Automatic fundus images mosaic based on SIFT feature

An automatic fundus image mosaic algorithm based on SIFT feature is presented, to overcome the characteristics of low contrast and the geometric distortion between different field of view of the fundus images. The SIFT feature of fundus images are extracted and described using vectors to determine the matching feature point pairs between two images, outlier point pairs are rejected using MLESAC algorithm employed RST model, the transformation matrix is then computed according to purified matching point pairs between images, at last image registration and image mosaic is implemented. The mosaic results of multiple images obtained by fundus camera show that the algorithm has good robustness and stability, and high-precision automatic fundus image mosaic can be achieved.