Masaki Nakagawa

born on Oct. 31, 1954 in Tokushima, Japan.
Professor of Media Interaction
Department of Computer and Information Sciences
Associate Dean, Faculty of Engineering

Research Contributions

 He has been working on handwriting recognition, pen-based user interfaces and applications especially educational applications.

 In 1990's, he actively collaborated with companies. He led a project to make two databases of on-line handwritten Japanese character patterns: one with 120 people contributing 12,000 patterns each, and another with 163 participants contributing 10,000 patterns each. Patterns were collected mostly in their sentential contexts, and verified by machine and human inspection. A portion of the database is made freely available for research purpose. At present, more than 60 groups are using it, which includes over 10 groups from abroad.

 He collaborated with Fujitsu to combine an on-line recognizer and an off-line recognizer. Off-line recognizers are insensitive to wrong stroke order and overwriting while on-line recognizers performs well for cursive or deformed patterns as far as their stroke orders are correct. They complement each other. His group implemented a hybrid system first for on-line Japanese handwriting recognition and improved recognition rate significantly. They marked the highest recognition rate to the standard database: Kuchibue_d. Even suppressing the off-line prototype dictionary from 91.8 MB to 9.7 MB, they achieved almost the same performance, i.e., 98.6% correct recognition when combined with context post processing. He also collaborated with Hitachi and helped Hitachi to make a FEP (front end processor) to input Japanese characters by handwriting for a famous Japanese word processor "Ichitaro".

 Pen interfaces are suitable for creative work which is not bothered by input methods. He proposed Lazy Recognition in early 90s. He showed prototype applications on PDAs, desktop tablet PCs and large electronic whiteboards. He proposed GUI for the board which allows the user to manipulate the contents with an electronic marker from any standing position and attract audience's attention without hiding the board by his/her body. He also showed several educational applications using the board. This research was awarded by the Japanese Society for Engineering Education. He collaborated with Hitachi Soft, which is now selling their products worldwide. His U.S. patents to scroll the window in proportion to the pen speed (U.S. Patent No. 6,128,014,“Human Interactive Type Display System,”Filed: July 10, 1997, Date of Patent: Oct. 3, 2000, U.S. Patent No. 6,683,628,B1,“ Human Interactive Type Display System,” Filed: May 11, 2000, Date of Patent: Jan. 27, 2004 and others), which has been possessed by the university, were sold to a company by a significant price, which was the highest amount among all the Japanese universities in the fiscal year 2010.

 Since around 2000, He has been working on removing writing constraints as much as possible. Starting from writing-box-free recognition, recent papers report models, methods and practices. The model evaluates the likelihood composed of character segmentation, character recognition, character pattern structure and context. The likelihood of character pattern structure considers the plausible height, width and inner gaps within a character pattern that appear in Chinese characters composed of multiple radicals (subpatterns). The recognition system incorporating this model separates freely written text into text line elements, estimates the average character size of each element, hypothetically segments it into characters using geometric features, applies character recognition to segmented patterns and employs the model to search the text interpretation that maximizes likelihood as Japanese text. The writing-box-free recognizer based on the model is used for several products through iLabo corporation: a university-based start-up. Sumsung's GALAXY for NTT docomo's smart phones, NEC tablets, SONY tablets and so on bundle the recognizer as a standard input method. Moreover, he applied the handwriting recognition technology to a dictionary of ancient cursive scripts of 67,739 categories and made them searchable by writing it with pen on tablet or with mouse. This was awarded by a Japanese newspaper (Nikkan Kogyo).



Publications in English

Recent Projects


Social Services

He has been serving for several committees of the Japanese government on Industry-Government-Academia partnership and those on IT-oriented and IT supported learning.