Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Invariant gender identification
Autore:
Tolba, AS;
Indirizzi:
Kuwait Univ, Dept Phys, Safat 13060, Kuwait Kuwait Univ Safat Kuwait 13060 wait Univ, Dept Phys, Safat 13060, Kuwait
Titolo Testata:
DIGITAL SIGNAL PROCESSING
fascicolo: 3, volume: 11, anno: 2001,
pagine: 222 - 240
SICI:
1051-2004(200107)11:3<222:IGI>2.0.ZU;2-B
Fonte:
ISI
Lingua:
ENG
Soggetto:
PRINCIPAL-COMPONENT; FACE; RECOGNITION; DIFFERENCE; CLASSIFICATION; NETWORKS; WOMEN; MEN;
Keywords:
gender identification; face recognition; neural networks; learning vector quantization; radial basis functions;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
27
Recensione:
Indirizzi per estratti:
Indirizzo: Tolba, AS Kuwait Univ, Dept Phys, POB 5969, Safat 13060, Kuwait Kuwait Univ POB 5969 Safat Kuwait 13060 69, Safat 13060, Kuwait
Citazione:
A.S. Tolba, "Invariant gender identification", DIGIT SIG P, 11(3), 2001, pp. 222-240

Abstract

In this paper, we address the problem of gender identification using different neural network classifiers: a learning vector quantization (LVQ) network and a radial basis function (RBF) network. Our results indicate that it is more favorable to use either the LVQ network or the RBF network than anyfeature-based methods. We present results showing identification of genderwith. a hit rate of 100% in the case of a LVQ network and 98.04% in the case of an RBF network. When hair information was excluded, the best LVQ classifier resulted in 95.1% correct identification. We show that while the twomodels are nearly accurate, the RBF model learns the task considerably faster than the LVQ model. These results are favorable compared with eigen-decomposition-based techniques. The effect of head covers (e.g., a scarf) usedby both men and women on system performance is studied. (C) 2001 Academic Press.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 21/01/20 alle ore 07:03:36