Orthogonal moment features for use with parametric and non-parametric classifiers

Abstract

This research examines a variety of approaches for using two-dimensional orthogonal polynomials for the recognition of handwritten Arabic numerals. It also makes use of parametric and non-parametric statistical and neural network classifiers. Polynomials, including Legendre, Zernike, and pseudo-Zernike, are used to generate moment-based features which are invariant to location, size, and (optionally) rotation. An efficient method for computing the moments via geometric moments is presented. A side effect of this method also yields scale invariance. A new approach to location invariance using a minimum bounding circle is presented, and a detailed analysis of the rotational properties of the moments is given. Data partitioning tests are performed to evaluate the various feature types and classifiers. For rotational invariant character recognition, the highest percentage of correctly classified characters was 91.7%, and for non-rotational invariant recognition it was 97.6%. This compares with a previous effort, using the same data and test conditions, of 94.8%. The techniques developed here should also be applicable to other areas of shape recognition.