Introduction to Computer Vision

Computer vision is the problem of getting a machine to extract meaning from pixels, and this course walks you through the classical pipeline that every modern system still rests on: how an image becomes a numerical array, how filtering and edge detection pull out structure, and how segmentation and description turn that structure into something a program can reason about. Expect weekly programming assignments, a couple of quizzes, a midterm, and a sizable project where you build an actual vision system end-to-end, with the final weeks moving into case studies on classification, recognition, and deep learning. It assumes you are comfortable with linear algebra, probability, and signal-processing intuition, and it serves as the natural on-ramp to graduate-level vision and ML electives, useful whether you end up in robotics, graphics, medical imaging, or any field where the input is an image rather than a row in a table.