|
Abstract : |
This publication can be retrieved by anonymous ftp topublications.ai.mit.edu. We have developed a new Bayesian framework for visual object recognition which is based on the insightthat images of objects can be modeled as a conjunction of local features. This framework can be used to both derive an object recognition algorithm and an algorithm for learning the features themselves. The overall approach, called complex feature recognitionorCFR,isunique for several reasons: it is broadly applicable to a wide range of object types,itmakes constructing object models easy, itis capable of identifying either the class or the identity of an object, and it is computationally e cient { requiring time proportional to the size of the image. Instead of a single simple feature such as an edge, CFR uses a large set of complex features that are learned from experience with model objects. The responseofasingle complex feature contains much more class information than does a single edge. This signi cantly reduces the number of possible correspondences between themodel andtheimage. In addition, CFR takes advantage of a type of image processing called oriented energy. Oriented energy is used to e ciently pre-process the image to eliminate some ofthe di culties associated with changes in lighting and pose., |
