An algorithm of cursive handwritten numerals segmentation based on multi mould is proposed.

A knowledge-based recognition system of unconstrained handwritten numerals is proposed.

This paper mainly discusses the application in the handwritten numeral pattern-recognition of artificial neural network.

At the same time, the exist difficult in handwritten digit recognition are pointed, and the possibility of solving the problems using NN technique is proved.

Results of testing the same sample set show that a good correctness rate of handwritten digit recognition is obtained by integration models.

To counter the complexity and limitation of traditional digital recognition methods,a kind of handwritten numeral recognition method based on BP neural network is proposed.

In this paper, many preprocessing ways of handwritten numeral are used.

Artificial Neural Network model for handwritten digit recognition based on template matching;

Handwritten Digit Recognition Method Based on Combination Features;

This paper presents the theory to recognize handwritten digits by the BP neural network,and an improved algorithm to accelerate the running speed of the network based on the analysis of the traditional BP algorithm s running speed.