Unsupervised Learning of Models for Recognition
We present a method to learn object class models for the purpose of object recognition. We focus on a particular type of model where objects are represented as constellations of rigid features (parts). The variability within a class is represented by a joint probability density function (pdf) on the shape of the constellation and the output of the feature detectors. The pdf may be estimated from training data once a model structure (type and number of features) has been specified. The method automatically identifies distinctive features in the training set and learns the statistical shape model. It is assmed that a set of generic feature detectors is available for the learning algorithm to choose from. The entire set of model parameters is learned using expectation maximization.
Download: pdf
Text Reference
Markus Weber, Max Welling, and Pietro Perona. Unsupervised learning of models for recognition. In JNSC. 1999.BibTeX Reference
@inproceedings{WeberWP_JNSC_1999,AUTHOR = "Weber, Markus and Welling, Max and Perona, Pietro",
TAG = "object_recognition",
TITLE = "Unsupervised Learning of Models for Recognition",
BOOKTITLE = "JNSC",
YEAR = "1999",
BIBSOURCE = "http://www.visionbib.com/bibliography/match595.html#TT42151"
}