Computer Vision

ADVANCED COURSE
3 units

SKILL SETS
Image formation / Image filtering / Image Analysis / Image Understanding / 

TOOLS 
Machine learning techniques / Linear algebra / Vector representations / Python

DESIGNED BY
Professor Hany Farid with assistance by Dr. Shruti Agarwal

DATASCI 281 introduces the theoretical and practical aspects of computer vision, covering both classical and state of the art deep-learning based approaches. This course covers everything from the basics of the image formation process in digital cameras and biological systems, through a mathematical and practical treatment of basic image processing, space/frequency representations, classical computer vision techniques for making 3-D measurements from images, and modern deep-learning based techniques for image classification and recognition.

The course will focus on developing understanding of processes by which images are formed and represented, and of the building blocks of classical computer vision techniques. Students will also understand key components of modern computer vision techniques, and how artificial neural networks are employed in these processes. Students will gain experience determining and applying appropriate mathematical and computational tools, and building computer vision systems to solve real-world problems. Developing an ability to read, understand, and apply concepts and techniques from computer-vision research literature is another course objective intended to ensure students are able to continue their learning and expertise in this domain after they complete the course.