Issue No.03 - May/June (2001 vol.16)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/5254.940024
The authors describe a new approach for data entry in wearable computing applications. A head-mounted digital camera records characters drawn by hand gestures or by a pointer on the forearm of the user. Similar to the Graffiti alphabet, the user draws each character in an isolated, single stroke. Based on their algorithm, a bank of finite state machines recognizes and processes the image's chain code to identify each hand-drawn character accurately.
character recognition, Graffiti-like alphabet, ubiquitous computing, wearable computing
Ömer Faruk Özer, Oguz Özün, C. Öncel Tüzel, Volkan Atalay, A. Enis Çetin, "Vision-Based Single-Stroke Character Recognition for Wearable Computing", IEEE Intelligent Systems, vol.16, no. 3, pp. 33-37, May/June 2001, doi:10.1109/5254.940024