A multi-scale and multi-orientation recognition technique applied to document interpretation application to french telephone network maps

Abstract

We consider the general problem of technical document interpretation, applied to the documents of the French telephonic operator, France Telecom. More precisely, we focus the content of this paper on the computation and the use of a new set of features allowing the classification of multi-oriented and multi-scaled patterns, as well as the rotation and scale parameters estimation. This set of invariants is based on the Fourier-Mellin transform (FMT). This transformation has two interesting properties in the context of our study. The first relies on the classification rate which is obtained with this method. Secondly, it provides a robust estimator of orientation and scale of the processed patterns through the use of the shift theorem of the Fourier transform. A comparison with parameter estimation issued from the Zernike moments is also given.