基于高阶胡氏矩的多目标图象识别算法  

IDENTIFICATION ALGORITHM OF MULTI-BJECT IMAGE USING HIGH-EVEL HU’S MOMENTS

作　　者：丘江[1] 刘波[1] 杨静[1] 

机构地区：[1]中国科学院西安光学精密机械研究所,710068

出　　处：《光子学报》2001年第9期1141-1145,共5页Acta Photonica Sinica

基　　金：中国科学院西安分院院长基金资助项目

摘　　要：本文提出了一种多目标图象识别算法，此算法以小波变换和目标区域分割算法实现图象的前期处理，以高阶胡氏矩为基础，利用k邻近法构建了分类器，实现了多类目标的识别与分类。仿真实验证明，此算法具有较高的识别精度。In image character matching,it is usually to identify using invariant moments.It is paid great attention since it′s invariant charac ter in rotation and scaling.This paper pesents an algorithm of multi object ide ntification.This algorithm uses wavelet transform and object′s region segmentat ion to fulfil image pre manipulation.Based on high level Hu′s moments,the sor ter is designed using k nearest neighbor.The result of identifi cation and sorting is gained by this sorter.Experimental results show that this algorithm can well identify the objects effectively.

关 键 词：高阶胡氏矩 目标区域分割 k邻近法 图象识别 小波变换 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]