Object recognition robust under translations, deformations, and changes in background

被引：57

作者：

Wurtz, RP

机构：

[1] Institut Für Neuroinformatik, Ruhr-Universität Bochum

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 1997年 / 19卷 / 07期

关键词：

object recognition; face recognition; coarse-to-fine strategy; parallel processing; Gabor function; wavelet transform; image pyramid; correspondence problem; background independence;

D O I：

10.1109/34.598234

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Recognition systems based on model matching using low level features often fail due to a variation in background. As a solution, I present a system for the recognition of human faces independent of hairstyle. Correspondence maps between an image and a model are established by coarse-fine matching in a Gabor pyramid. These are used for hierarchical recognition.

引用

页码：769 / 775

页数：7

共 8 条

[1]

[Anonymous], 1992, THEORY

[2]

BICHSEL M, 1995, INT WORKSH AUT FAC G

[3] COMPLETE DISCRETE 2-D GABOR TRANSFORMS BY NEURAL NETWORKS FOR IMAGE-ANALYSIS AND COMPRESSION [J].

DAUGMAN, JG .

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1988, 36 (07) :1169-1179

[4] DISTORTION INVARIANT OBJECT RECOGNITION IN THE DYNAMIC LINK ARCHITECTURE [J].

LADES, M ;

VORBRUGGEN, JC ;

BUHMANN, J ;

LANGE, J ;

VANDERMALSBURG, C ;

WURTZ, RP ;

KONEN, W .

IEEE TRANSACTIONS ON COMPUTERS, 1993, 42 (03) :300-311

[5]

LEE TS, 1996, IEEE T PATTERN ANAL, V18

[6]

McKenna SJ, 1997, LECT NOTES COMPUT SC, V1206, P35, DOI 10.1007/BFb0015977

[7] WHY ARE FACES HARD TO RECOGNIZE IN PHOTOGRAPHIC NEGATIVE [J].

PHILLIPS, RJ .

PERCEPTION & PSYCHOPHYSICS, 1972, 12 (05) :425-&

[8]

WURTZ RP, 1995, MULTILAYER DYNAMIC L, V41

← 1 →