Rotation, Scale and Shift Invariant Pattern Recognition System

Song Jianzhong

doi:null

您当前的位置：

首页 >

文章列表页 >

Rotation, Scale and Shift Invariant Pattern Recognition System

更新时间：2020-08-12

- Rotation, Scale and Shift Invariant Pattern Recognition System
- Optics and Precision Engineering Vol. 0, Issue 2, Pages: 1-12(1987)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published Online：15 April 1987，
  
  Published：15 April 1987
- 稿件说明：
移动端阅览
宋建中. 旋转、比例、平移不变的图形识别系统[J]. 光学精密工程, 1987,(2): 1-12

Song Jianzhong. Rotation, Scale and Shift Invariant Pattern Recognition System[J]. Editorial Office of Optics and Precision Engineering, 1987,(2): 1-12
宋建中. 旋转、比例、平移不变的图形识别系统[J]. 光学精密工程, 1987,(2): 1-12 DOI：

Song Jianzhong. Rotation, Scale and Shift Invariant Pattern Recognition System[J]. Editorial Office of Optics and Precision Engineering, 1987,(2): 1-12 DOI：

摘要

在高分辨率、高灵敏度的空间光调制器开始问世的今天

降低光学相关器对图像失真的敏感程度是实时光学图形识别系统能否实用的关键。本文叙述了一种用坐标变换的方法来实现旋转、比例、平移不变的图形识别系统。在数学上证明了傅里叶变换加上polar-

n变换(简称P-

变换)

可以实现平移、旋转和比例的不变性

并进了计算机仿真。本文提出了两种实现P-

变换的方法。一种是采用特殊的电视摄像机。用对数形的锯齿波按辐射状扫描摄像管的靶面

另一种是采用一个计算机产生的两值光学元件

并给出了该光学元件的相位函数的解析表达式。本文还给出了用这两种办法实现的光学系统及实验结果。实验结果表明

两种系统都能在输入图像发生旋转、比例变化和平移的情况下

实时地做到对输入目标的识别。

Abstract

This paper introduces the Polar-Mellin transformation for distortion-invariant pattern recognition with emphasis on the implementation of the Polar-Mellin transform by a computer-generated optical element and by a special TV camera. When the computer-generated optical element or the TV camera for the polar-ln transform is used for correlation

the pattern which is interested can always be recognized even though the pattern is rotated or seale-changed or shifted. In this paper

two kinds of distortion-invariant systems for pattern recognition using the computer-generated optical element and the TV comera are given. Computer simulations and primary experiments have proven that methods described in this paper are correct.

关键词

Keywords

references

Views

526

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰