Office of the Registrar

Introduction to Computer Vision (3) Humans effortlessly recognize objects and places and form opinions of them from visual inputs. However, it is very difficult for a computer algorithm to extract useful content from images and videos. Computer vision has wide-ranging applications such as gesture capture (Kinect), face recognition in cameras, image-based search (Google), autonomous vehicles (Google car), biometrics using retinal image, medical imaging (image-guided surgery), and surveillance analysis. This course is an introduction to current algorithms used in computer vision and computational photography. Topics include image statistics, image processing, color vision, texture synthesis, image warping, motion tracking, automatic image editing, object and scene recognition, 3D reconstruction, face detection, and image databases. Students learn state-of-the art mathematical tools in computer vision and also gain hands-on experience in image manipulation. Simple machine learning algorithms are also introduced. Working models of computer vision are demoed in class and homework includes programming exercises in MATLAB or Python. Recommendation: CSC-280 and MATH-221. Note: Basic programming skills and interest in solving simple math is required.