This lecture summarizes the material in a tutorial we gave at AAAI2008 [Grauman and Leibe,
2008]1. Our goal is to overview the types of methods that figure most prominently in object
recognition research today, in order to give a survey of the concepts, algorithms, and representations
that one might use to build a visual recognition system. Recognition is a rather broad and quickly
moving field, and so we limit our scope to methods that are already used fairly frequently in the
literature. As needed, we point the reader to outside references for more details on certain topics.
We assume that the reader has basic familiarity with machine learning algorithms for supervised
classification and some background in low-level image processing.
The visual recognition problem is central to computer vision research. From robotics to information retrieval, many desired applications demand the ability to identify and localize categories, places, and objects. This tutorial overviews computer vision algorithms for visual object recognition and image classification. We introduce primary representations and learning approaches, with an emphasis on recent advances in the field. The target audience consists of researchers or students working in AI, robotics, or vision who would like to understand what methods and representations are available for these problems. This lecture summarizes what is and isn't possible to do reliably today, and overviews key concepts that could be employed in systems requiring visual categorization.
Table of Contents: Introduction / Overview: Recognition of Specific Objects / Local Features: Detection and Description / Matching Local Features / Geometric Verification of Matched Features / Example Systems: Specific-Object Recognition / Overview: Recognition of Generic Object Categories / Representations for Object Categories / Generic Object Detection: Finding and Scoring Candidates / Learning Generic Object Category Models / Example Systems: Generic Object Recognition / Other Considerations and Current Challenges / Conclusions