Share Email Print
cover

Proceedings Paper

Technological research on an application of neural network in character recognition
Author(s): Ping Li; Xiaofeng Mu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The artificial neural network Abstract simulates the principle of human neural element movement. It has many abilities such as study independently, adaptation itself , association,reasoning from analogy and generalization. The application of the artificial neural network in character recognition. The two procedurcs of character recognition ,i. e. ,the procedure of learning and the procedure of recognition ,were comprehensively described in this paper. The procedure of learning, that is, the procedure of training, the characteristic parameters produce the standard sample, and characters are recognized by using the standard sample, it can make continuously adaptation itself correction in use by the results of recognition. Because, of adopting the improved BP algorithm, reasonably selecting initial values, the adjusting method of learning rate, putting in momentum and introducing the simulated annealing method, the problems of the slow convergence speed of the original algorithm, bogging the local minimum and training paralysis was solved to improve the recognizing rate and obtained satisfactory results.

Paper Details

Date Published: 10 August 1998
PDF: 7 pages
Proc. SPIE 3558, Automated Optical Inspection for Industry: Theory, Technology, and Applications II, (10 August 1998); doi: 10.1117/12.318353
Show Author Affiliations
Ping Li, Changchun Institute of Optics and Fine Mechanics (China)
Xiaofeng Mu, Changchun Institute of Optics and Fine Mechanics (China)


Published in SPIE Proceedings Vol. 3558:
Automated Optical Inspection for Industry: Theory, Technology, and Applications II
Shenghua Ye, Editor(s)

© SPIE. Terms of Use
Back to Top