This document presents an approach for unsupervised scale-invariant object class recognition using a probabilistic model. The model represents objects as flexible constellations of parts with probabilistic representations for shape, appearance, scale, and occlusion. An entropy-based feature detector is used to select image regions and scales. A maximum likelihood algorithm estimates the parameters of the scale-invariant object model from unlabeled training images. The model demonstrates good recognition performance on datasets with geometric and non-geometric object classes.