全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

迭代的图变换匹配算法

DOI: 10.11834/jig.20140510

Keywords: 图变换匹配,图像匹配,K近邻图,几何约束

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的图像的精确匹配在图像处理与识别中起着重要的作用。为了提高图像的匹配效果,提出了一种迭代的图变换匹配算法来实现误匹配关系的去除从而提高图像的匹配精度。方法首先利用传统的图变换匹配(GTM)算法从初始匹配关系集合中获得较为精确的匹配关系子集;然后,利用已经获得的正确匹配点集与初始匹配点集之间的几何关系对初始匹配进行修正;最后,利用GTM对修正后的匹配关系进一步优化,从而得到更多的精确匹配关系。结果实验结果显示在不同的图像变换场景下,相比于传统GTM算法,该算法具有较高的查全率。结论所提算法能够克服传统GTM算法所得正确匹配关系少的缺陷。

References

[1]  Deng B S,Song H C,Yang B,et al. Feature point matching based on affine iterative model [J]. Journal of Image and Graphics,2007,12(4):678-683.[邓宝松, 宋汉辰, 杨冰, 等.基于仿射迭代模型的特征点匹配算法 [J]. 中国图象图形学报,2007,12(4):678-683.]
[2]  Tian H,Li G H,Jia L,et al. Local descriptor for object recognition in high resolution remote sensing images [J]. Energy Procedia,2011,13:683-691.
[3]  Misra I,Moorthi S M,Dhar D, et al. An automatic satellite image registration technique based on Harris corner detection and random sample consensus outlier rejection model [C]//Proceedings of the 1st International Conference on Recent Advances in Information Technology. Piscataway,United States:IEEE Computer Society,2012:68-73.
[4]  Ding W Y,Wang P, Huang Q, et al. Method for automatic registration of images with affine transformation [J]. Journal of Chongqing University of Technology: Natural Science, 2010,24(3):71-75. [丁文益, 王平, 黄庆, 等.一种适应仿射变换的全自动景象匹配算法[J]. 重庆理工大学学报:自然科学,2010,24(3):71-75.]
[5]  Fischler M A,Bolles R C. Random sample consensus:a paradigm for model fitting with applications to image analysis and automated cartography [J]. Communications of the ACM,1981,24(6):381-395.
[6]  Zhang Z Y,Deriche R,Faugeras O. A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry [J]. Artificial Intelligence,1995,78(1/2):87-119.
[7]  Wei Z Q,Huang L,Ji X P. Research on sequence image matching based on point feature [J]. Journal of Image and Graphics,2009,14(3):525-530. [魏志强, 黄磊, 纪筱鹏.基于点特征的序列图像匹配方法研究 [J].中国图象图形学报,2009,14(3):525-530.][DOI:10.11834/jig.20090323]
[8]  Zhuang Z G,Sun H J,Dong J Y,et al. Corner detection based image matching algorithm and its application on image stitching [J]. Journal of Xiamen University:Natural Science,2007,146(4):501-505.[庄志国, 孙惠军, 董继扬, 等.基于角点检测的图像匹配算法及其在图像拼接中的应用 [J]. 厦门大学学报:自然科学版,2007,146(4):501-505.]
[9]  Li X X,Zheng J B,Zhang Y N. Novel automatic method for image registration [J]. Application Research of Computers,2008,25(1):290-291.[李秀秀, 郑江滨, 张艳宁.一种新的自动图像配准技术[J].计算机应用研究,2008,25(1):290-291.]
[10]  Aguilar W,Frauel Y,Escolano F, et al. A robust graph transformation matching for non-rigid registration [J].Image and Vision Computing,2009,27:897-910.
[11]  Aguilar W. Object recognition based on the structural correspondence of local features [D]. Mexico City:Universidad Nacional Autonoma de Mexico,2006.
[12]  Mikolajczyk K,Schmid C. A performance evaluation of local descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.
[13]  Lowe D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision,2004,60(2):91-110.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133