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
DAUGMAN, JG
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1988, 36 (07): : 1169 - 1179
[4] DISTORTION INVARIANT OBJECT RECOGNITION IN THE DYNAMIC LINK ARCHITECTURE
LADES, M
VORBRUGGEN, JC
BUHMANN, J
LANGE, J
VANDERMALSBURG, C
WURTZ, RP
KONEN, W
[J]. 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
PHILLIPS, RJ
[J]. PERCEPTION & PSYCHOPHYSICS, 1972, 12 (05): : 425 - &
[8] WURTZ RP, 1995, MULTILAYER DYNAMIC L, V41

← 1 →