作者: A. Vinciarelli , M. Perone
DOI: 10.1109/ICDAR.2003.1227781
关键词:
摘要: This work describes an online handwriting recognition system working in combination with offline recognizer. The input data is first transcribed by theonline recognizer, then converted into bitmapand recognized the system. outputs ofthe two recognizers are combined probabilisticallyresulting a classifier out-performing both individualsystems. Experiments were performed over databaseof single digits. error rate of recognizeris reduced 43% when offlinesystem applied.