Feature extraction: on the importance of zoning information in cursive script recognition
R.K. Powalka, Nasser Sherkat, RJ Witrow · Nottingham Trent University's Institutional Repository (Nottingham Trent Repository) · 1994
Cursive script has many ambiguities. Feature extraction, by locating some specific characteristics of a writing sample in isolation or in combination with other features, can minimise the effect of these ambiguities. There are many features that can be extracted from any given sample. Information about the expected vertical letter position within the word, the zoning information, is envisaged to be a powerful criterion. This paper presents the results of experiments carried out to evaluate the usefulness of zoning information. The influence of the applied zoning criteria was varied and the results were observed. A discussion of the way the zoning information can be used to improve the recognition rate and the way in which an existing recognizer is modified to make use of this information is presented.