DocumentCode
3458053
Title
Uniform Sampling BSIR Method for Image Registration
Author
Zuo Xin ; Dai Xiubin ; Luo Limin ; Zhu Feng ; Zhang Feng
Author_Institution
Lab. of Image Sci. & Technol., Southeast Univ., Nanjing, China
fYear
2010
fDate
21-23 Oct. 2010
Firstpage
1
Lastpage
5
Abstract
In this paper, we propose a more accurate method to align two images under rotation, scaling, blurring in weak texture image. This method utilizes the uniform log-polar sampling (ULP) technique in order to overcome the problem of over-sampling in the fovea area and under-sampling in the peripheral area which affects the accuracy of registration. The proposed method can effectively estimate the rotation and scale parameters more precisely and can also deal with center occlusion. Experimental results demonstrate the effectiveness and robustness of the proposed approach in registrations with geometry transformation, blurring and center occlusion.
Keywords
image registration; image texture; center occlusion; geometry transformation; image registration; over-sampling; rotation parameters; scale parameters; under-sampling; uniform log-polar sampling technique; uniform sampling blur and similarity transform invariant registration method; weak texture image; Accuracy; Computer science; Image registration; Magnetic resonance; Pixel; Robustness; Transforms;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition (CCPR), 2010 Chinese Conference on
Conference_Location
Chongqing
Print_ISBN
978-1-4244-7209-3
Electronic_ISBN
978-1-4244-7210-9
Type
conf
DOI
10.1109/CCPR.2010.5659248
Filename
5659248
Link To Document