Abstract-This paper presents an accelerometer-based pen device for online handwriting recognition applications. The accelerometer-based pen device consists of a triaxial accelerometer, a microcontroller, and an RF wireless transmission module. Users can hold the pen device to write numerals in air without space limitations. The accelerations generated by hand motions are generated by the accelerometer embedded in the pen device, and are transmitted to a personal computer for further signal preprocess via the wireless module. Subsequently, a dynamic time warping (DTW) algorithm is applied to align the accelerations and search class templates for each digit in the training stage. Finally, the accelerations can be recognized via the alignment with the class templates in the testing stage. The average user-dependent and userindependent recognition rates were 90.6% and 84.8%, respectively. Our experimental results have successfully validated the effectiveness of the accelerometer-based pen device for 3-dimensional (3-D) online handwriting recognition.
IndexTerms-Onlinehandwriting recognition, accelerometer-based input device, dynamic time warping.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.