THE USE OF MAXIMUM CURVATURE POINTS FOR THE RECOGNITION OF PARTIALLY OCCLUDED OBJECTS

被引：67

作者：

HAN, MH

JANG, DS

机构：

[1] Department of Industrial Engineering, Texas A and M University, College Station

来源：

PATTERN RECOGNITION | 1990年 / 23卷 / 1-2期

关键词：

Clique; Occlusion; Polygonization; Weight matching;

D O I：

10.1016/0031-3203(90)90046-N

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A graph-theoretic optimization method is used to recognize partially occluded objects from a 2-D image through the use of maximal cliques and a weight matching algorithm. The vertices of an occluded object image with high curvature values are classified by the objects which are hypothesized to be involved in the occlusion. A heuristic method is also developed to further improve the computational speed. A few typical examples are given to illustrate the accuracy of the optimization model as well as the simplicity of the companion heuristic method. © 1990.

引用

页码：21 / 33

页数：13

共 24 条

[1] HYPER - A NEW APPROACH FOR THE RECOGNITION AND POSITIONING OF TWO-DIMENSIONAL OBJECTS [J].