Error Repair in Human Handwriting - An Intelligent User Interface for Automatic On-Line Handwriting Recognition

Several important factors, such as recognition accuracy, user acceptance, and system usability, have to be considered in designing an interface of a handwriting recognition system. Since both users and recognition algorithms make mistakes, it is desirable for the user interface of a handwriting recognition system to have mechanisms recovering from errors. In this paper we address the problem of error repair in on-line handwritingrecognition. First, we perform a user study on error occurrences and corresponding repair patterns in human handwriting. Based on a data analysis, we have identified typical types of errors and repair patterns. We then propose methods to deal with error repair in an on-line handwriting system. We have developed a prototype system to demonstrate and evaluate the proposed error handling mechanisms. The system extends NPen++, an on-line handwriting recognition system developed in our lab, by providing error repair abilities to users in addition to its high recognition rate. The experimental results indicate that the error handling mechanisms can significantly improve the system performance in case of the data containing error repair.