Emojis Generation Based on Deep Convolution Generative Adversarial Network

Abstract

With the development of information technology and mobile communication, people's usage of emoji is increasing. However, designing emojis by artists can be time-consuming and costly. Therefore, this study attempts to use the Deep Convolution Generative Adversarial Network (DCGAN) method in deep learning to automatically generate emojis. DCGAN is a combination of Convolutional Neural Network (CNN) and Generative Adversarial Network (GAN). It introduces convolutional networks into the generative model for unsupervised training, which can improve the learning effect of the generator network. DCGAN consists of two different models: a generator model and a discriminator model. The generator's role is to produce fake images that are similar to the training images, and the discriminator's role is to judge whether the fake image is the same as a real image. During training, the generator continuously tries to defeat the discriminator by producing better and better fake images, while the discriminator tries its best to distinguish between real and fake images. Through continuous optimization of the generator and discriminator, this study can finally obtain clear new emojis. Overall, the images generated by DCGAN can largely fulfill our purpose. Many novel emojis could be obtained to replace the work of human artists. However, the quality of the generated emojis has some defects, and it is still necessary to screen out images with strange shapes that are not suitable for daily life.