Shared chain mutual information measure for image fusion

Image fusion is becoming one of the hottest techniques in image processing. The paper proposes a shared chain mutual information concept to quantitatively and objectively evaluate the performances of difference image fusion techniques. Furthermore, the performances of two widely used image fusion techniques, i.e. wavelet transform based fusion and pyramid transform based fusion operating on a typical hyperspectral image set, are evaluated using the proposed method. The performances evaluation results agree with the comparison results of classification accuracy in real application, which further prove the correctness and effectiveness of the proposed measure.