Unsupervised Learning of Models for Recognition
- Creators
- Weber, M.
- Welling, M.
-
Perona, P.
Abstract
We present a method to learn object class models from unlabeled and unsegmented cluttered scenes for the purpose of visual object recognition. We focus on a particular type of model where objects are represented as flexible constellations of rigid parts (features). The variability within a class is represented by a joint probability density function (pdf) on the shape of the constellation and the output of part detectors. In a first stage, the method automatically identifies distinctive parts in the training set by applying a clustering algorithm to patterns selected by an interest operator. It then learns the statistical shape model using expectation maximization. The method achieves very good classification results on human faces and rear views of cars.
Additional Information
© Springer-Verlag Berlin Heidelberg 2000. This work was funded by the NSF Engineering Research Center for Neuromorphic Systems Engineering (CNSE) at Caltech (NSF9402726), and an NSF National Young Investigator Award to P.P. (NSF9457618). M.Welling was supported by the Sloan Foundation. We are also very grateful to Rob Fergus for helping with collecting the databases and to Thomas Leung, Mike Burl, Jitendra Malik and David Forsyth for many helpful comments.Additional details
- Eprint ID
- 98356
- DOI
- 10.1007/3-540-45054-8_2
- Resolver ID
- CaltechAUTHORS:20190829-131534540
- Center for Neuromorphic Systems Engineering, Caltech
- EEC-9402726
- NSF
- IIS-9457618
- NSF
- Alfred P. Sloan Foundation
- Created
-
2019-08-30Created from EPrint's datestamp field
- Updated
-
2021-11-16Created from EPrint's last_modified field
- Series Name
- Lecture Notes in Computer Science
- Series Volume or Issue Number
- 1842