Heterogeneous image matching based on phase consistency

The Image matching is an important step in image registration and image fusion. To solve the problem that SAR images and optical image matching are sensitive to radiation distortion, a novel heterogeneous image matching algorithm is proposed based on image frequent-domain wavelet decomposition based on phase congruency. Firstly, morphological denoising was carried out for image pairs, and then wavelet decomposition was performed by log-Gabor filter to obtain phase consistency of pixel points (PC graph). Then, feature descriptors were established based on the maximum index graph. Double-point matching was used as the search strategy for feature matching, and the random sampling consensus algorithm was used to eliminate false matching. Compare with traditional SIFT method. Experimental results show that the proposed algorithm has better matching effect than SIFT method and is an effective heterogeneous image matching algorithm