About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Publication
Computer Vision and Image Understanding
Paper
Bayesian approach to model matching with geometric hashing
Abstract
In geometric hashing methods, the hash function involves quantization of the values, which can result in the disgraceful degradation of the performance of the system in the presence of noise. Intuitively, it is better to replace the quantization of hash values by a method that gives less weight to a hash table entry. This paper shows how the intuitive notions can be translated into a well-founded Bayesian approach to object recognition and gives precise formulas for the optimal weight functions that should be used in hash space. These extensions allow the geometric hashing method to be viewed as a Bayesian maximum-likelihood framework. The validity of the approach is demonstrated by performing similarity-invariant object recognition. The results represent a complete object recognition system, since the feature extraction process is automated. © 1994 Academic Press. All rights reserved.