Laser & Optoelectronics Progress, Volume. 57, Issue 2, 21005(2020)
Image Registration Based on Spectral and Spatial Feature Matching
Aiming at image registration scenes with inconspicuous feature points, we proposed a registration algorithm based on spectral and spatial feature matching to ensure that the overlapping area of two adjacent images to be registered exceeds 80%. Based on the invariance of the rotation center of the Fourier spectrogram, the rotation angle of the two images in the spatial domain around any point was converted into the rotation angle around the center of the spectrogram in the frequency domain. Using the transformation relationship between the polar and Cartesian coordinate systems, the degree of rotation around the center of the spectrogram was converted into a one-dimensional translation, and the rotation angle was obtained using the SAD (Sum of Absolute Difference) algorithm. The SAD algorithm was then applied to determining the translation matrix. The proposed registration algorithm proposed would be suitable for image registration scenes with both inconspicuous and obvious feature points. Moreover, it was characterized by a high speed and registration accuracy.
Get Citation
Copy Citation Text
Chen Zefeng, Wu Qingyang, Chen Shunzhi, Li Qifeng, Lu Xiaoting, Huang Haotao. Image Registration Based on Spectral and Spatial Feature Matching[J]. Laser & Optoelectronics Progress, 2020, 57(2): 21005
Category: Image Processing
Received: May. 5, 2019
Accepted: --
Published Online: Jan. 3, 2020
The Author Email: Qingyang Wu (wuqingyang@sztu.edu.cn)