Computer Vision

Catalog description

This course explores the theoretical foundations and practical applications of Computer Vision (CV), the field of artificial intelligence that enables computers to derive meaningful information from digital images, videos, and other visual inputs. For the doctoral candidate, this course moves beyond basic image processing to focus on the high-level understanding of visual data through advanced machine learning and deep learning techniques. Students will investigate the entire computer vision pipeline, from low-level image acquisition and feature extraction to high-level tasks such as object detection, image segmentation, and facial recognition. The course places a strong emphasis on Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). Additionally, students will explore specialized domains including medical imaging informatics, autonomous vehicle perception, and 3D scene reconstruction. The course concludes with a critical look at the challenges of "visual bias" and the ethical implications of pervasive visual surveillance.