ON GEOMETRIC HASHING AND THE GENERALIZED HOUGH TRANSFORM

被引：21

作者：

HECKER, YC ^{[1
]}

BOLLE, RM ^{[1
]}

机构：

[1] IBM CORP,THOMAS J WATSON RES CTR,EXPLORATORY COMP VIS GRP,YORKTOWN HTS,NY 10598

来源：

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS | 1994年 / 24卷 / 09期

关键词：

D O I：

10.1109/21.310509

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

The generalized Hough transform and geometric hashing are two contemporary paradigms for model-based object recognition. Both schemes simultaneously find instances of objects in a scene and determine the location and orientation of these instances. The methods encode the models for the objects in a similar fashion and object recognition is achieved by image features ''voting'' for object models. For both schemes, the object recognition time is largely independent of the number of objects that are encoded in the object-model database. This paper puts the two schemes in perspective and examines differences and similarities. We also study the object representation techniques and discuss how the object representations are used for object recognition and position estimation.

引用

页码：1328 / 1338

页数：11

共 27 条

[11]

HECKER YC, 1991, 36 SPIE P GEOM METH

[12]

HONG J, 1988, 9TH P INT C PATT REC

[13]

Hough P.V.C., 1962, US Patent, Patent No. 3069654

[14] A SURVEY OF THE HOUGH TRANSFORM [J].

ILLINGWORTH, J ;

KITTLER, J .

COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1988, 44 (01) :87-116

[15]

KALVIN A, 1988, INT J ROBOT RES, V5, P38

[16] FINDING CIRCLES BY AN ARRAY OF ACCUMULATORS [J].

KIMME, C ;

BALLARD, D ;

SKLANSKY, J .

COMMUNICATIONS OF THE ACM, 1975, 18 (02) :120-122

[17]

KISHON E, 1987, P AAAI WORKSHOP SPAT, P250

[18]

Lamdan Y., 1988, Second International Conference on Computer Vision (IEEE Cat. No.88CH2664-1), P238, DOI 10.1109/CCV.1988.589995

[19]

LAMDAN Y, 1989, 467 NEW YORK U COUR

[20]

LAMDAN Y, 1989, THESIS NEW YORK U

← 1 2 3 →