Scale space semi-local invariants

被引:20
作者
Bruckstein, AM [1 ]
Rivlin, E [1 ]
Weiss, I [1 ]
机构
[1] UNIV MARYLAND, CTR AUTOMAT RES, COMP VIS LAB, COLLEGE PK, MD 20742 USA
关键词
local invariants; object recognition; scale space;
D O I
10.1016/S0262-8856(96)01140-7
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper we discuss a new approach to invariant signatures for recognizing curves under viewing distortions and partial occlusion. The approach is intended to overcome the ill-posed problem of finding derivatives, on which local invariants usually depend. The basic idea is to use invariant finite differences, with a scale parameter that determines the size of the differencing interval. The scale parameter is allowed to vary so that we obtain a 'scale space'-like invariant representation of the curve, with larger difference intervals corresponding to larger, coarser scales. In this new representation, each traditional local invariant is replaced by a scale-dependent range of invariants. Thus, instead of invariant signature curves we obtain invariant signature surfaces in a 3-D invariant 'scale space'.
引用
收藏
页码:335 / 344
页数:10
相关论文
共 33 条
[1]   THE CURVATURE PRIMAL SKETCH [J].
ASADA, H ;
BRADY, M .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1986, 8 (01) :2-14
[2]  
BARRETT E, 1991, CVGIP IU, V53, P45
[3]  
BRUCKSTEIN AM, 1993, CVGIP-IMAG UNDERSTAN, V58, P49, DOI 10.1006/ciun.1993.1031
[4]  
BRUCKSTEIN AM, 1990, UNPUB AT T TECHN JUL
[5]  
BRUCKSTEIN AM, 1990, SIMILARITY INVARIANT
[6]  
Buchin S., 1983, AFFINE DIFFERENTIAL
[7]  
CARTAN E, 1995, OEUVRES COMPLETES, P1727
[8]  
Duda R. O., 1973, PATTERN CLASSIFICATI, V3
[9]   SHAPE FROM SHADING IN THE LIGHT OF MUTUAL ILLUMINATION [J].
FORSYTH, D ;
ZISSERMAN, A .
IMAGE AND VISION COMPUTING, 1990, 8 (01) :42-49
[10]  
Grace JH, 1903, ALGEBRA INVARIANTS