立体视觉Gaussian Super-pixel Based Fast Image Segmentation Using Graph Cuts.-Gaussian Super-pixel Based Fast Image Segmentation Using Graph Cuts.

利用互信息，进行基于互信息的图像超分频重建-A Mutual Information Based Sub-Pixel Registration Method for Image Super Resolution

本文提出的超像素渐进合并算法应用了图论的基本框架：一幅图像被映 射成一个加权的无向图，其中超像素被当作图中的顶点，而相邻超像素之间通过边 相连，由超像素间的相似度计算出相应边的权值，通过排序每次合并权值最小的两 个超像素。-Shot into a weighted undirected graph, including super pixels as the vertices in the graph, and the adjacent pixels by boundary betw

使用matlab编写的获取SLIC超像素方法分割的结果图的每个块的Lab各个通道的均值和方差值，为后续算法提供数据。(The mean and variance of each Lab channel in each block of SLIC super-pixel segmentation result graph are obtained by matlab, which provides data for subsequent algorithms.)