Making a personal recognition dictionary from characters automatically generated by using handwriting model

Abstract

Proposes a method which makes a personal recognition dictionary from pseudo-characters that are automatically generated by using a computer model of human handwriting. The method consists of three stages. First a handwriting model mimicking an individual person is derived from his real handwritten characters. Next, pseudo-handwritten characters are generated by using the model, and finally a personal recognition dictionary is built from those generated characters. The proposed method requires much fewer of the user's real handwritten characters than conventional methods. This results in reducing the users' burden. The experimental results demonstrate that pseudo handwritten characters have a high enough quality to make useful personal dictionaries for handwritten character recognition. >