Improving object recognition by transforming Gabor filter responses

被引：20

作者：

Potzsch, M

Kruger, N

vonderMalsburg, C

机构：

[1] UNIV SO CALIF,DEPT COMP SCI,LOS ANGELES,CA 90089

[2] UNIV SO CALIF,NEUROBIOL SECT,LOS ANGELES,CA 90089

来源：

NETWORK-COMPUTATION IN NEURAL SYSTEMS | 1996年 / 7卷 / 02期

关键词：

D O I：

10.1088/0954-898X/7/2/015

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Previous work described a biologically motivated object recognition system with Gabor wavelets as basic feature type. These features are robust against slight distortion, rotation and variation in illumination. We here describe extensions of the system that address image variance due to arbitrary in-plane rotation, substantial scale changes and moderate depth rotation of objects, and to background variation, using simple linear transformation of the Gabor filter responses. The performance of the system is enhanced significantly.

引用

页码：341 / 347

页数：7

共 12 条

[1] 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

[2] RELATIONS BETWEEN THE STATISTICS OF NATURAL IMAGES AND THE RESPONSE PROPERTIES OF CORTICAL-CELLS [J].

FIELD, DJ .

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1987, 4 (12) :2379-2394

[3]

FISER J, 1994, INVEST OPHTH VIS SCI, V35, P1625

[4] AN EVALUATION OF THE TWO-DIMENSIONAL GABOR FILTER MODEL OF SIMPLE RECEPTIVE-FIELDS IN CAT STRIATE CORTEX [J].

JONES, JP ;

PALMER, LA .

JOURNAL OF NEUROPHYSIOLOGY, 1987, 58 (06) :1233-1258

[5] 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

[6]

LADES M, 1994, THESIS RUHR U BOCHUM

[7]

Maurer T., 1995, P INT WORKSH AUT FAC

[8]

Potzsch M., 1994, 9404 IRINI RUHR U BO

[9] NEURONAL MECHANISMS OF OBJECT RECOGNITION [J].

TANAKA, K .

SCIENCE, 1993, 262 (5134) :685-688

[10]

VONDERMALSBURG C, 1981, MODELS NEURAL NETWOR, V2, P95

← 1 2 →