在多聚焦图像融合算法中，针对多分辨率系数融合法无法提取源图像清晰像素点和分块法存在的块效应的现象，从多聚焦图像清晰像素点和人眼视觉对比度的特征出发，利用平稳小波变换(SWT)的非下采样性和平移不变性，定义基于SWT的图像像素点区域对比度作为提取像素点的依据，在研究区域对比度邻域大小对像素点提取影响的基础上，设定适合的阈值建立提取模板，对多聚焦源图像中清楚区域的像素点进行提取，并对小部分未能提取的像素位置采用基于局部能量策略进行融合。仿真实验结果表明，新算法既有效地提取源图像的清晰像素点，又改善了块效应现象，融合效果有了很大提升。

In the area of multi-focus images fusion, the multi-resolution coefficients fusion algorithms can not extract the clear pixels from source images, and the block extract algorithms always cause block effects. Therefore, the authors define the image pixels’ regional contrast based on stationary wavelet transform (SWT), which is non-subsampled and translation invariant, considering the characteristics of the clear pixels in multi-focus images and the contrast features of human visual system. On the basis of studying how different neighborhood sizes of regional contrast can affect the correctness of extracted pixels, a proper threshold is set to build extraction templates, which are used to extract pixels in the clear region in source images. Then, the method of image fusion based on local energy mechanism is applied to those un-extracted pixels. The experimental results illustrate the novel algorithm in the paper can not only effectively extract the clear pixels from source images, but also reduce the block effects greatly, and the quality of the fused image is improved sharply.