Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Eigenpaxels and a neural-network approach to image classification
Autore:
McGuire, P; DEleuterio, GMT;
Indirizzi:
C Core, St Johns, NF A1B 3X5, Canada C Core St Johns NF Canada A1B 3X5C Core, St Johns, NF A1B 3X5, Canada Univ Toronto, Toronto, ON M3H 5T6, Canada Univ Toronto Toronto ON Canada M3H 5T6 ronto, Toronto, ON M3H 5T6, Canada
Titolo Testata:
IEEE TRANSACTIONS ON NEURAL NETWORKS
fascicolo: 3, volume: 12, anno: 2001,
pagine: 625 - 635
SICI:
1045-9227(200105)12:3<625:EAANAT>2.0.ZU;2-Y
Fonte:
ISI
Lingua:
ENG
Soggetto:
NATURAL IMAGES; CURVED OBJECTS; RECOGNITION; REPRESENTATION; ORGANIZATION;
Keywords:
face recognition; hybrid system; image classification; principal components;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
23
Recensione:
Indirizzi per estratti:
Indirizzo: McGuire, P C Core, St Johns, NF A1B 3X5, Canada C Core St Johns NF CanadaA1B 3X5 St Johns, NF A1B 3X5, Canada
Citazione:
P. McGuire e G.M.T. D'Eleuterio, "Eigenpaxels and a neural-network approach to image classification", IEEE NEURAL, 12(3), 2001, pp. 625-635

Abstract

A expansion encoding approach to image classification is presented. Localized principal components or "eigenpaxels" are used as a set of basis functions to represent images. That is, principal-component analysis is applied locally rather than on the entire image, The "eigenpaxels" are statisticallydetermined using a database of the images of interest. Classification based on visual similarity is achieved through the use of a single-layer error-correcting neural network. Expansion encoding and the technique of subsampling are key elements in the processing stages of the eigen paxel algorithm. Tested using a database of frontal face images consisting of 40 individuals, the algorithm exhibits equivallent performance to other comparable but more cumbersome methods. In addition, the technique is shown to be robust tovarious types of image noise.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 23/01/20 alle ore 03:55:46