Multi-focus image registration algorithm based on image preprocessing and improved SIFT
Ke Lin, Wei Pan · 2023
Image registration is an important technology in the image processing, which is widely used in computer vision, image fusion, image reconstruction and other fields. To solve the problem of poor image registration due to fuzzy regions in multi-focus images, this paper proposes a multi-focus image registration algorithm based on image preprocessing and improved SIFT. The reference image and the image to be registered are preprocessed by Gaussian smoothing. And then all images are feature extracted and classified. Last, the image is feature matched by bidirectional adaptive threshold algorithm, and finally the registered image is obtained by the registration result. Compared with SIFT algorithm, the number of feature extraction and feature matching of the proposed algorithm increase by 56.57% and 67.43% respectively.