Alphanumeric Hand-Prints Classification: Similarity Analysis between Local Decisions

This paper presents the analysis of similarity between local decisions, in the process of alphanumeric hand-prints classification. From the analysis of local characteristics of hand-printed numerals and characters, extracted by a zoning method, the set of classification decisions is obtained and the similarity among them is investigated. For this purpose the Similarity Index is used, which is an estimator of similarity between classifiers, based on the analysis of agreements between their decisions. The experimental tests, carried out using numerals and characters from the CEDAR and ETL database, respectively, show to what extent different parts of the patterns provide similar classification decisions.