Application of Deep Convolutional Generative Adversarial Networks to Generate Pose Invariant Facial Image Synthesis Data

Abstract

The field of technology is currently developing rapidly, one of the developments is artificial intelligence. Artificial intelligence can still find it difficult to solve problems that are easy for humans to do but difficult for computers to describe, such as facial recognition. There are still several problems related to the existing facial recognition model, namely, the facial recognition model is still unable to recognize facial shapes that are not in a perfect state due to several factors such as face position, lighting, expression, and obstacles covering the face. Among these several factors, the most influencing factor is the position of the face. Therefore, in this study, deep convolutional generative adversarial networks (DCGANs) will be applied to generate fake image data with varying face positions. This research will be carried out starting from collecting data, processing data, designing and training models, hyperparameter tuning, and lastly analyzing test results. Based on the results of hyperparameter tuning that were performed sequentially, the best hyperparameter combination produced is 200 epoch, 0.002 Generator learning rate, 0.5 Generator momentum/beta1, Adam as Generator optimizer, 0.0002 Discriminator learning rate, 0.5 Discriminator momentum/beta1, and Adam as Discriminator optimizer. The combination of hyperparameters gives a result with an FID score of 74.05. Based on testing with human observers, generated fake images have relatively good results, but there are still few bad fake image results