The Community for Technology Leaders
2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW) (2013)
San Jose, CA, USA
July 15, 2013 to July 19, 2013
ISBN: 978-1-4799-1604-7
pp: 1-4
Ruohan Qian , Department of Electronic Engineering and Information Science, University of Science and Technology of China, China
Weihai Li , Department of Electronic Engineering and Information Science, University of Science and Technology of China, China
Nenghai Yu , Department of Electronic Engineering and Information Science, University of Science and Technology of China, China
ABSTRACT
The detection of image rotation and the estimation of rotation angle are of great help to “copy-paste” image forgery detection because the copy-pasted slice is often rotated to gain better visual effect. This paper proposes a novel blind image rotation detection algorithm with high precision rotation angle estimation. The proposed algorithm is based on the periodicity within pixel variances, which is introduced by the rotation interpolation. Experiment results show that this algorithm can estimate rotation angle precisely with a fine rotation angle resolution of 0.2 degrees for images of 1024 pixels in width.
INDEX TERMS
peak detection, rotation detection, rotation angle estimation, image forensics
CITATION

R. Qian, W. Li and N. Yu, "High precision rotation angle estimation for rotated images," 2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), San Jose, CA, USA, 2013, pp. 1-4.
doi:10.1109/ICMEW.2013.6618298
89 ms
(Ver 3.3 (11022016))