中文说明： 设计实现了一个自由手写体数字识别系统。文中首先对待识别数字的预处理进行了介绍，包括二值化、噪声处理、图像分割、归一化、细化等图像处理方法；其次，探讨了数字字符特征向量的提取；最后采用了bp神经网络算法,并以MATLAB作为编程工具实现了具有友好的图形用户界面的自由手写体数字识别系统。实验结果表明，本方法具有较高的识别率，并具有较好的抗噪性能。
English Description：
A free handwritten numeral recognition system is designed and implemented. In this paper, firstly, the preprocessing of the number to be recognized is introduced, including binarization, noise processing, image segmentation, normalization, thinning and other image processing methods; secondly, the extraction of digital character feature vector is discussed; finally, the BP neural network algorithm is adopted, And MATLAB is used as a programming tool to realize a free handwritten digit recognition system with friendly graphical user interface. The experimental results show that this method has high recognition rate and good anti noise performance.