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
    ASADA, H
    BRADY, M
    [J]. 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
    FORSYTH, D
    ZISSERMAN, A
    [J]. IMAGE AND VISION COMPUTING, 1990, 8 (01) : 42 - 49
  • [10] Grace JH, 1903, ALGEBRA INVARIANTS