TRAINABLE METHOD OF PARAMETRIC SHAPE-DESCRIPTION

被引：96

作者：

COOTES, TF

COOPER, DH

TAYLOR, CJ

GRAHAM, J

机构：

[1] Department of Medical Biophysics. University of Manchester, Manchester, M13 9PT, Oxford Road

来源：

IMAGE AND VISION COMPUTING | 1992年 / 10卷 / 05期

关键词：

FLEXIBLE SHAPE MODELS; DEFORMABLE TEMPLATES;

D O I：

10.1016/0262-8856(92)90044-4

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We have developed a trainable method of shape representation which can automatically capture the invariant properties of a class of shapes, and provide a compact parametric description of variability. We have applied the method to a family of flexible ribbons (worms), and to heart shapes in echocardiograms. We show that in both cases a natural parameterization of shape results.

引用

页码：289 / 294

页数：6

共 17 条

[1]

Bookstein F., 1998, MORPHOMETRIC TOOLS L, V54, P398

[2] PRINCIPAL WARPS - THIN-PLATE SPLINES AND THE DECOMPOSITION OF DEFORMATIONS [J].

BOOKSTEIN, FL .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1989, 11 (06) :567-585

[3]

CHIN R, 1986, COMPUT SURV, V18

[4] AN OBJECT LOCATION STRATEGY USING SHAPE AND GREY-LEVEL MODELS [J].

COOPER, DH ;

BRYSON, N ;

TAYLOR, CJ .

IMAGE AND VISION COMPUTING, 1989, 7 (01) :50-56

[5]

COOPER DH, 1991, 2ND P BR MACH VISION, P185

[6]

FUKUNAGA K, 1970, IEEE T COMPUT APR, V19

[7]

Gill P. E., 1981, PRACTICAL OPTIMIZATI

[8]

Gower J. C., 1982, MATH SCI, V7, P1

[9]

Grimson W. E. L., 1990, OBJECT RECOGNITION C

[10]

HILL A, 1991, 2ND P BR MACH VIS C

← 1 2 →