Leung, Thomas K. and Burl, Michael C. and Perona, Pietro (1998) Probabilistic affine invariants for recognition. In: 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society , Los Alamitos, CA, pp. 678-684. ISBN 0-8186-8497-6 http://resolver.caltech.edu/CaltechAUTHORS:20111222-145123625
Full text is not posted in this repository. Consult Related URLs below.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20111222-145123625
Under a weak perspective camera model, the image plane coordinates in different views of a planar object are related by an affine transformation. Because of this property, researchers have attempted to use affine invariants for recognition. However, there are two problems with this approach: (1) objects or object classes with inherent variability cannot be adequately treated using invariants; and (2) in practice the calculated affine invariants can be quite sensitive to errors in the image plane measurements. In this paper we use probability distributions to address both of these difficulties. Under the assumption that the feature positions of a planar object can be modeled using a jointly Gaussian density, we have derived the joint density over the corresponding set of affine coordinates. Even when the assumptions of a planar object and a weak perspective camera model do not strictly hold, the results are useful because deviations from the ideal can be treated as deformability in the underlying object model.
|Item Type:||Book Section|
|Additional Information:||© 1998 IEEE. Date of Current Version: 06 August 2002. This work is supported by the NSF engineering research center for neuromorphic systems engineering at Caltech, a National Young Investigator Award to PP and a Berkeley Fellowship to TKL.|
|Other Numbering System:|
|Official Citation:||Leung, T.K.; Burl, M.C.; Perona, P.; , "Probabilistic affine invariants for recognition," Computer Vision and Pattern Recognition, 1998. Proceedings. 1998 IEEE Computer Society Conference on , vol., no., pp.678-684, 23-25 Jun 1998 doi: 10.1109/CVPR.1998.698677 URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=698677&isnumber=15135|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Tony Diaz|
|Deposited On:||22 Dec 2011 23:57|
|Last Modified:||22 Dec 2011 23:57|
Repository Staff Only: item control page