Lecture 9: Constraints: Visual Object Recognition

Flash and JavaScript are required for this feature.

Download the video from iTunes U or the Internet Archive.

Description: We consider how object recognition has evolved over the past 30 years. In alignment theory, 2-D projections are used to determine whether an additional picture is of the same object. To recognize faces, we use intermediate-sized features and correlation.

Instructor: Patrick H. Winston

Related Resources

Prof. Winston wrote about the Rumpelstiltskin principle, which was briefly mentioned in this lecture, in the Slice of MIT blog.