Sun Jianguo, Han Qilong, Kou Liang, Zhang Liguo, Zhang Kejia, Jin Zilong
J Opt Soc Am A Opt Image Sci Vis. 2018 Mar 1;35(3):480-490. doi: 10.1364/JOSAA.35.000480.
In this paper, we propose a method named region mosaicking on Laplacian pyramids (RMLP) to fuse multi-focus images that are captured by microscope. First, we apply the sum-modified Laplacian to measure the focus of multi-focus images. Then the density-based region growing algorithm is utilized to segment the focused region mask of each image. Finally, the mask is decomposed into a mask pyramid to supervise region mosaicking on a Laplacian pyramid. The region level pyramid keeps more original information than the pixel level. The experiment results show that RMLP has the best performance in quantitative comparison with other methods. In addition, RMLP is insensitive to noise and can reduce the color distortion of the fused images on two datasets.
在本文中，我们提出了一种名为拉普拉斯金字塔区域拼接（RMLP）的方法，用于融合显微镜拍摄的多聚焦图像。首先，我们应用求和修正拉普拉斯算子来测量多聚焦图像的聚焦程度。然后，利用基于密度的区域生长算法对每个图像的聚焦区域掩码进行分割。最后，将掩码分解为掩码金字塔，以监督拉普拉斯金字塔上的区域拼接。区域级金字塔比像素级保留了更多的原始信息。实验结果表明，与其他方法相比，RMLP在定量比较中具有最佳性能。此外，RMLP对噪声不敏感，并且可以减少两个数据集上融合图像的颜色失真。
