Skip to content


Prof. Masaki Nakagawa
Handwriting-based User Interfaces
On 2015-09-22 15:00 at G205
Due to the success of touch-sensitive smart phones and tablets, direct pointing
and direct manipulation has finally become common. Moreover, users can write
text, draw figures and annotate whatever they like with their fingers or pens
these devices. In this talk, I will present the belief that the ultimate merit
of handwriting-based user interfaces is to support human-centered and creative
work and describe the research and development that I have been conducting in
these 30 years. I will talk how we invented so called “touch scroll” in
1990’s, why and how we made a large database of on-line handwritten patterns
and report that our handwriting recognizer has been employed in 90% of smart
phones having handwriting input. Then, I will present the latest architecture
handwriting recognition required from user interfaces and applications, but the
details of pattern recognition algorithms will be omitted unless they are
required. Finally, I will present a future application, which is challenging to
pattern recognition, human interface and artificial intelligence communities,
i.e., automatic scoring of handwritten exams. (V. Hlavac, the host: The talk is
planned for 60 minutes)

Masaki Nakagawa, University of Agriculture and Technology, Tokyo

He has been working on handwriting recognition, pen-based user interfaces and
applications especially educational applications. Since 1980’s, he has been
collaborating with many companies. Especially with Hitachi and Fujitsu, his
laboratory made handwriting recognizers for real commercial use. He has been
continuing handwriting recognition research to improve accuracy, performance
robustness, In 2011, he made a start-up named iLabo, which now sells the best
handwriting recognizers for touch-based smart phones, tablets and so on. In
2012, iLabo was selected as one of the 100 most promising ventures in Japan by
Nikkei Business. In 1990, he also proposed User Interfaces for tablet devices
and showed several educational applications using various sizes of tablets. His
U.S. patents to scroll the window in proportion to the pen speed, which is
so-called “touch scroll”, were sold from his university to a company by a
significant price. It was the highest amount among all the Japanese
in the fiscal year 2010. He is now employing recent machine learning methods
handwriting recognition, user interfaces and IT education. He is also working
historical document processing to read excavated documents from the Heijo
in Nara, Japan and to read Chu Nom documents in Vietnam. He is a fellow of IAPR
(International Association of Pattern Recognition), IEICE (Institute of
Electronics, Information and Communication Engineers, Japan) and IPSJ
(Information Processing Society of Japan).
Back to the list