Webcast: Learning to Label Images (Microsoft Research)

For IR geeks only this hour long lecture from Rich Zemel, associate professor, Department of Computer Science, University of Toronto. Recorded August 15, 2006.

The problem of image labeling, in which each pixel is assigned to one of a finite set of labels, is a difficult problem, as it entails deciding which components of an image belong to the same object as well as classifying the components. I will describe two approaches we have taken to this problem, both utilizing conditional random fields to model contextual effects. The first uses a novel form of learning higher-order structure, which we developed for this work but has broader applicability. The second is a simpler and more efficient method that turns out to work just as well. In both cases, the model is trained on a database of images and the learning method estimates model parameters by maximizing a lower bound of the data likelihood. We examine performance on three real-world image databases, and compare our system to a standard classifier and other conditional random field approaches.

Source: Microsoft Research (via ResearchChannel.com)

This entry was posted on Tuesday, September 26th, 2006 at 12:32 am and is filed under Uncategorized. You can follow any responses to this entry through the RSS 2.0 feed. Responses are currently closed, but you can trackback from your own site.