Previous studies have used convolutional neural networks (CNN) to classify synthetic images created by generative adversarial networks (GANs) to confirm images as either being synthetic or natural. Similar to other research, this thesis will cover the classification of synthetic images witha CNN. However, instead of classifying images created by GANs, a latent diffusion based generator is covered instead. This comparative study gathered results from the performance of botha human baseline as well as a CNN’s ability to classify images generated by stable diffusion and real images created by or taken by humans.The results from this study show that the CNN created greatly outperformed the human baseline when classifying the data sets over multipledifferent image domains.
Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:his-22674 |
Date | January 2023 |
Creators | Karlsson, Sacharias, Johansson, Niklas, Freden, Mikael |
Publisher | Högskolan i Skövde, Institutionen för informationsteknologi |
Source Sets | DiVA Archive at Upsalla University |
Language | Swedish |
Detected Language | English |
Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
Format | application/pdf |
Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.0016 seconds