2D shape segmentation: A new approach

被引：6
作者：
Wu, KN
Levine, MD
机构：
[1] MCGILL UNIV,CTR INTELLIGENT MACHINES,MONTREAL,PQ H3A 2A7,CANADA
[2] MCGILL UNIV,DEPT ELECT ENGN,MONTREAL,PQ H3A 2A7,CANADA
来源：
PATTERN RECOGNITION LETTERS | 1996年 / 17卷 / 02期
基金：
加拿大自然科学与工程研究理事会;
关键词：
2D shape; segmentation; corner detection; finite elements; charge density distribution; electrostatics;
D O I：
10.1016/0167-8655(95)00107-7
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We propose a novel approach to 2D shape segmentation by simulating the electrical charge density distribution on a 2D contour. The method is unique and invariant with respect to scale, translation and rotation. It computes significant 2D shape features by considering global data and is easily extensible to the 3D case.
引用
收藏
页码：133 / 140
页数：8
相关论文
共 19 条
12