Image matching algorithm combining SIFT with region segmentation

Wen-Tao Qiu; Jian ZHAO

doi:null

您当前的位置：

首页 >

文章列表页 >

Image matching algorithm combining SIFT with region segmentation

更新时间：2020-08-12

- Image matching algorithm combining SIFT with region segmentation
- Chinese Journal of Liquid Crystals and Displays Vol. 27, Issue 1, (2012)
- 作者机构：
  
  中国科学院长春光学精密机械与物理研究所2. 中科院长春光学精密机械与物理研究所
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391.9
- Received：30 March 2012，
  
  Revised：11 June 2012，
  
  Published Online：29 June 2012，
  
  Published：15 February 2012
- 稿件说明：
移动端阅览
郭春桔, 夏森林, 孙振, 汪映寒. 侧链含稠环的新型聚酰亚胺液晶垂直取向剂的制备及表征[J]. 液晶与显示, 2012,27(1): 8-13

GUO Chun-ju, XIA Sen-lin, SUN Zhen, WANG Ying-han. Preparation and Characterization of Novel Polyimide with Thick Ring in Side Chain for Vertical Alignment Liquid Crystals[J]. , 2012,27(1): 8-13
郭春桔, 夏森林, 孙振, 汪映寒. 侧链含稠环的新型聚酰亚胺液晶垂直取向剂的制备及表征[J]. 液晶与显示, 2012,27(1): 8-13 DOI：

GUO Chun-ju, XIA Sen-lin, SUN Zhen, WANG Ying-han. Preparation and Characterization of Novel Polyimide with Thick Ring in Side Chain for Vertical Alignment Liquid Crystals[J]. , 2012,27(1): 8-13 DOI：

摘要

针对待配准图在参考图上存在多个相似的区域，传统的SIFT(Scale Invariable Feature Transformation)算法导致匹配点数量较少，影响对模型变换参数估计的情况，提出了结合区域分割的SIFT特征提取和特征匹配的方法。算法首先对图片进行边缘检测以及形态学滤波预处理，提取出边缘丰富区，接着采用改进的简化SIFT，并在匹配阶段，结合强匹配点对与SSDA(Sequential Similarity Detection Algorithm)检测出的粗匹配位置进行匹配，增加了算法区分相似区域的能力。与原始算法相比，该算法可以得到更多正确的匹配点对，时效性上更优。

Abstract

Aiming at solving the situation that the original SIFT algorithm can only get few number of matching points if there are a few regions similar to the matching image on the reference image

which will affect the estimation of parameters in the transformation model. Proposed algorithm first apply edge detection and morphology filtering in the image preprocessing stage to extract edge-abundant areas

then adopt an improved simplified SIFT

and combine the rough matching area detected by SSDA and robust matching points while matching points

thus improving the discrepancy of similar points in the algorithm. Compared to the original algorithm

our proposed algorithm can get more correct matching points and is less time consuming.

关键词

Keywords

references

王永明，王贵锦．图像局部不变性特征与描述［M］.北京：国防工业出版社，2010: 79-87,129-133,150-163.[J].,2010,:79-163[2]倪国强, 刘琼.多源图像配准技术分析与展望[J].光电工程,2004,31(1):1-6[3]Tuyte T, Mikolajczyk. Local invariant feature detectors: A survey. Foundations and trends in computer graphics and vision 2008,v3.[J].Foundations and trends in computer graphics and vision,2008,3:-[4]David G. Lowe. Distinctive image features from scale-invariant keypoints [J].International Journal of computer vision 2004, 60(2), 91-110[J].International Journal of computer vision,2004,60(2):91-110[5]Ke Y, Sukthankar R.PCA SIFT: a more distinctive representation for local image descriptors [J].Proc Conf Computer Vision and Pattern Recognition,2004,:-[6]Mikolajczyk K, Schmid C.. A performance evaluation of local descriptorsIEEE [J].Transactions on Pattern Analysis and Machine Intelligence,2005,(27):1615-1630[7]Herbert B, Tinne T, Luc V G.SURF: speeded up robust features[J].Computer Vision and Image Understanding,2008,110(3):346-359[8]Rob Hess. An Open-Source SIFT Library[J].Proceedings of the international conference on multimedia,2010,:-[9] OpenCV. http://opencv.willowgarage.com[10]纪华.仿射不变特征提取及其在景象匹配中的应用 [D].长春：中国科学院长春光学精密机械与物理研究所[J].,2010,:-[11]Koenderink J.The structure of image[J].Biological Cybernetics,1984,50:363-396[12]Lindeberg T.Scale-space for discrete signals[J].IEEE Transaction PAMI,1980,207:187-207[13]M .A. Fischler and R. C.Bolles. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography[J].Communications of the ACM,1981,24(6):-[14]杨帆等编著.数字图像处理与分析[J].北京航空航天大学出版社,2007,:207-263.[15]邸男，李桂菊，魏雅娟.采用SIFT的末制导图像匹配技术 [J].红外与激光工程,2011,40(8):1549-1593[16]何斌，马天予，王运坚，朱红莲编著.Visual C++数字图像处理[J].人民邮电出版社,2001,:491-508

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Image registration combining cross-scale point matching and multi-scale feature fusion

Improved YOLOv5 lightweight binocular vision UAV obstacle avoidance algorithm based on Ghost module

Point cloud registration algorithm based on statistical local feature description and matching

Target handoff based on improved ORB algorithm on non-overlapping cameras

Image Matching Algorithm Combining SIFT with Region Segmentation

Related Author

GU Yu

LÜ Xiaoqi

OU Zhuolin

BAI Yue

CAO Tianyi

JIA Yifan

TAO Zhiyong

LI Xinchun

Related Institution

School of Information Engineering， Inner Mongolia University of Science and Technology

School of Information Engineering， Inner Mongolia University of Technology

Changchun Institute of Optics， Fine Mechanics and Physics， Chinese Academy of Sciences

University of Chinese Academy of Sciences

SWJTU-Leeds Joint School

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰