A New Feature Fusion Method for Handwritten Character Recognition Based on 3D Accelerometer

Abstract:

In this paper, a new feature fusion method for Handwritten Character Recognition based on single tri-axis accelerometer has been proposed. The process can be explained as follows: firstly, the short-time energy (STE) features are extracted from accelerometer data. Secondly, the Frequency-domain feature namely Fast Fourier transform Coefficient (FFT) are also extracted. Finally, these two categories features are fused together and the principal component analysis (PCA) is employed to reduce the dimension of the fusion feature. Recognition of the gestures is performed with Multi-class Support Vector Machine. The average recognition results of ten Arabic numerals using the proposed fusion feature are 84.6%, which are better than only using STE or FFT feature. The performance of experimental results show that gesture-based interaction can be used as a novel human computer interaction for consumer electronics and mobile device.

• Periodical: Applied Mechanics and Materials (Volumes 44-47)
• Pages: 1583-1587
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.44-47.1583
• Online since: December 2010
• Authors: Zhen Yu He
• Keywords: Feature Fusion, Gesture Recognition, Human-Computer Interaction (HCI), Short-Time Energy, Tri-Axial Accelerometer Data

References

[1] Jiayang Liu, Lin Zhonga, Jehan Wickramasuriyab and Venu Vasudevan, uWave: Accelerometer-based personalized gesture recognition and its applications, Pervasive and Mobile Computing, Vol 5 (2009), pp.657-675.

DOI: 10.1016/j.pmcj.2009.07.007

[2] Eun-Seok Choi, Won-Chul Bang, et. al, Beatbox Music Phone: Gesture Interactive Cell phone using Tri-axis Accelerometer, IEEE Int. Conference on Industrial Technology, (2005).

DOI: 10.1109/icit.2005.1600617

[3] Sung-Jung Cho, Eunseok Choi, et. al., Two-stage Recognition of Raw Acceleration Signals for 3-D Gesture- Understanding Cell Phones, 10th IWFHR, La Baule, France, Oct. (2006).

[4] Sung-Do Choi, A.S. Lee, Soo-Young Lee, On-Line Handwritten Character Recognition with 3D Accelerometer, IEEE International Conference on Information Acquisition, 2006, pp.845-850.

DOI: 10.1109/icia.2006.305842

[5] S. Kallio, J. Kela and J. Mantyjarvi, Online gesture recognition system for mobile interaction, IEEE International Conference on Systems, Man and Cybernetics, vol 3 (2003), p.2070-(2076).

DOI: 10.1109/icsmc.2003.1244189

[6] L.R. Rabiner, R.W. Schafer, Digital Processing of speech signals, Prentice Hall, (1978).

[7] Alan V. Oppenheim, Ronald W. Schafer and John R. Buck, Discrete-time signal processing (2en ed. ) Prentice Hall, (1999).

[8] Jian Yang, Jing-yu Yang, David Zhang and Jian-feng Lu, Feature fusion: parallel strategy vs. serial strateg, Pattern Recohnition, vol 3(2003), pp.1369-1381.

DOI: 10.1016/s0031-3203(02)00262-5

[9] J. Mantyla, J. Himberg, T. Seppanen, Recognizing Human Motion with Multiple Acceleration Sensors, IEEE International Conference on Systems, Man and Cybernetics, Tucson, USA, vol. 3494 (2001), pp.747-752.

DOI: 10.1109/icsmc.2001.973004