Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Scale invariant face detection and classification method using shift invariant features extracted from log-polar image
Autore:
Hotta, K; Mishima, T; Kurita, T;
Indirizzi:
Saitama Univ, Saitama 3388570, Japan Saitama Univ Saitama Japan 3388570Saitama Univ, Saitama 3388570, Japan Natl Inst Adv Ind Sci & Technol, Neurosci Res Inst, Tsukuba, Ibaraki 3058568, Japan Natl Inst Adv Ind Sci & Technol Tsukuba Ibaraki Japan 3058568 8568, Japan
Titolo Testata:
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
fascicolo: 7, volume: E84D, anno: 2001,
pagine: 867 - 878
SICI:
0916-8532(200107)E84D:7<867:SIFDAC>2.0.ZU;2-Q
Fonte:
ISI
Lingua:
ENG
Soggetto:
DYNAMIC ATTENTION MAP; RECOGNITION;
Keywords:
scale invariance; face detection; face recognition; log-polar image; shift invariant features;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
39
Recensione:
Indirizzi per estratti:
Indirizzo: Hotta, K Saitama Univ, Saitama 3388570, Japan Saitama Univ Saitama Japan3388570 Univ, Saitama 3388570, Japan
Citazione:
K. Hotta et al., "Scale invariant face detection and classification method using shift invariant features extracted from log-polar image", IEICE T INF, E84D(7), 2001, pp. 867-878

Abstract

This paper presents a scale invariant face detection and classification method which uses shift invariant features extracted from a Log-Polar image. Scale changes of a face in an image are represented as shift along the horizontal axis in the Log-Polar image. In order to obtain scale invariant features, shift invariant features are extracted from each row of the Log-Polarimage. Autocorrelations, Fourier spectrum, and PARCOR coefficients are used as shift invariant features. These features are then combined with simpleclassification methods based on Linear Discriminant Analysis to realize scale invariant face detection and classification. The effectiveness of the proposed face detection method is confirmed by experiments using face imagescaptured under different scales, backgrounds, illuminations, and dates. Toevaluate the proposed face classification method, we performed experimentsusing 2, 800 face images with 7 scales under 2 different backgrounds and face images of 52 persons.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 20/01/20 alle ore 04:45:18