Design of Handwritten Numeral Recognition System Based on BP Neural Network

In the case of pattern recognition, handwritten numeral recognition is an important research topic in pattern recognition, and it has a very wide application in today's information society. However, the research on numeral recognition is still in the development stage, and the recognition effect is not ideal. A handwritten numeral recognition method based on BP neural network is proposed. Firstly, the image is grayed, binarized, smoothed, denoised and normalized to extract the pixel value; Then the designed BP neural network is trained, compared with the expected results and expected structure, and the BP neural network is adjusted and modified; Finally, the trained neural network is obtained. Experiments show that the accuracy of this method for handwritten digit recognition is 85.88%.