Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Face distributions in similarity space under varying head pose
Autore:
Sherrah, J; Gong, S; Ong, EJ;
Indirizzi:
Univ London Queen Mary & Westfield Coll, Dept Comp Sci, London E1 4NS, England Univ London Queen Mary & Westfield Coll London England E1 4NS S, England
Titolo Testata:
IMAGE AND VISION COMPUTING
fascicolo: 12, volume: 19, anno: 2001,
pagine: 807 - 819
SICI:
0262-8856(20011001)19:12<807:FDISSU>2.0.ZU;2-P
Fonte:
ISI
Lingua:
ENG
Soggetto:
REPRESENTATION; RECOGNITION;
Keywords:
Gabor filters; head pose estimation; similarity representation; face recognition;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
25
Recensione:
Indirizzi per estratti:
Indirizzo: Sherrah, J Univ London Queen Mary & Westfield Coll, Dept Comp Sci, Mile End Rd, London E1 4NS, England Univ London Queen Mary & Westfield Coll Mile End Rd London England E1 4NS
Citazione:
J. Sherrah et al., "Face distributions in similarity space under varying head pose", IMAGE VIS C, 19(12), 2001, pp. 807-819

Abstract

Real-time identity-independent estimation of head pose from prototype images is a perplexing task requiring pose-invariant face detection. The problem is exacerbated by changes in illumination, identity and facial position. We approach the problem using a view-based statistical learning technique based on similarity of images to prototypes. For this method to be effective, facial images must be transformed in such a way as to emphasise differences in pose while suppressing differences in identity. We investigate appropriate transformations for use with a similarity-to-prototypes philosophy. The results show that orientation-selective Gabor filters enhance differences in pose and that different filter orientations are optimal at different poses. In contrast, principal component analysis (PCA) was found to provide an identity-invariant representation in which similarities can be calculated more robustly. We also investigate the angular resolution at which pose changes can be resolved using our methods. An angular resolution of 10 degrees was found to be sufficiently discriminable at some poses but not at others, while 20 degrees is quite acceptable at most poses. (C) 2001 Elsevier Science B.V. All rights reserved.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 25/01/20 alle ore 00:28:35