Abstract

In landmark-based image registration, estimating the landmark correspondence plays an important role. In this letter, a novel landmark correspondence estimation technique using mean shift algorithm is proposed. Image corner points are detected as landmarks and mean shift iterations are adopted to find the most probable corresponding point positions in two images. Mutual information between intensity of two local regions is computed to eliminate mis-matching points. Multi-level estimation (MLE) technique is proposed to improve the stability of corresponding estimation. Experiments show that the precision in location of correspondence landmarks is exact. The proposed technique is shown to be feasible and rapid in the experiments of various mono-modal medical images.

© 2008 Chinese Optics Letters

Reconstruction of distorted underwater images using robust registration

Zhen Zhang and Xu Yang
Opt. Express 27(7) 9996-10008 (2019)

Groupwise registration of sequential images from multispectral imaging (MSI) of the retina and choroid

Jianwei Lin, Yuanjie Zheng, Wanzhen Jiao, Bojun Zhao, Shaoting Zhang, James Gee, and Rui Xiao
Opt. Express 24(22) 25277-25290 (2016)

Retinal image registration via feature-guided Gaussian mixture model

Chengyin Liu, Jiayi Ma, Yong Ma, and Jun Huang
J. Opt. Soc. Am. A 33(7) 1267-1276 (2016)

Efficient subpixel image registration algorithms

Manuel Guizar-Sicairos, Samuel T. Thurman, and James R. Fienup
Opt. Lett. 33(2) 156-158 (2008)

Analysis of macular OCT images using deformable registration

Min Chen, Andrew Lang, Howard S. Ying, Peter A. Calabresi, Jerry L. Prince, and Aaron Carass
Biomed. Opt. Express 5(7) 2196-2214 (2014)