PERFORMANCE OF AN OPTIMAL SUBSET OF ZERNIKE FEATURES FOR PATTERN-CLASSIFICATION

This paper presents a technique of selecting an optimal number of feat ures from the original set of features. Due to the large number of fea tures considered, it is computationally more efficient to select a sub set of features that can discriminate as well as the original set. The subset of features is determined using stepwise discriminant analysis . The results of using such a scheme to classify scaled, rotated, and translated binary images and also images that have been perturbed with random noise are reported. The features used in this study are Zernik e moments, which are the mapping of the image onto a set of complex or thogonal polynomials. The performance of using a subset is examined th rough its comparison to the original set. The classifiers used in this study are neural network and a statistical nearest neighbor classifie r. The back-propagation learning algorithm is used in training the neu ral network. The classifers are trained with some noiseless images and are tested with the remaining data set. When an optimal subset of fea tures is used, the classifers performed almost as well as when trained with the original set of features.