摘要
为了快速而准确地识别出不同类的物体,提出基于修正不变矩和最小范数的物体识别方法,提取物体的不变矩和圆形度特征,利用泛函分析中的范数理论对不同形状的物体进行识别,方法简单,识别速度快,并且识别率较高.仿真结果表明该方法对物体的平移、旋转、缩放都具有不变性,从而验证了该方法的有效性.
In order to recognise various objects fleetly and accurately, objects recognition based on modified invariant moments and mini-norm is proposed in the paper, the features such as invariant moments, and rotundity are extracted, and objects of different shapes are recognised by using norm theory of functional analysis. The method is simple, recognition is rapid,and the recognition rate is very high. The simulation results demonstrate that the method is invariant to the translation, rot.ating and scale of objects. So the efficiency is proved in the paper.
出处
《微电子学与计算机》
CSCD
北大核心
2008年第6期42-45,49,共5页
Microelectronics & Computer
基金
国家自然科学基金项目(60475021)
河南省杰出青年基金项目(0412000400)
关键词
特征提取
不变矩
范数
物体识别
feature extraction
invariant moments
norm
objects recognition
