The evaluation of feature extraction criteria applied to neural network classifiers

Feature extraction is a crucial part of classijicationprocedures. In this paper we present an approach, how to utilize feature extraction criteria to predict the potential efficiency of a neural network classijiel: Statistical and geometrical criteria are introduced for analysis. The complete system of our research consists of a class of generalized Hough-Transformations for feature extraction and a subsequent neural network. The neural network performs the classijication based on respective features. For an example we concentrated on a pattern recognition problem the classijication of handwritten numerals. As a result of our work we assign two feature extraction criteria to the employed network for a significant estimation of its eflciency.