12/23/2024
Before the university closes for the holidays, we would like to congratulate and highlight our first graduate of the PhD in Computer Science program. Samah Baraheem, graduated in May 2024. Congratulations, Samah! Check out her PhD dissertation below.
Title: Automatic Sketch-To-Image Synthesis and Recognition
Abstract: Image is used everywhere since it conveys a story, a fact, or an imagination without any words. Thus, it can substitute sentences because the human brain can extract knowledge from images faster than words. However, creating an image from scratch is not only time-consuming, but also a tedious task that requires skills. Creating an image is not a trivial task since it contains rich features and fine-grained details, such as colors, brightness, saturation, luminance, texture, shadow, and so on. Thus, in order to generate an image in less time and without any artistic skills, sketch-to-image synthesis can be used. The reason is that hand sketches are much easier to produce, where only the key structural information is contained. Moreover, it can be drawn without skill and in less time. In fact, because sketches are often simple and rough black and white and sometimes imperfect, converting a sketch into an image is not a trivial problem. Furthermore, since the generated images have been improved over time regardless of the input modality, it sometimes becomes hard to distinguish between the synthetic images and genuine ones. Of course, this improves the content and the media, but it is considered as a serious threat regarding legitimacy, authenticity, and security. Thus, an automatic detection system of AI-generated images is a legitimate need. The contribution of this dissertation is two-fold. We first generate high-quality realistic images from simple, rough, black and white sketches, where a newly collected dataset of sketch-like images is compiled for training purposes. Second, since artificial images would have advantages and disadvantages in the real world, we create an automated system that is able to detect and localize synthetic images from genuine ones, where a large dataset of generated and real images is collected to train a CNN model.