Title :
Off-line handwritten digit recognition based on improved BP artificial neural network
Author :
Zhang, Chengde ; Huang, Xiangnian
Author_Institution :
Sch. of Math. & Comput. Eng., Xihua Univ., Chengdu
Abstract :
This paper improved the adaptive factor of gradient to improve the transfer function on the base of the means of momentum, aimed at the training difficult to escape the flat area of error. This method had an application on off-line handwritten recognition. The results showed: this method could not only raise precision of BP artificial neural network, but also improve the convergent speed of it.
Keywords :
handwriting recognition; neural nets; improved BP artificial neural network; off-line handwritten digit recognition; transfer function; Artificial neural networks; Character recognition; Computer errors; Computer networks; Convergence; Handwriting recognition; Mathematics; Neurons; Presses; Transfer functions; BP artificial neural network; factor of gradient; off-line handwritten digit recognition; transfer function;
Conference_Titel :
Service Operations and Logistics, and Informatics, 2008. IEEE/SOLI 2008. IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-2012-4
Electronic_ISBN :
978-1-4244-2013-1
DOI :
10.1109/SOLI.2008.4686473
