Part-based statistical models for object classification and detection

We propose using simple mixture models to define a set of mid-level binary local features based on binary oriented edge input. The features capture natural local structures in the data and yield very high classification rates when used with a variety of classifiers trained on small training sets, ex...

Full description

Saved in:
Bibliographic Details
Published in2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) Vol. 2; pp. 734 - 740 vol. 2
Main Authors Bernstein, E.J., Amit, Y.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2005
Subjects
Character recognition
Degradation
Layout
Machine vision
Object detection
Photometry
Robustness
Scalability
Statistics
Training data
Online AccessGet full text

Cover

More Information
Summary:We propose using simple mixture models to define a set of mid-level binary local features based on binary oriented edge input. The features capture natural local structures in the data and yield very high classification rates when used with a variety of classifiers trained on small training sets, exhibiting robustness to degradation with clutter. Of particular interest is the use of the features as variables in simple statistical models for the objects thus enabling likelihood based classification. Pre-training decision boundaries between classes, a necessary component of non-parametric techniques, are thus avoided. Class models are trained separately with no need to access data of other classes. Experimental results are presented for handwritten character recognition, classification of deformed BTEX symbols involving hundreds of classes, and side view car detection.
ISBN:0769523722
9780769523729
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2005.270