Machine Learning for Computer Vision

by Roberto Cipolla (editor)

Throwing Down the Visual Intelligence Gauntlet.- Actionable Information in Vision.- Learning Binary Hash Codes for Large-Scale Image Search.- Bayesian Painting by Flexible Priors for Colour-Invariant Object Recognition.- Real-Time Human Pose Recognition in Parts from Single Depth Images.- Scale-Invariant Vote-based 3D Recognition and Registration from Point Clouds.- Multiple Classifier Boosting and Tree-Structured Classifiers.- Simultaneous detection and tracking with multiple cameras.- Applications of Computer Vision to an extreme test.

274 pages, Paperback

First published August 17, 2011