The rapid advancement of generative neural networks has facilitated the creation of photorealistic images, raising concerns about the proliferation of misinformation. Detecting AI-generated fakes has become crucial, given their potential impact on public opinion and various sectors. This dataset presents a comparative analysis of real and AI-generated images, focusing on building a novel dataset named Realistic AI-Generated Image (RealAIGI) dataset.
This dataset supports the LookCursor AI project, which implements eye-tracking-based cursor control using OpenCV and Dlib. The primary file included is shape_predictor_68_face_landmarks.dat, a pre-trained model used to detect and map 68 facial landmarks essential for tracking eye movements. The dataset enables accurate facial feature detection, which is critical for cursor movement based on eye gaze. This resource is valuable for researchers working on assistive technology, human-computer interaction (HCI), and computer vision applications.
