Current page: Information->Indexed and Annotated Bibliography
T. Y. T. Chan and L. Goldfarb
ABSTRACT
A new approach to the feature detection problem, i.e. learning {\"u}seful{\" }primitive features from raw images, is proposed. The {\"u}seful{\" }features are defined within the training environment as those that allow the learning agent (learning system) to form object representations sufficient for subsequent object recognition. In other words, the {\"u}seful{\" }features detected are discriminating, useful features. 
ECVision indexed and annotated bibliography of cognitive computer vision publications
This bibliography was created by Hilary Buxton and Benoit Gaillard, University of Sussex, as part of ECVision Specific Action 8-1
The complete text version of this BibTeX file is available here: ECVision_bibliography.bib
Primitive pattern learningSite generated on Friday, 06 January 2006