[1]朱俊,任明武,杨章静,等.基于角点检测的快速匹配算法[J].南京理工大学学报(自然科学版),2011,(06):755-758.
 ZHU Jun,REN Ming-wu,YANG Zhang-jing,et al.Fast Matching Algorithm Based on Corner Detection[J].Journal of Nanjing University of Science and Technology,2011,(06):755-758.
点击复制

基于角点检测的快速匹配算法
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
期数:
2011年06期
页码:
755-758
栏目:
出版日期:
2011-12-31

文章信息/Info

Title:
Fast Matching Algorithm Based on Corner Detection
作者:
朱俊任明武杨章静赵炜
南京理工大学计算机科学与技术学院,江苏南京210094
Author(s):
ZHU JunREN Ming-wuYANG Zhang-jingZHAO Wei
School of Computer Science and Technology,NUST,Nanjing 210094,China
关键词:
角点检测 特征匹配 角点特征 图像灰度 位置信息 互相关函数
Keywords:
corner detection feature matching graphic point features gray-level pixel location information correlation function
分类号:
TP391. 41
摘要:
针对复杂图像的快速匹配,提出基于Shi-Tomasi 角点检测的特征匹配算法。依据图像的 角点特征、图像灰度和位置信息,采用最大互相关函数进行相似度计算和粗匹配,用随机样本一致 性算法对匹配点对进行校正并消除错误匹配。将该算法应用于实景照片拼接,实验结果表明,对 存在较大色差和形变的图像,其匹配精度为97%左右,匹配精度和速度均优于传统匹配算法。
Abstract:
In view of the fast image registration of complicated images,a matching algorithm based on Shi-Tomasi corner detection is described. The max correlation function is used for similarity computation and rough matching according to the corner features, image gray and location information of the images. Random sample consensus method is used for revising matching points and removing false matching. The algorithm is applied to real photo stitching. Experimental results show that the matching accuracy of this algorithm is about 97% for images with chromatic aberration or deformation and outperforms traditional point matching algorithms both in matching accuracy and running speed.

参考文献/References:

[1] 冈萨雷斯. 数字图像处理[M]. 阮秋奇,阮宇智,译. 2 版. 北京: 电子工业出版社, 2009.
[2] Papakostas G A,Karakasis E G,Koulouriotis D E. Novel moment invariants for improved classification performance in computer vision applications [J]. Pattern Recognition. 2010, 43( 1) : 58-68.
[3] unic' J,Hirota K,Rosin P L. A Hu moment invariant as a shape circularity measure[J]. Pattern Recognition, 2010, 43( 1), 47-57.
[4] Goncalves H,Goncalves J A,Corte-Real L. HAIRIS: A method for automatic image registration through histogram-based image segmentation [J]. IEEE Transactions on Image Processing, 2011, 20( 3) : 776-789.
[5] Chae K Y,Dong W P, Jeong C S. SUSAN window based cost calculation for fast stereo matching[J]. Lecture Notes in Computer Science, 2005, 38( 2) : 947-952.
[6] Shi J,Tomasi C. Good features to track [A]. Proceedings CVPR’94[C]. Seattle,USA: Computer Vision and Pattern Recognition, 1994: 593-600.
[7] 林学晶. 视频图像拼接技术研究[D]. 南京: 南京理 工大学计算机科学与技术学院, 2005.
[8] 汪华琴. 基于特征点匹配的图像拼接方法研究 [M]. 武汉: 华中师范大学出版社, 2007.
[9] 腾飞. 基于相对点矩的SAR 图像匹配算法[J]. 电 子设计工程, 2011, 19( 6) : 147-149.

相似文献/References:

[1]侯建,齐乃明.月球车视觉系统立体匹配算法研究[J].南京理工大学学报(自然科学版),2008,(02):176.
 HOU Jian,QI Nai-ming.Stereo Matching Algorithm for Lunar Rover[J].Journal of Nanjing University of Science and Technology,2008,(06):176.
[2]娄震,陆建峰,杨静宇.用于X射线图像的角点检测方法[J].南京理工大学学报(自然科学版),2002,(06):561.
 LouZhen LuJianfeng YangJingyu.Corner Detection Used for X-ray Images[J].Journal of Nanjing University of Science and Technology,2002,(06):561.
[3]张冰怡,魏 博,陈建成,等.基于对偶编码的中文分词算法[J].南京理工大学学报(自然科学版),2014,38(04):526.
 Zhang Bingyi,Wei Bo,Chen Jiancheng,et al.Chinese word segmentation algorithm based on pair coding[J].Journal of Nanjing University of Science and Technology,2014,38(06):526.

备注/Memo

备注/Memo:
基金项目: 国家自然科学基金( 60875010) 作者简介: 朱俊( 1981-) ,男,博士生,主要研究方向: 计算机应用,模式识别; E-mail: xiaobaabc@ sina. com; 通讯作者: 任明武( 1969-) ,男,博士,教授,博士生导师,主要研究方向: 模式识别与智能系统,E-mail: renmingwu@ mail. njust. edu. cn。
更新日期/Last Update: 2012-10-25