Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the di...
Choosing good features to represent objects can be crucial to the success of supervised machine learning algorithms. Good high-level features are those that concentrate informatio...
A number of recent systems for unsupervised featurebased learning of object models take advantage of cooccurrence: broadly, they search for clusters of discriminative features tha...
Abstract. In this paper, we present novel image-derived, invariant features that accurately capture both the geometric and color properties of an imaged object. These features can ...