基于矩特征傅立叶描述法的目标形状识别  

Shape Recognition Based on Fourier Descriptor of Moments

作　　者：张金华[1] 傅山[2] 

机构地区：[1]上海交通大学电子信息与电气工程学院,上海200240 [2]上海交通大学航空航天学院,上海200240

出　　处：《微计算机信息》2009年第34期167-169,共3页Control & Automation

摘　　要：针对适用于实时图像处理的目标识别系统,本文提出了一种结合矩特征和傅立叶描述子的形状识别新方法。该方法以质心为中心将物体划分为多个扇形区域,计算各扇形区域的矩特征值获得表示物体形状的矩特征序列,再通过离散傅立叶变换得到具有平移、旋转以及比例不变性的归一化矩特征傅立叶描述子。实验结果表明,该方法具有很好的实时性和很高的识别率,能准确地识别二维物体和三维物体的形状,具有很好的工程应用前景。To apply to real-time image processing of target recognition system,a new method for shape recognition in which moments and Fourier descriptors were combined was presented. The object was divided into a sequence of fan-shaped sub-regions,originated at the centroid of the object image. The moments calculated in all the subregions formed the moment sequence to represent the characteristics of the object. The Fourier Descriptor of the moment sequence was then derived using DFT,which has properties of invariant in the translation,rotation and scale transform. The experiments results demonstrated that this technique has very good realtime performance and high recognition rate,can identify the shapes of 2-D objects accurately,as well as for 3-D objects. It shows this new method has very good outlook engineering application.

关 键 词：不变矩 傅立叶描述子 目标识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]