Investigation of generative adversarial network models' image generation performance

Abstract

One of the most important developments in the field of deep learning is the generative adversarial network(GAN) models. These models, known as GAN, are the most modern approaches used in image editing, image/cartoon painting, high resolution super image acquisition, and the transfer of the texture/pattern in another image to another image. In this study, the performances of GAN models (cGAN, DCGAN, InfoGAN, SGAN, ACGAN, WGAN-GP, LSGAN), which are commonly used in the literature, in producing synthetic images very similar to the real images were investigated. The originality of the study is the development of a hybrid GAN model (cDCGAN) that incorporates the advantages of cGAN and DCGAN and evaluates the performances of GAN methods in comparison with deep learning based convolutional neural networks (CNN). Synthetic images similar to the images in the data sets were generated with the encoded models. Fréchet inception distance (FID) metric and CNN were used to calculate the similarity of the produced synthetic images to the existing images so as to evaluate the model performance. In the experimental studies, time-based image production performances of all models were evaluated. As a result, it was observed that the images produced by the LSGAN model provide a high classification performance rate, but with DCGAN and WGANGP, it produces clearer noise images.

Generative Artificial Intelligence: A Historical and Future Perspective

“…The general pseudocode of the GAN model is as Figure 6. [28]. can employ binary classifiers to distinguish between fake and real images.…”

An examination of synthetic images produced with DCGAN according to the size of data and epoch

“…Examples of facial images with glasses, hats, curls, straight hair, different facial shapes, and facial expressions are shown in figure 1. GANs are a machine learning technique consisting of two neural networks that are simultaneously trained [12]. The first of these networks is the Generator network, which produces the fake data, and the other is the Discriminator network, which is used to distinguish the generated fake image from the real image [13].…”