Quality Testing for Pressed Raised Character on Metal Label Using GRBF Networks

Abstract:

In accordance with the obvious characteristics of the pressed raised character image and the shortages of the template matching method.
a new method of using the general radial-basis function neural network (GRBFN) for testing the quality of the pressed character is presented. The structures and training methods of GRBFN are fully analyzed, as well as the functionality of hidden layer, excited focus and area. The results show the checker based on GRBFN has highly checking ratio for the label pressed raised characters. It is suited to the quality testing of raised characters.

• Periodical: Key Engineering Materials (Volumes 315-316)
• Pages: 691-695
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.315-316.691
• Online since: July 2006
• Authors: Chang Hou Lu, J.H. Cao, Jian Mei Li, Xue Yong Li
• Keywords: Neural Network (NN), Pressed Raised Character, Quality Testing

References

[1] C.H. Lu, J.H. Cao and X.Y. Li: Journal of Mechanical Engineering, Vol. 41 (2005) No. 2, p.87.

[2] Z.H. Zhou: Journal of computer, Vol. 25 (2002) No. 1, p.1.

[3] B.C. Sung: IEEE trans. NN, Vol. 8 (1997) No. 1, pp.43-53.

[4] G.H. Wan: Computer Engineering and Application, Vol. 38 (2002) No. 6, p.204.

[5] B. Verma: Pattern Recognition Letters, Vol. 22 (2001) No. 9, pp.991-998.

[6] T. Poggio and F. Girosi: Proceeding of the IEEE, Vol. 78 (1990) No. 9, p.1481.

[7] M.J. Orr: Neural Computation, Vol. 7 (1995), p.606.

[8] M.T. Musaoi and et al: Neural Networks, Vol. 5 (1992), pp.595-603.