INVARIANT IMAGE-ANALYSIS BASED ON RADON-TRANSFORM AND SVD

A Radon-based invariant image analysis method is introduced, The linea rity, shift, rotation, and scaling properties of the Radon transform a re utilized to achieve invariant features to translation, rotation, an d scaling. The singular values of a matrix, constructed by row-stackin g of projections, are used to construct the invariant feature vector, This feature vector will be used as input to a classifier, which is he re, the back-propagation neural network followed by a maximum-output-s elector. A performance function is introduced to evaluate the performa nce of the recognition system. This performance function can also be u sed to indicate how closely the pattern matches the decision template. The effectiveness of this method is illustrated by a simulation examp le and it is compared with the method of Zernike moments.