IDENTIFICATION AND INSPECTION OF 2-D OBJECTS USING NEW MOMENT-BASED SHAPE DESCRIPTORS

被引：32

作者：

SLUZEK, A

机构：

[1] School of Applied Science, Nanyang Technological University, Singapore, 2263, Nanyang Avenue

来源：

PATTERN RECOGNITION LETTERS | 1995年 / 16卷 / 07期

关键词：

MOMENT INVARIANTS; SHAPE DESCRIPTORS; 2-D OBJECT IDENTIFICATION; DIGITAL CIRCLES; AUTOMATED QUALITY INSPECTION;

D O I：

10.1016/0167-8655(95)00021-8

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Anew method of using the moment invariants for the identification and inspection of 2-D shapes is proposed. The prototype object is described by a family of shapes. These shapes are created by occluding the object by circles (of different radius) located in the object's centre of area. The moment invariants of such shapes are functions of a parameter describing the size of circles. Using these functions it is possible to create from a single moment invariant many shape descriptors, so there is no need to use the moments of higher order. The application of the method to the quality inspection of industrial parts is presented.

引用

页码：687 / 697

页数：11

共 27 条

[1] RECOGNITIVE ASPECTS OF MOMENT INVARIANTS [J].