원문정보
초록
영어
The paper introduces the Keren registration method and points out its disadvantage which means it will become inaccuracy on the large scale parameters. To reduce the error on large scale parameters of Keren registration, a two step method is proposed, which the phase correlation algorithm is used to estimate the large translation and rotation angle roughly and the improved Keren algorithm is used to estimate accurately the small translation and rotation angle. The experimental results show that the two step method makes less absolute error of angle than Keren method in the situation of large translation and rotation angle. A new method of estimating the standard deviation of noise is introduced to the robust certainty function, which reduces the impact of noise in the process of interpolation using normalized convolution algorithm. By the edge detection of fusion image in the first stage of the interpolation process of normalized convolution algorithm, a calculation method of long axis and short axis of the structure self-adaptive function is improved. The experimental results show that the proposed interpolation method can improve the performance of the original algorithm and enhance the effect of image super-resolution reconstruction.
목차
1. Introduction
2. Theory of Keren Image Registration
3. Image Registration based on Phase Correlation and KerenRegistration Method
3.1. The Phase Correlation Algorithm
3.2. Our Proposed Image Registration Algorithm
4. Reconstruction
4.1. The Improved Structure-Adaptive Applicability Function
4.2. The New Robust Certainty Function
5. Experiments
6. Conclusion
References