The invention provides a recovery method for a single motion blur image. The method comprises the following steps of establishing a mathematical model of a motion blur image degradation process; carrying out two-dimensional Fourier transform on the motion blur image to obtain a spectrogram; carrying out centralization processing on the spectrogram to obtain alternately dark and bright stripes; according to the alternately dark and bright stripes, obtaining blur parameters, wherein the blur parameters comprise blur length and a blur angle; carrying out optimal window processing on the boundary of the motion blur image; and according to the mathematical model and the blur parameters, carrying out Wiener filtering on the motion blur image subjected to the optimal window processing to obtain a recovered motion blur image. By use of the recovery method for the single motion blur image, detail problems in the motion blur image can be effectively identified, so that the recovery method is high in accuracy and restoration, and can be favorably applied to scenes which can not be repeatedly shot.