Handwritten digit generation based on generative adversarial networks

Abstract

This paper introduced a method to generate handwritten digit images by using the Generative Adversarial Networks model. Alternating loss and unstable accuracy were persistent problems during the training process. Human handwritten digit image generation plays a crucial role in criminal investigation and machine learning. There are many excellent and effective ordinary deep networks in machine learning programs for recognizing different pieces of images. However, only a few models can be used to construct new patterns. The experiment used Generative Adversarial Networks as the core algorithm to generate data that look like human-written digits. A Convolutional Neural Networks model is used as Discriminator to evaluate whether an image is genuine or created. The inverse convolutional layers in the code turn input into a two-dimensional pixel values picture. The MNIST provides as much as 60,000 data samples for training the program, where thousands of handwritten single digits, between 0 and 9, are displayed by 28*28 pixels images in greyscale. The pictures created by the algorithm initially looked blurry. But after thousands of training steps, the statistics appeared much more realistic. With more iterations carried out, the output images became more and more distinguishable.