University of Cambridge > Talks.cam > Inference Group > Face Recognition: Who's That Blonde?

Face Recognition: Who's That Blonde?

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Emli-Mari Nel.

Can we reliably recognize people automatically, and how far can we go? This talk will take a tour through the weird and wonderful world of Computer Vision, Machine Learning, and Bayesian Inference, to explain the intricacies of each step in the problem, and how it can be addressed.

An overview will be given of some fundamentals: Viola and Jones’ cascaded filters, Active Appearance Models, Constrained Local Models, and some methods for feature extraction. A number of new ideas will be presented: a Bayesian counterpart to Constrained Local Models, casting face recognition as an inference problem over a noisy channel, and using Markov Random Fields for higher-level tasks like face clustering. A live demonstration on around 13000 images with 6000 unique identities will be given.

This talk is part of the Inference Group series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2022 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity