Towards cognitive image fusion
Information Fusion
| Hi-index | 0.00 |
Performances evaluation method that can compare and analyze different fusion techniques is an essential part of image fusion techniques. In this paper we propose a performance assessment method for image fusion techniques based on accurate measurement of general relationship among a image set. Numerical verifications, using data constructed from four kinds of typical relations and multi-variable time series generated from a logistic function, are conducted to demonstrate the proposed concept of nonlinear correlation information entropy and its characteristics. Furthermore, the performances of two widely used image fusion techniques, i.e. wavelet transform based fusion and pyramid transform based fusion operating on typical hyperspectral image sets, are evaluated using the proposed method. The performances evaluation results agree with the classification accuracy in application.