Improved rotation invariant pattern recognition using circular harmonics of binary gray level slices

We introduce a new rotation invariant pattern recognition method based on n onlinear correlation. The images are decomposed into disjoint binary slices and then correlated using the common linear correlation. This operation is very discriminant even when the target is embedded in strong noise. We ext end our sliced orthogonal nonlinear generalized correlation method to rotat ion invariant pattern recognition by combining the information of a circula r harmonic (CH) of each binary slice of the reference object with binary sl ices of the target. In addition to improved discrimination capability, the method avoids the time-consuming process of finding proper centers for the CHs. Results are presented including the study of the stability of the corr elation peaks in the presence of background noise and overlapping Gaussian noise. (C) 2000 Elsevier Science B.V. All rights reserved.