The image classification method based on multivariate Bernoulli naive Bayes with Dirichlet prior and hyper parameter optimization

This paper presents a novelty classification method based on multivariate Bernoulli naive Bayes with Dirichlet prior and hyper parameter optimization. We test the proposed method on 15-Scenes and Msrc-v2 data set by comparing with basic multivariate Bernoulli naive Bayes and SVM (Support Vector Machine). The experiments show that our method has advantages both in running time and classification precision.