| Hi-index | 0.00 |
This paper describes a method for numeral character recognition. Initially the image of an unknown numeral is pre-processed and two feature sets were compiled and used for numeral character recognition. The first feature set is compounded by topological characteristics and by characteristics obtained from pictorial distribution analysis of numeral images. The second set of features is the proper numeral images, after being normalized. The classification process is divided into two stages. In the first stage, the classification is based on the first feature set. In the second stage of classification, Hopfield networks are used to find the most probable numeral class. Experimental results obtained from testing the laboratory prepared data and those handwritten numerals extracted from real Brazilian bank checks show that the recognition rates of 85% and 92.4% were achieved, respectively.