The Community for Technology Leaders
Green Image
<p><b>Abstract</b>—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.</p><p>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%.</p><p>The techniques developed here should also be applicable to other areas of shape recognition.</p>
Orthogonal moments, Zernike moments, feature selection, handwritten character recognition, shape recognition, statistical classifiers, neural network classifiers.
Mandyam Srinath, Robert R. Bailey, "Orthogonal Moment Features for Use With Parametric and Non-Parametric Classifiers", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 18, no. , pp. 389-399, April 1996, doi:10.1109/34.491620
106 ms
(Ver 3.3 (11022016))