Object Class Recognition by Unsupervised Scale-Invariant Learning

We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of the object: shape, appearance, occlusion and relative scale. An entropy-based feature detector is used to select regions and their scale within the image. In learning the parameters of the scale-invariant object model are estimated. This is done using expectation-maximization in a maximum-likelihood setting. In recognition, this model is used in a Bayesian manner to classify images. The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).

• Type: Conference
• Year: 2003
• Where: CVPR
• Authors: Robert Fergus, Pietro Perona, Andrew Zisserman
• Keywords: Computer Vision, CVPR 2003, Flexible Objects, Object Class Models, Scale Invariant Manner, Scale-invariant Object Model, Unsegmented Cluttered Scenes