Katsuhiko Akiyama

Hybrid pen-input character recognition system based on integration of online-offline recognition

Describes a handwritten character recognition system that integrates offline recognition requiring a bitmap image and online recognition involving an input pattern as a sequence of x-y coordinates. Offline recognition performs well for painted or overwritten patterns (for which online recognition would not be suited), whereas online recognition is suitable for very deformed patterns (for which offline recognition is not suited). Because each method has different recognition capabilities, the methods complement each other when integrated together. We have implemented a hybrid handwritten character recognition system in which the recognition results of the offline and online recognizer are integrated to create an improved product. After testing several integration methods for a handwritten character database, we found that the best method increased the recognition rate from 73.8% (offline) and 84.8% (online) to 87.6% (integrated).

Handwriting-based learning materials on a tablet PC: a prototype and its practical studies in an elementary school

This paper presents handwriting-based learning materials (HLMs) on a tablet PC and their practical studies in an elementary school. We designed HLMs to be created using HLM components or a HLM template for teachers to create their original materials. Practical studies demonstrated that HLMs could be effectively used when children expressed and presented their ideas in a classroom and when they practiced calculations and characters by hand. We also investigated the application of a handwriting recognition technique to automatically check childrens handwritten answers to drill materials. Using questionnaires, we confirmed that automatic checking not only saved time but also improved the childrens motivation to learn. HLMs were enthusiastically embraced by both field teachers and children.