Computer Vision

Catalog description

An important goal of artificial intelligence (AI) is to equip computers with the capability of interpreting visual inputs. Computer vision is an area in AI that deals with the construction of explicit, meaningful descriptions of physical objects from images. It includes the techniques for image processing, pattern recognition, geometric modeling, and cognitive processing. This course introduces students to the fundamental concepts and techniques used in computer vision, which includes image representation, image pre-processing, edge detection, image segmentation, object recognition and detection, and neural networks and deep learning. In addition to learning about the most effective machine learning techniques, students will gain the practical implementation of applying these techniques to real engineering problems.