A correcting method of a real-time image is disclosed and includes: continuously receiving real-time images from an image inputting device; analyzing an image feature in each real-time image; computing a motion vector of each real-time image based on a feature difference between any two time-adjacent real-time images; computing a moving trajectory predicted value of a latest real-time image based on accumulated motion vectors; computing a compensation value of the latest real-time image when determining that a difference between the moving trajectory predicted value and the motion vector of the latest real-time image is within a correction allowable range, and correcting the latest real-time image by the compensation value; and, resetting the image inputting device and outputting a default image when determining that the difference between the moving trajectory and the motion vector of the latest real-time image exceeds the correction allowable range.