Design of Online Handwritten Numeral Recognition System

Abstract:

An effective online handwritten numeral recognition system is designed based on the Matlab GUI interface. The coordinate locations of the handwritten numerals are recorded, from which the stroke direction variations and the 2-dimensional distance between the starting point and ending point of the numeral are obtained as the features, which are encoded into 42 bits binary sequence, and then input to the Hopfield neural network. The associative memory function of the Hopfield neural network can implement the learning and recognition of the handwritten numeral. Testing results show that the designed system has high recognition rate and fast recognition speed.

• Periodical: Applied Mechanics and Materials (Volumes 201-202)
• Pages: 329-332
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.201-202.329
• Online since: October 2012
• Authors: Yue Fen Chen, Jun Huan Lin, Guo Ping Li
• Keywords: Handwritten Numeral Recognition, Hopfield Neural Network, Stroke Direction

References

[1] L.L. Cheng, N. Kazuki, HiroshiSako and F. Hiromichi. Patten Recognition, Vol. 37(2004) No.2, pp.265-279

[2] W. L. Jiang, W. Wang, Z.X. Sun. Computer science. Vol. 3(2006)No.9, pp.207-210.

[3] S.Y. Yang. Pattern Recognition and Intelligent Computation. (Beijing Electron Industry Press , China 2009).

[4] Z. H. Yang. Computer Engineering and Applications. Vol. 44(2008) No.13, pp.27-29.

[5] C.Z. Bai. Applied Mathematics and Computation, (2008)No.203, pp.72-79.