Estimation of motion parameters from blurred images

摘要

The problem of estimating the motion parameters of an object in the presence of blur is considered using moment functions. Blur invariant moments are used as normalization constraints to normalize the image of the object to a canonical form with respect to an assumed affine motion. The crucial point of this method is that the blur level has no influence on the canonical form. Then we obtain the motion parameters from the normalizing transformation matrices. Examples of both artificially deformed and real images are employed to demonstrate the effectiveness of the proposed scheme.