Title :
Recognition of regulation writing characters by accelerometer in smart phone based on HMM
Author :
Yang Li ; Tobe, Y. ; Murase, K. ; Yunlong Zhao
Author_Institution :
Dept. of Comput. Sci. & Technol., Harbin Eng. Univ., Harbin, China
Abstract :
With the development of mobile devices, real-time recognition and detection by mobile devices are becoming more popular. In this paper, we design a mechanism of recognizing the 26 uppercase characters, space, comma symbol and dot symbol rapidly by tri-accelerometer in smartphone, in order to extend the input method. In this system, a serial of methods has been used to capture the writing tracks according to the motion of the phone. At the same time, the less learning algorithms were used in order to reduce the requirements of performance as far as possible. The experiment results show the recognition accuracy is almost greater than 80.25%.
Keywords :
accelerometers; gesture recognition; hidden Markov models; smart phones; hidden Markov model; recognition accuracy; regulation writing character recognition; smartphone; triaccelerometer; Abstracts; Acceleration; Accelerometers; Accuracy; Character recognition; Gravity;
Conference_Titel :
System Integration (SII), 2014 IEEE/SICE International Symposium on
Conference_Location :
Tokyo
Print_ISBN :
978-1-4799-6942-5
DOI :
10.1109/SII.2014.7028142