Multi-Scale Image Registration Algorithm based on Improved SIFT
This paper proposes an image registration algorithm based on improved SIFT feature. In the feature detection, evenly distributed feature points are detected using non-maximum suppression and reduces detection times by dynamic adjustment of detecting step. While employs feature matching, the threshol...
Saved in:
Published in | Journal of multimedia Vol. 8; no. 6; p. 755 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
Oulu
Academy Publisher
01.12.2013
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | This paper proposes an image registration algorithm based on improved SIFT feature. In the feature detection, evenly distributed feature points are detected using non-maximum suppression and reduces detection times by dynamic adjustment of detecting step. While employs feature matching, the threshold of Euclidean distance ratio is adaptively determined according to the properties of images. Lastly, the error matching points are removed by geometric constraint consistency between the feature points through RANSAC algorithm. Experimental results show the effectiveness of the proposed algorithm. Index Terms-First Term; Second Term; Third Term; Fourth Term; Fifth Term; Sixth Term |
---|---|
Bibliography: | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 |
ISSN: | 1796-2048 1796-2048 |
DOI: | 10.4304/jmm.8.6.755-761 |