Minimum image resolution for shape recognition using the Generic Jacobi Fourier moments

We consider the use of Jacobi-Fourier moments for the classification of objects from motion blurred images. A set of numerical features are extracted from an image. These features are invariant to the changes in the scale, orientation, position, and illumination of the objects in the vision field. The test images used here have been acquired when the objects are vibrating at different frequencies and moving at constant velocity. The blur extent by image motion can be obtained using moment descriptors of the motion. Also, the acquisition system is characterized by means the optical transfer function (OTF); which can be computed by the geometric moments of motion function of the object centroid. The classification method is tested using images from objects which have intrinsically little differences between them. Experimental results show that, the proposed classification method based in Jacobi Fourier moments can be well addressed to grade images smeared by motion. A comparison of effectiveness is done with motion descriptors based on geometric moments.