Real-time parallel and cooperative recognition of facial images for an interactive visual human interface

Hasegawa, Osamu; Yokosawa, E.; Ishizuka, M.

doi:10.1109/icpr.1994.577210

Cited by 3 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With the face matching system of Turk and Pentland [24], a face is located tentatively by time-space filtering of moving images, and gray-scale fragments thus obtained are treated as potential facial patterns, while the ultimate judgment is made in the manner explained in the following. Information related to face movement may be used not only for face detection but also as a means for real-time manmachine interaction [58,59].…”

Section: Spotting a Face In A Scenementioning

confidence: 99%

Computer recognition of human face?A survey

Akamatsu

1999

Syst. Comp. Jpn.

View full text Add to dashboard Cite

The article presents the latest trends in computer‐based human face recognition. First, methods of facial pattern representation intended to identify persons using frontal face images are introduced as well as recent studies in extending those methods by giving flexibility in terms of face orientation and view. The FERET face recognition project, which is one of the driving forces to promote robustness in face recognition technology, is considered. In addition, computer face recognition is treated as an element of media processing for content search and editing of visual databases, and studies in computer face recognition that model human cognition in the face recognition process are surveyed. Finally, the state of the art in extracting facial patterns from visual scenes is analyzed. © 1999 Scripta Technica, Syst Comp Jpn, 30(10): 76–89, 1999

show abstract

Section: Spotting a Face In A Scenementioning

confidence: 99%

Computer recognition of human face?A survey

Akamatsu

1999

Syst. Comp. Jpn.

View full text Add to dashboard Cite

show abstract

“…The experience of realism is further enhanced when the computer is equipped with visual and auditory senses with which to perceive the user [1,3,6,9,10,12,20,21,23,[26][27][28]. In this symmetric situation, both the human and synthetic head can see and be seen, and can hear and be heard.…”

Section: Introductionmentioning

confidence: 99%

Reactive memories: an interactive talking-head

Devin

Hogg

2003

Image and Vision Computing

View full text Add to dashboard Cite

“…Esta e urna maneira de tratar as grandes varial'5es presentes na face, pais construimos urn modele que representa mais precisamente urn deterrninado tipo de face. Mesmo com a restri"'o de modelar urn determi- (3) Com as imagens normalizadas em rela<;iio a media formamas a matriz A, definida como conjunto de imagens exemplo a caracteriza<;iio de uma nova face apresentada ao sistema, segundo o modele defiuido pela componentes principals, e dada por k=l...M' (10) onde wk e o valor da proje<;iio da nova imagem r subtrafda da media do conjunto de imagens exemplo 1Ji sabre o k -esimo autovalor u'f e M' e a quantidade de autovalores em que a imagem vai ser projetada (Mt ~ M). A imagem codificada (4) como modele de componentes principals pode entlio ser caracterizada como o conjunto de pesos de proje,ao sabre os autovetores do modele defiuido via Obtemos entlio a matriz de autocorrela<;iio do conjunto de imagens definida como (5) (11) Os autovalores, .A;, e autovalores, 11;, da matriz C, satisfazem a seguinte re1a~iio :…”

unclassified

Sistema de Reconhecimento Facial Baseado em Análise de Componentes Principais

Neto

Ling²

1998

JCIS

View full text Add to dashboard Cite

Resumo -Neste trabalho mostramos a implementa,ao de urn sistema de reconhecimeuto facial. 0 sistema de reconhecimento facial emprega a analise de compcnentes principais de urn conjunto de imagens exemplo de faces para modelar a face. 0 modele de componentes principais obtido na ana-. lise das imagens exemplo e utilizado para extrair caracterfsticas das imageus faciais a serem reconhecidas pelo sistema. A classifical'lio das caracterfsticas obtidas e realizada com urn classificador de distancia minima 0 sistema obteve uma taxa de classifical'oes corretas de 97,70% quando testado com 435 imageus de 102 individuos.Abstract -We present the development and implementation of a face recognition system using principal component analysis to construct a face model from a training set of face images. The computed principal component face model is applied in the feature extraction task. We tested the system in the task of correctly classifying 435 images from 102 people with a minimum distance classifier. These images have a great deal of variations concerning position, scale, expression and illumination, even among images of the same person. The proposed system was able to handle such variations and achieved a recognition rate of97.70%.Palavras Chaves : reconhecimento facial, processamento de imagens, analise de componentes principais.

show abstract

Real-time parallel and cooperative recognition of facial images for an interactive visual human interface

Cited by 3 publications

References 3 publications

Computer recognition of human face?A survey

Computer recognition of human face?A survey

Reactive memories: an interactive talking-head

Sistema de Reconhecimento Facial Baseado em Análise de Componentes Principais

Contact Info

Product

Resources

About