; 1; Dept. of Computation and Neural Systems; 2; Dept. of Electrical Engineering; California Institute of Technology; MC 136--93, Pasadena; 3; Universita di Padova
SVM HeaderParse 0.2
; CA 91125, U.S.A.; Italy
SVM HeaderParse 0.1
. 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. 1 Introduction and Related Work We are interested in the problem of recognizing members of object classes, where we define an object class as a collection of objects which share characteristic features or parts that are v...