Christoph Bregler and Jitendra Malik

EECS Department, University of California, Berkeley

Technical Report No. UCB/CSD-96-897

, 1996

http://www2.eecs.berkeley.edu/Pubs/TechRpts/1996/CSD-96-897.pdf

This paper describes a new technique for object recognition based on learning appearance models. The image is decomposed into local regions which are described by a new texture representation derived from the output of multiscale, multiorientation filter banks. We call this representation "Generalized Second Moments" as it can be viewed as a generalization of the windowed second moment matrix representation used by Garding & Lindeberg. Class-characteristic local texture features and their global composition is learned by a hierarchical mixture of experts architecture. The technique is applied to a vehicle database consisting of 5 general car categories (Sedan, Van with back-doors, Van without back-doors, old Sedan, and Volkswagen Bug). This is a difficult problem with considerable in-class variation. Our technique has a 6.5% misclassification rate, compared to eigen-images which give 17.4% misclassification rate, and nearest neighbors which give 15.7% misclassification rate.

---

BibTeX citation:

@techreport{Bregler:CSD-96-897,
    Author= {Bregler, Christoph and Malik, Jitendra},
    Title= {Learning Appearance Based Models: Hierarchical Mixtures of Experts Approach Based on Generalized Second Moments},
    Year= {1996},
    Month= {Nov},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/1996/5360.html},
    Number= {UCB/CSD-96-897},
    Abstract= {This paper describes a new technique for object recognition based on learning appearance models.  The image is decomposed into local regions which are described by a new texture representation derived from the output of multiscale, multiorientation filter banks. We call this representation "Generalized Second Moments" as it can be viewed as a generalization of the windowed second moment matrix representation used by Garding & Lindeberg. Class-characteristic local texture features and their global composition is learned by a hierarchical mixture of experts architecture. The technique is applied to a vehicle database consisting of 5 general car categories (Sedan, Van with back-doors, Van without back-doors, old Sedan, and Volkswagen Bug). This is a difficult problem with considerable in-class variation. Our technique has a 6.5% misclassification rate, compared to eigen-images which give 17.4% misclassification rate, and nearest neighbors which give 15.7% misclassification rate.},
}

EndNote citation:

%0 Report
%A Bregler, Christoph 
%A Malik, Jitendra 
%T Learning Appearance Based Models: Hierarchical Mixtures of Experts Approach Based on Generalized Second Moments
%I EECS Department, University of California, Berkeley
%D 1996
%@ UCB/CSD-96-897
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/1996/5360.html
%F Bregler:CSD-96-897