analysis of discrete cosine transforms (DCT) and discrete wavelet transforms (DWT) of face images. From both the DCT and DWT domain coefficients, which describe the facial information, we build compact and meaningful features vector, using simple statistical measures and quantization. This feature vector is called as the hybrid dominant frequency features. Then, we apply a combination of the L2 and Lq metric to classify the hybrid dominant frequency features to a person's class. The aim of the proposed system is to overcome the high memory space requirement, the high computational load, and the retraining problems of previous methods. The proposed system is tested using several face databases and the experimental results are compared to a well-known Eigenface method. The proposed method shows good performance, robustness, stability, and accuracy without requiring geometrical normalization. Furthermore, the purposed method has low computational cost, requires little memory space, and can overcome retraining problem.
ER -