Recognition of Handwritten Digit Using Convolutional Neural Network

Abstract

In recent decades, Convolutional Neural Network (CNN) has achieved remarkable results in both the research field and the application field due to the significant achievement acquired in computer technology. However, handwritten digit recognition still has great development space due to its complexity. At present, the recognition of handwriting has received intensive attention from many researchers. In this paper, we introduce the Convolutional Neural Network (CNN) based on TensorFlow framework is introduced, and use the MINIST data set which is widely used in handwritten digit recognition to analyze the structure and parameters of the CNN model. Furthermore, we utilize different functions and structures and analyze the problems in experiments, so as to provide some reference for the research and development aiming at handwritten digit recognition.