A METHOD TO SPEED-UP THE BAYES CLASSIFIER

A method is proposed to combine the branch-and-bound (BAB) algorithm w ith the Bayes classifier. Given the input feature vector from an unkno wn class, the BAB algorithm is efficient for searching for the nearest neighbor (NN) from among the set of reference vectors. Hence BAB is o ften used to implement the k-NN classifier. However, it is known that the k-NN classifier is not as accurate as the Bayes classifier, which has the highest recognition rate provided the class statistics are kno wn. Hence it is attractive to combine the BAB algorithm with the Bayes classifier so that the resulting system will inherit improved speed a nd accuracy. In this article, an extension of the BAB algorithm is pro posed so that it can be used to implement the Bayes classifier. Gaussi an statistics are assumed in modeling the class conditional densities. A system for recognizing printed Chinese characters is implemented, a nd satisfactory results are obtained. (C) 1998 Elsevier Science Ltd. A ll rights reserved.