中文摘要：

为了提高噪声图像的融合效果，基于剪切波变换和稀疏表示理论提出了一种对噪声图像的融合方法。基本思想主要包括4步：①对噪声图像进行剪切波分解，得到各个尺度下的剪切波系数；②利用稀疏表示理沦对低频子带的剪切波系数进行融合，而对高频子带的系数选用绝对值最大的原则进行融合；⑧对融合后的剪切波系数进行硬阈值处理；④利用剪切波逆变换得到最终的结果。实验结果表明所提方法是有效的。

英文摘要：

In order to further impoove noisy image fusion effect, a novel fusion method tor noise image based on shearlet transform and sparse representation is presented. The proposed scheme performs the four stages ： （1） Perform a shearlet transform decomposition of each source image and obtain their low-pass and high-pass coefficients; （2） Obtain the fused shearlet transform coefficients in the low-pass bands with a sparse representation based fusion approach while in the high-pass bands by fusing the largest absolution values ; （3） The hard thresholding is applied to the fusion shearlet transform coefficients. （4） The result image is obtained by the inverse shearlet transform. Experimental results show that the proposed algorithm for image fusion is very effective.