Recognition of digital annotation with invariant HONN based on orthogonal Fourier-Mellin moments

A recently developed type of moments, Orthogonal Fourier-Mellin Moments (OFMMs) is applied to the specific problem of full scale and rotation invariant recognition of digital annotation in GIS. In order to recognize digital annotation in segmented images, the OFMMs is used as the input vector to a High Order Neural Network (HONN) to distinguish digital annotation from other information. It has the advantages of non-redundancy of information, robustness with respect to noise and the ability to reconstruct the original object. The High Order Neural Network is different from other neural networks in that it has no hidden layers. The results show that the method is subjected to scale and rotation change, and non-computational cost.