中文摘要：

提出一种基于显著性的多尺度图像融合模型.先利用轮廓波变换将输入图像分解成子图序列,然后计算每幅子图像的区域显著性,并选取显著性大的参数作为最终融合参数,最后通过反变换获得融合图像,图像的显著性通过谱冗余法获得.实验结果表明,该方法较传统方法融合效果更好.

英文摘要：

This paper presents a multi-scale saliency-based image fusion model.First,the source images were decomposed into sub-image sets by contourlet transform,then the saliency of each piece of sub-image was calculated and the coefficients were selected by maximizing saliency,and finally,the fused image was obtained by inversing contourlet transform.The saliency of the image was calculated by spectral residual theory.Experimental results show that the proposed model outperforms traditional models.