Maximum likelihood based framework for second-level adaptive prediction

A study is presented of a maximum likelihood based framework for second-level adaptive prediction which is formed from a group of predictors. It is a natural extension to first-level prediction which is formed directly from a group of pixels. The proposed framework offers a greater degree of freedom for adaptation and tackles the problem of model uncertainty that is inherent in first-level prediction methods. It is shown that the proposed methods of taking the weighted average and the weighted median of a group of predictions are alternative and competitive adaptive image prediction methods. The authors also present an extensive discussion on some related research works and theories, generalisation of proposed methods and some possible ways for further improvement.