On-line computer recognition of proposed standard ANSI(USASI) handprinted characters
作者:
Highlights:
•
摘要
A robust real-time system for recognition of handprinted characters of the upper case English alphabet is described. The basic system is suited to implementation on small computers and has been designed to accept characters conforming to the stroke types and sequences suggested by a proposed ANSI(USASI) standard. Experiments with 2340 samples from 10 untrained subjects yielded an overall character recognition accuracy of 98.3%. The system is quite robust with respect to size and stylistic variations. The robustness and real-time operation of the system are largely attributed to the preprocessing and stroke identification techniques developed, which include a new two-stage syntactic classifier for the identification of curvilinear strokes.
论文关键词:Character recognition,Syntactic pattern recognition,Stroke identification,Real-time system,Handprinted characters
论文评审过程:Received 2 May 1978, Available online 19 May 2003.
论文官网地址:https://doi.org/10.1016/0031-3203(78)90005-5