Improved cross-correlation for template matching on the Laplacian pyramid

被引：9

作者：

Bonmassar, G

Schwartz, EL

机构：

[1] Boston Univ, Dept Biomed Engn, Boston, MA 02215 USA

[2] Boston Univ, Dept Cognit & Neural Syst, Boston, MA 02215 USA

来源：

PATTERN RECOGNITION LETTERS | 1998年 / 19卷 / 08期

关键词：

correlation; Laplacian pyramid; template matching; pyramid architectures;

D O I：

10.1016/S0167-8655(98)00056-7

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Template matching (1) via cross-correlation on Laplacian pyramid image architectures has been traditionally performed in a "coarse" to "fine" fashion. In the present paper, we show that by computing cross-correlation within each level of the pyramid independently, and considering the sum across (expanded) levels, a significant improvement in Peak to Correlation Energy (PCE) (Kumar and Hassebrook, 1992) is obtained. This result is illustrated with a number of numerical examples. (C) 1998 Published by Elsevier Science B.V. All rights reserved.

引用

页码：765 / 770

页数：6

共 12 条

[1] A FAST TECHNIQUE FOR RECURSIVE SCENE MATCHING USING PYRAMIDS [J].