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...

基于初始尺度变换的SIFT匹配算法

Keywords: 尺度不变特征,特征点匹配,初始尺度

Full-Text   Cite this paper   Add to My Lib

Abstract:

直接使用检测到的SIFT(Scale-InvariantFeatureTransformation)特征点进行特征点匹配,匹配性能仍然有待提升.提出了改进的SIFT匹配算法,利用匹配特征点的尺度比直方图,估计出近似的图像尺度比k,然后将空间分辨率较高的图像初始尺度增大到k倍,再次提取特征点进行匹配.实验结果表明,相比于其它用尺度约束条件提升性能的匹配算法,基于初始尺度变化的SIFT匹配算法在处理结构型图像时性能得到了很大的提升.

References

[1]  1Lowe D G. Distinctive image features from scale-invariant keypoints[J], International Journal of Computer Vision, 2004,60(2):91-110.
[2]  2Mikolajczyk K, Schmid C. A performance evaluation of local descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630.
[3]  3Torr P H S, Zisserman A. MLESAC: a new robust estimator with application to estimating image geometry[J]. Computer Vision and Image Understanding, 2000, 78(1):138-156.
[4]  4Fischler 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.
[5]  5Alhwarin F, Wang C, Ristic-Durrant D, et al. A.: Improved SIFT-features matching for object recognition[C].In Visions of Computer Science-BCS International Academic Conf., Imperial College, London, UK, September, 2008.
[6]  6Yi Z, Zhiguo C, Yang X. Multi-spectral remote image registration based on SIFT[J]. Electronics Letters, 2008, 44(2): 107-108.
[7]  7Bastanlar Y, Temizel A, Yardimci Y. Improved SIFT matching for image pairs with scale difference[J]. Electronics Letters, 2010, 46(5): 346-U4867.
[8]  8Lindeberg T. Scale-space theory: A basic tool for analysing structures at different scales[J]. Journal of Applied Statistics, 1994. 2(21): 224-270.
[9]  9Lindeberg T. Feature detection with automatic scale selection[J]. International Journal of Computer Vision, 1998. 30(2): 79-116.
[10]  10Mikolajczyk K. Affine Covariant Features [EB-OL],http://www.robots.ox.ac.uk/~vgg/research/affine/

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133