A novel image fusion metric based on multi-scale analysis

Pixel-level image fusion has been investigated in various applications, and many algorithms have been proposed. However, the automatic performance evaluation of these algorithms is still a challenging issue. In this paper, we propose an image fusion metric from an edge information preservation perspective, which is according to the fact that edge information plays a crucial role in the human perception of image quality. We implement a multi-scale analysis and calculate the edge preservation value of the fused image scale-by-scale. In this way, the proposed method achieves an accurate edge preservation measure. Extensive experiments demonstrate that the proposed method is consistent with the subjective evaluations..and outperforms other recently developed blind evaluation metrics.