Webcast: Learning to Label Images (Microsoft Research)
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)
The FreePint Family is a family of resources to help information workers be more effective, raise the value of information in their organisations and contribute to success.
'FreePint... provides most of my professional development because it won't come through work and [other resources] just don't cut it.'
FUMSI Forum: Do you have a research question? Post it to the FUMSI Forum, where professionals share Q&A and useful tips on how to Find, Use, Manage and Share Information. It's free.