The comparison of handwritten digital image classification based on different neural networks

Abstract

Based on the wide application of neural network in image recognition and character recognition, this paper introduces three kinds of neural network models, compares and analyzes the performance of different neural network models in practical application. This paper first introduces the development of neural networks, especially the convolutional neural network, and the principles of the three neural network models in detail. Then building and training the three models that are based on the analysis. Finally, through experimental simulation, it shows that convolutional neural network has an outstanding advantage in handwritten digital image recognition.