A fast algorithm, based on power cepstrum and crosscorrelation,techniques, for registration of image frames in a video is presented.Since compensation for unwanted rotations between image frames isneeded, the shift invariance property of Fourier spectrum is used tofind this rotation. The registration and information recovery approachesinvolve three image processing steps: a feature extraction step usingthe difference of Gaussian filtered images combined with medianfiltering for removal of noise, to enhance significant fluorescent bloodvessels combined with median filtering for removal of noise;compensation for rotational and translational shifts in the Fourierdomain using the spectral properties, crosscorrelation, and powercepstrum; lastly, information in each frame is maximized in comparisonto the subsequent frames. Such analysis allows better interpretation ofthe video content for diagnostic evaluation of retinopathies
展开▼