A Handwriting Recognition System Based on Visual Input

摘要: One of the most promising methods interacting with small portable computing devices such as personal digital assistants is use handwriting. However, for data acquisition touch sensitive pads, which are limited in size, and special pens required. In order to render this communication method more natural Munich & Perona [11] proposed visually observe writing process on ordinary paper automatically recover pen trajectory from video image sequences. On basis work we developed a complete handwriting recognition system based visual input. will describe employed tracking, feature extraction, statistical recognition. The di erences compared classical on-line systems modi cations tracking be discussed. demonstrate feasibility approach evaluation results writer independent unconstrained task presented.