首页 | 官方网站   微博 | 高级检索  
     

一种鲁棒的图像局部仿射不变特征提取方法
引用本文:周韬,张茂军,熊志辉,徐玮.一种鲁棒的图像局部仿射不变特征提取方法[J].模式识别与人工智能,2013,26(3):276-281.
作者姓名:周韬  张茂军  熊志辉  徐玮
作者单位:1.国防科技大学信息系统与管理学院长沙410073
2.武警工程大学信息工程系西安710086
基金项目:国家自然科学基金项目(No.61175006,61175015)、湖南省研究生科研创新项目(No.CX2010B024)、国防科学技术大学优秀博士生创新项目(No.B100504)资助
摘    要:提出一种鲁棒的图像局部仿射不变特征提取方法.该方法首先对图像进行M进制小波变换,根据M进制小波变换系数的能量性质来检测图像特征点.然后以检测到的稳定特征点为中心,根据特征点周围的局部图像信息,以矩的形式构造仿射不变特征描述子.实验结果证明该方法对图像的旋转变化、尺度变化、视点变化、平移等所有仿射变换均具有较好的不变性.

收稿时间:2012-04-25

A Robust Affine Invariant Local Image Features Extraction Method
ZHOU Tao,ZHANG Mao-Jun,XIONG Zhi-Hui,XU Wei.A Robust Affine Invariant Local Image Features Extraction Method[J].Pattern Recognition and Artificial Intelligence,2013,26(3):276-281.
Authors:ZHOU Tao  ZHANG Mao-Jun  XIONG Zhi-Hui  XU Wei
Affiliation:1.College of Information Systems and Management,National University of Defense Technology,Changsha 410073
2.Department of Information Engineering,Engineering University of CAPF,Xi′an 710086
Abstract:A robust affine invariant local image features extraction method is proposed. Firstly,the image is transformed with M band wavelet. The feature points of the image are detected according to the energy of the M band wavelet transform coefficients. Then,every detected feature point is set to be a center. According to the local image information around the center,affine invariant feature is constructed with a moment structure. The experiments prove the invariant efficiency of the proposed method in image rotation,shift,scaling and viewpoint change etc.
Keywords:
点击此处可从《模式识别与人工智能》浏览原始摘要信息
点击此处可从《模式识别与人工智能》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号