A paradigm for invariant object recognition of brightness, optical flow and binocular disparity images

被引:23
作者
Jacobson, Lowell [1 ]
Wechsler, Harry [1 ]
机构
[1] Univ Minnesota, Dept Elect Engn, Minneapolis, MN 55455 USA
基金
美国国家科学基金会;
关键词
Binocular disparity; invariant object recognition; spatial-frequency analysis; optical flow; Wigner distribution;
D O I
10.1016/0167-8655(82)90053-8
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We suggest the Wigner distribution (WD) for the analysis of 2-D images. The WD can be used to rigorously define a local power-spectrum at each point of an image. Furthermore, an invariant representation of a given image can he obtained by applying a complex-logarithmic (CL) conformal mapping to the spatial-frequency domain of the WD. The representation is such that all local spectra are invariant, within a linear shift, with respect to linear transformations of the image. A discrete WD has been implemented and results are shown. We next describe how the same CL-mapped WD of a scalar or vector field could be used for binocular disparity and motion analysis, respectively, where the goal is object recognition.
引用
收藏
页码:61 / 68
页数:8
相关论文
共 19 条
[1]   WIGNER DISTRIBUTION FUNCTION AND ITS OPTICAL PRODUCTION [J].
BARTELT, HO ;
BRENNER, KH ;
LOHMANN, AW .
OPTICS COMMUNICATIONS, 1980, 32 (01) :32-38
[2]  
BASTIAANS MJ, 1979, J OPT SOC AM, V69, P1710, DOI 10.1364/JOSA.69.001710
[3]   WIGNER DISTRIBUTION FUNCTION APPLIED TO OPTICAL SIGNALS AND SYSTEMS [J].
BASTIAANS, MJ .
OPTICS COMMUNICATIONS, 1978, 25 (01) :26-30
[4]   POSITION, ROTATION, AND SCALE INVARIANT OPTICAL CORRELATION [J].
CASASENT, D ;
PSALTIS, D .
APPLIED OPTICS, 1976, 15 (07) :1795-1799
[5]  
CLAASEN TACM, 1980, PHILIPS J RES, V35, P372
[6]  
CLAASEN TACM, 1980, PHILIPS J RES, V35, P217
[7]  
CLAASEN TACM, 1980, PHILIPS J RES, V35, P276
[8]  
DEBRUIJN NG, 1967, INEQUALITIES, P57
[10]  
JACOBSON L, 1982, NEW PARADIGM COMPUTA