We present a pattern recognizer to classify a variety of objects and their pose on a table from real world images. Learning of weights in a linear discriminant is based on estimat...
We introduce a novel set of features for robust object recognition. Each element of this set is a complex feature obtained by combining position- and scale-tolerant edgedetectors ...
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 constel...
Humans have used sketching to depict our visual world since prehistoric times. Even today, sketching is possibly the only rendering technique readily available to all humans. This...
Abstract. An important task in object recognition is to enable algorithms to categorize objects under arbitrary poses in a cluttered 3D world. A recent paper by Savarese & Fei-...