Hand-written character recognition using MEMS motion sensing technology

In this paper, a micro inertial measurement unit (muIMU) based on micro electro mechanical systems (MEMS) sensors is applied to sense the motion information produced by characters written by human subjects. The muIMU is built to record the three-dimensional accelerations and angular velocities of the motions during hand-writing. (Here we write the characters in a plane, so only two accelerations and one angular velocity are taken from muIMU in processing the data discussed in this paper). Then, we compared the effectiveness of data processing methods such as FFT (fast Fourier transform) and DCT (discrete cosine transform) by showing their corresponding experimental results. Subsequently, we gave an analysis of these two methods, and chose DCT as the preferred data processing method. For character recognition (26 English alphabets and 10 numerical digits), unsupervised network self-organizing map (SOM) is applied to classify the characters and comparatively good results are obtained. Our goal is to show the feasibility of character recognition based on selected sensor motion information, and provide a potential technology for human-gesture recognition based on MEMS motion sensors.

[1]  Lakhmi C. Jain,et al.  Recent advances in artificial neural networks: design and applications , 2000 .

[2]  David F. McAllister,et al.  Self-tracking of human motion for virtual reality systems , 1994, Electronic Imaging.

[3]  Gi-Joon Nam,et al.  Two-dimensional position deteciton system with MEMS accelerometer for MOUSE applications , 2001, DAC '01.

[4]  Xiaoyong Yang.  An enhanced SOFM method for automatic recognition and identification of digital modulations , 2004, Proceedings. DELTA 2004. Second IEEE International Workshop on Electronic Design, Test and Applications.

[5]  The Duy Bui,et al.  Recognition of Vietnamese sign language using MEMS accelerometers , 2005 .

[6]  Philip Heng Wai Leong,et al.  A Novel Real-Time Error Compensation Methodology for μIMU-based Digital Writing Instrument , 2006, 2006 IEEE International Conference on Robotics and Biomimetics.

[7]  B. Milner.  Handwriting recognition using acceleration-based motion detection , 1999 .

[8]  Adrian David Cheok,et al.  Micro-accelerometer based hardware interfaces for wearable computer mixed reality applications , 2002, Proceedings. Sixth International Symposium on Wearable Computers,.

[9]  Kyoung-Ho Kang,et al.  Self-contained spatial input device for wearable computers , 2003, Seventh IEEE International Symposium on Wearable Computers, 2003. Proceedings..

[10]  Josh H. M. Lam,et al.  Towards a human airbag system using /spl mu/IMU with SVM training for falling-motion recognition , 2005, 2005 IEEE International Conference on Robotics and Biomimetics - ROBIO.

[11]  Soo-Young Lee,et al.  On-Line Handwritten Character Recognition with 3D Accelerometer , 2006, 2006 IEEE International Conference on Information Acquisition.

[12]  J. Chae,et al.  Two-dimensional position detection system with MEMS accelerometer for mouse applications , 2001, Proceedings of the 38th Design Automation Conference (IEEE Cat. No.01CH37232).

[13]  Chi Chiu Tsang,et al.  A Calibration Method for MEMS Inertial Sensors Based on Optical Tracking , 2007, 2007 2nd IEEE International Conference on Nano/Micro Engineered and Molecular Systems.