Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
An integrated face recognition system based on multiscale local discriminatory features
Autore:
Hong, B; Tang, S;
Indirizzi:
Univ Massachusetts, Dept Elect & Comp Engn, N Dartmouth, MA 02747 USA UnivMassachusetts N Dartmouth MA USA 02747 gn, N Dartmouth, MA 02747 USA Univ Massachusetts, Dept Comp Sci, N Dartmouth, MA 02747 USA Univ Massachusetts N Dartmouth MA USA 02747 ci, N Dartmouth, MA 02747 USA
Titolo Testata:
PATTERN ANALYSIS AND APPLICATIONS
fascicolo: 4, volume: 4, anno: 2001,
pagine: 235 - 243
SICI:
1433-7541(2001)4:4<235:AIFRSB>2.0.ZU;2-Q
Fonte:
ISI
Lingua:
ENG
Soggetto:
NEURAL-NETWORK; IMAGES;
Keywords:
face recognition; feature extraction; pattern classification; wavelet transform;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
31
Recensione:
Indirizzi per estratti:
Indirizzo: Hong, B Univ Massachusetts, Dept Elect & Comp Engn, N Dartmouth, MA 02747 USA Univ Massachusetts N Dartmouth MA USA 02747 rtmouth, MA 02747 USA
Citazione:
B. Hong e S. Tang, "An integrated face recognition system based on multiscale local discriminatory features", PATTERN A A, 4(4), 2001, pp. 235-243

Abstract

Despite some successes, the process of Automatic Facial Recognition (AFR) remains a significant challenge when unconstrained imaging conditions are involved. The authors believe that this occurs because an effective feature extraction method of facial images has not been found so far. In this papera new approach to extract powerful local discriminatory features is described. First, the wavelet transform is used for extraction of multi-resolution coarse features, and then the emphasis is placed on the extraction of Multiscale fine Local Discriminatory Features (MLDFs). Instead of using traditional wavelet features, the authors examine the multiscale local statistical characteristics to derive stronger discriminatory features based on some important wavelet subbands. To efficiently utilise potentials of the extracted multi-MLDFs, an integrated recognition system is developed where the multi-classifiers first conduct the corresponding coarse classification, thena decision making scheme is used to associate different priorities with each of the classifiers to make the final recognition. Experiments have shownthat this scheme provides superior performance to popular methods, such asPrincipal Components Analysis (PCA or Eigenface), wavelet features, neuralnetworks, etc.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 25/02/20 alle ore 07:18:09