A Computer Vision Sampler

This course explores concepts in visual recognition, visual motion analysis, and visual reconstruction through a sample of techniques. There will be lectures, homework, and two exams.

The class meets on Tuesdays and Thursdays from 8:30 am to 9:45 am in room 2231 of the French Family Science Building.

However, the first three lectures will be on Zoom (click here to access or access through Sakai). In person lectures will start on January 18.



  • The midterm exam is on Thursday, February 24, from 8:30 am to 9:45 am.
  • The final exam is on Saturday, April 30, from 7 pm to 9 pm (two hours).
Both exams will be in French 2231.


We will use Ed STEM to communicate with each other outside of class or office hours.

An early theory of vision and action. This drawing from Descartes' Treatise on Man (1677) illustrates how the pineal gland (H), the site of the soul and the imagination, tilts in different ways inside the brain to blow spirits in the direction of tubes connected to the retina or the arm. Descartes had a rather hydraulic view of how the brain works, with spirits issuing from the pineal gland opening tiny tubes between the inside surface of the brain and the bodily organs to cause sensations and motion. Blowing spirits simultaneously towards tube 4-3 (which connects the inside of the brain to the retinal image of point B on the arrow) and tube 8-7 (which makes the arm move towards point B) causes the idea of the image of point B to correspond to the action of the arm pointing towards it. Similarly, repeatedly blowing spirits towards tube 4-3 and towards a corresponding tube in the seat of memory (another part of the brain, not shown) repeatedly opens and closes the memory tubes, which permanently deform as a consequence: A memory of the visual sensation is thereby formed.

COMPSCI 527, Duke University, Site based on the fluid 960 grid system