Exploiting foveation in user-centred image fusion

The selection of image fusion techniques has always been a compromise between effectiveness and efficiency. In this paper, foveation (using log-polar transformation) is introduced to satisfy the real-time requirement of applications where the fused image is eventually presented to a human to interpret. Log-polar transformation achieves a data reduction without a subsequent loss in perceptual information. Thus, it can be used to reduce the execution time of any existing image fusion technique without modifying the technique itself. In this paper, the log-polar transformation is integrated with three widely-used image fusion techniques: image averaging, the Laplacian pyramid, and the Discrete Wavelet Transform. Then, the proposed fusion process is objectively evaluated using a set of established metrics; they are Mutual Information (MI), Xydas & Petrovic (Q^AB/F), and Piella & Heijmans (Q_w).