Affine invariants for object recognition using the wavelet transform

被引:42
作者
Khalil, MI [1 ]
Bayoumi, MA [1 ]
机构
[1] Queens Univ, Dept Elect & Comp Engn, Kingston, ON K7L 3N6, Canada
关键词
affine transformation; dyadic wavelet transform; planar object recognition; invariant features;
D O I
10.1016/S0167-8655(01)00102-7
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Dyadic wavelet transform has been used to derive affine invariant functions. The invariant functions are based on the dyadic wavelet transform of the object boundary. Three invariant functions have been calculated using different numbers of dyadic levels. Experimental results show that these invariant functions outperform some traditional invariant functions. The stability of these invariant functions have been tested for a large perspective transformation. (C) 2002 Elsevier Science B.V. All rights reserved.
引用
收藏
页码:57 / 72
页数:16
相关论文
共 20 条
[1]   Geometric and illumination invariants for object recognition [J].
Alferez, R ;
Wang, YF .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1999, 21 (06) :505-536
[2]  
[Anonymous], 1998, PHYS A
[3]  
[Anonymous], 1993, RECOGNIZING PLANAR O
[4]   APPLICATION OF AFFINE-INVARIANT FOURIER DESCRIPTORS TO RECOGNITION OF 3-D OBJECTS [J].
ARBTER, K ;
SNYDER, WE ;
BURKHARDT, H ;
HIRZINGER, G .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1990, 12 (07) :640-647
[5]   A linear signal decomposition approach to affine invariant contour identification [J].
Cyganski, D ;
Vaz, RF .
PATTERN RECOGNITION, 1995, 28 (12) :1845-1853
[6]  
Guggenheimer HN., 1963, Differential Geometry
[7]   VISUAL-PATTERN RECOGNITION BY MOMENT INVARIANTS [J].
HU, M .
IRE TRANSACTIONS ON INFORMATION THEORY, 1962, 8 (02) :179-&
[8]  
JIN Q, 1992, 11TH IAPR INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, PROCEEDINGS, VOL I, P742, DOI 10.1109/ICPR.1992.201667
[9]   AFFINE INVARIANT MODEL-BASED OBJECT RECOGNITION [J].
LAMDAN, Y ;
SCHWARTZ, JT ;
WOLFSON, HJ .
IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, 1990, 6 (05) :578-589
[10]  
MALLAT S, 1992, IEEE T PATTERN ANAL, V14, P7