Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Hybrid neural method for locating eyes in facial images
Autore:
Zhang, D; Peng, H; Wang, KQ;
Indirizzi:
Hong Kong Polytech Univ, Biometr Res Ctr, Dept Comp, Kowloon, Hong Kong, Peoples R China Hong Kong Polytech Univ Kowloon Hong Kong Peoples R China eoples R China Tsing Hua Univ, Dept Automat, Beijing 100084, Peoples R China Tsing Hua Univ Beijing Peoples R China 100084 ng 100084, Peoples R China Harbin Inst Technol, Dept Comp Sci & Engn, Harbin, Peoples R China Harbin Inst Technol Harbin Peoples R China ngn, Harbin, Peoples R China
Titolo Testata:
OPTICAL ENGINEERING
fascicolo: 10, volume: 40, anno: 2001,
pagine: 2151 - 2158
SICI:
0091-3286(200110)40:10<2151:HNMFLE>2.0.ZU;2-B
Fonte:
ISI
Lingua:
ENG
Soggetto:
FACE RECOGNITION; FEATURE-EXTRACTION; DEFORMABLE TEMPLATES;
Keywords:
eyes location; radial basis function networks; knowledge-based approach; hybrid neural method; face recognition;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Physical, Chemical & Earth Sciences
Engineering, Computing & Technology
--discip_EC--
Citazioni:
24
Recensione:
Indirizzi per estratti:
Indirizzo: Zhang, D Hong Kong Polytech Univ, Biometr Res Ctr, Dept Comp, Kowloon, Hong Kong, Peoples R China Hong Kong Polytech Univ Kowloon Hong Kong Peoples R China China
Citazione:
D. Zhang et al., "Hybrid neural method for locating eyes in facial images", OPT ENG, 40(10), 2001, pp. 2151-2158

Abstract

Locating facial features automatically in a scene is an essential but relatively unsolved problem. We develop a novel hybrid neural method for human eye location by the following stages: (1) facial images are preprocessed for normalization; (2) the candidate regions of eyes are detected using an improved version of radial basis function (RBF) networks, which is capable ofdealing with those facial images containing some changes of eye size or face orientation; and (3) a hierarchical knowledge-based approach is presented to evaluate these candidates and locate the positions of both eyes. The proposed method is tested on various face images. The experimental results illustrate the effectiveness of our method. (C) 2001 Society of Photo-Optical Instrumentation Engineers.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 25/01/20 alle ore 09:40:28