Fergus, R. and Perona, P. and Zisserman, A. (2003) Object class recognition by unsupervised scale-invariant learning. In: 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE , Los Alamitos, CA, pp. 264-271. ISBN 0769519008 http://resolver.caltech.edu/CaltechAUTHORS:20111018-135127518
Full text not available from this repository.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20111018-135127518
We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of the object: shape, appearance, occlusion and relative scale. An entropy-based feature detector is used to select regions and their scale within the image. In learning the parameters of the scale-invariant object model are estimated. This is done using expectation-maximization in a maximum-likelihood setting. In recognition, this model is used in a Bayesian manner to classify images. The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).
|Item Type:||Book Section|
|Additional Information:||© 2003 IEEE. Issue Date: 18-20 June 2003. Date of Current Version: 15 July 2003. Timor Kadir for advice on the feature detector. D. Roth for providing the Cars (Side) dataset. Funding was provided by CNSE, the UK EPSRC, and EC Project CogViSys.|
|Other Numbering System:|
|Official Citation:||Fergus, R.; Perona, P.; Zisserman, A.; , "Object class recognition by unsupervised scale-invariant learning," Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on , vol.2, no., pp. II-264- II-271 vol.2, 18-20 June 2003 doi: 10.1109/CVPR.2003.1211479 URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1211479&isnumber=27266|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Tony Diaz|
|Deposited On:||25 Oct 2011 15:13|
|Last Modified:||25 Oct 2011 15:13|
Repository Staff Only: item control page