基于Fourier-Mellin变换的图像配准算法及性能研究

Image Registration Algorithm and Efficiency Research Based on Fourier-Mellin

快速傅立叶变换(FFT)改进了离散傅立叶变换(DFT)的计算过程,被广泛应用于数字图像的实时处理中。在相位相关技术的基础上,提出了一种新的图像配准算法,即在需要配准的两幅图像中心选取相同区域大小,进行Fourier-Mellin变换,变换后是一个二维脉冲信号,由此而得到图像配准参数。实验结果表明了该算法的有效性和可靠性。

The fast Fourier transform （FFT） improves the computational process of the discrete Fourier transform （DFT）, and is applied in real time processing of digital image abundantly. This paper proposes a new image registration algorithm based on phase-correlation technology, two same size patch needed to be cropped in the central patch of the two image, then conduct the Fourier-Mellin transform, the transformed result was a 2-D impulse. And the impulse location can determine the scaled and rotated factors. The experimental results show that the algorithm is efficient and reliable.