|
Abstract:
We present a method to learn object class models from unlabeled and unsegmented cluttered scenes for the purpose of visual object recognition. Objects are represented as flexible constellations of rigid parts (features). The variability within a class is represented by a joint probability density function on the shape of the constellation and the output of part detectors. In a first stage, our proposed learning 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 good classification results on a variety of data sets, including human faces, cars and cartoons figures.