Pen-based recognizing of handprinted characters

Abstract

This paper introduces the object-oriented character recognition engine AQUIRE. It was originally designed as a general pattern-classifier under the academic aspects of object-orientation and parallelism together with low space and time complexity. When industry expressed interest in using AQUIRE to provide pen-based computers and applications with a powerful character-recognition engine, AQUIRE was revised to meet the commercial requirements. Together with a brief discussion of some special pen-related problems, this paper contains the theoretical background for the recognition mechanism and a description of the methods used to perform a high quality and high speed recognition-process with a minimum of executable code (∼18KB on IBM-AT kompatible machines under MS-DOS). Furthermore it contains the most significant performance parameters such as speed and recognition accuracy. The proposed method has been implemented on an INFOS NotePad 386-SX pen-computer and on the associative processor AM 3 developed within the PROMETHEUS project at the Department for Technical Computer Sciences at J.W.Goethe-University in Frankfurt. The acceleration of the recognition mechanism by using the associative type of parallelism will be shown.