[1]LI Xiyan,Jl Dongsheng,WU Chongzheng.The Research of lmage Mosaic Algorithm Based on SURF and Pseudo-Zernike Moments[J].Journal of Zhengzhou University (Engineering Science),2014,35(06):69-73.[doi:10.3969/j.issn.1671-6833.2014.06.017]
Copy
Journal of Zhengzhou University (Engineering Science)[ISSN
1671-6833/CN
41-1339/T] Volume:
35卷
Number of periods:
2014 06
Page number:
69-73
Column:
Public date:
2014-11-25
- Title:
-
The Research of lmage Mosaic Algorithm Based on SURF and Pseudo-Zernike Moments
- Author(s):
-
LI Xiyan; Jl Dongsheng; WU Chongzheng
-
1. Finanee and Eeonomies Deparment of information Engineering, 2hengzhou Chenggong College, 2hengzhou 451200, china;2. School of Infommation Seienee & Engineering , Lanzhou University, Lanzhou 730030, China
-
- Keywords:
-
SURF; pseudo-zernike moments; RANSAC algorithm; image mosaie
- CLC:
-
TP751.1
- DOI:
-
10.3969/j.issn.1671-6833.2014.06.017
- Abstract:
-
The feature points matching image mosaie algorithm was found to be sensilive to rolations andnoise , and an automatie image mosaie method based on SURF and Pseudo-Zernike moments algorithm was pro.posed. The improved SURF feature points detector was used to get the comers, then the pseudo-Zemike mo.ments defined on the interest point neighborhood were eomputed. Through comparing the Bray-Curtis similaritymeasure of the pseudo-Zernike moments to extraet the initial feaure points pair, then the spurious featurepoints pair were rejeeted by RANSAC algorithm, then by means of using the geometrie transform of input ima-ges for registration, the overlapping region of two images was fused and the image Mosaie was finished. lm-proved SURF feature detection algorihm extraet feature points are uniform, aeeurate and fast. The proposedmethod of image registration is robust to rotation , lranslalion and noise.