A Method for Large-scale Microscope Images Mosaicing Based on Minimum Routing Cost Spanning Tree
基于最小路由代价树的大规模显微图像拼接方法

In order to build high quality panoramic image, the conception of a mosaicing graph and three rules for high quality panoramic image are presented in the paper.An image registration algorithm based on blocking-spatial clustering is used to calculate the registration position and to evaluate the registration quality of pairs of images to obtain weight of edge in mosaicing graph.Then a method of images mosaicing based on minimum routing cost spanning tree is proposed to calculate global optimum position of every image by constructing the minimum routing cost spanning tree of the mosaicing graph and to create the panoramic image.In the case study, the proposed method demonstrates high quality.