Computer vision is powering technologies ranging from computer graphics to social robotics to autonomous vehicle. The course introduces tools of signal and image processing right up to neural networks. Students will write and debug programs that process images or video streams and construct recognizers to identify objects of interest for various purposes, such as scene understanding, facial recognition, or medical image processing. Students will work on a project of a topic of their choice and apply computer vision concepts, techniques, and tools to build computer vision applications.

As computing professionals, we are expected to practice our profession with the highest level of integrity and competence. This means a commitment to develop professional computing competencies and apply them responsibly in our practice. Learning activities in this course focus on the development and application of professional computing competencies through collaboration with peers, iterative development of project artifacts, and use of appropriate computing tools and platforms.