On the computational aspects of affine moment invariants for gray-scale images

Affine moment invariants are widely used in pattern recognition and computer vision. The affine transform usually decomposed into a set of geometric transforms. The computation of these transforms relies on their relations with the geometric moments. Approximate computation of geometric moments produced a very large dynamic range that results in numerical instabilities. In this work, an exact method is used for the computation of affine moment invariants for gray level images, where the proposed method completely removes the approximation errors. Numerical experiments are performed to test the invariance of symmetric as well as asymmetric images subject to affine transformations. A comparison with the approximation method is made. The obtained results clearly explained the efficiency of the proposed method.