Representations that uniquely characterize images module translation, rotation, and scaling

被引：25

作者：

Brandt, RD

Lin, F

机构：

[1] WAYNE STATE UNIV,DEPT ELECT & COMP ENGN,DETROIT,MI 48202

[2] INTELLIGENT DEVICES INC,GLEN ELLYN,IL 60137

来源：

PATTERN RECOGNITION LETTERS | 1996年 / 17卷 / 09期

基金：

美国国家科学基金会;

关键词：

invariant; translation; rotation; scaling;

D O I：

10.1016/0167-8655(96)00062-1

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Representations that uniquely characterize images module the planar geometric similarity transformations are presented. Such representations are invariant with respect to translation, rotation, scaling, and their combination. We will first discuss basic invariants, that is, the invariants for translation, rotation, and scaling only. We will then discuss hybrid invariants, that is, invariants with respect to combinations of translation, rotation, and scaling.

引用

页码：1001 / 1015

页数：15