Bayesian learning of finite generalized inverted Dirichlet mixtures: Application to object classification and forgery detection

作者：

Highlights：

• A finite mixture model based on the generalized inverted Dirichlet distribution is proposed.

• An approach to learn the new proposed mixture model is developed.

• The proposed statistical framework is applied to object classification and forgery detection.

摘要

•A finite mixture model based on the generalized inverted Dirichlet distribution is proposed.•An approach to learn the new proposed mixture model is developed.•The proposed statistical framework is applied to object classification and forgery detection.

论文关键词：Finite mixtures,Generalized inverted Dirichlet,Bayesian inference,BIC,Model selection,Gibbs sampling,Object classification,Forgery detection

论文评审过程：Available online 5 October 2013.

论文官网地址：https://doi.org/10.1016/j.eswa.2013.09.030