danyuan

针对可见光与红外图像的特点和难点，提出了可见光与红外图像配准与融合中的关键技术，即: 使用新型的基于一维最大类间方差和最大连通性测量的图像分割方法对源图像进行分割来更好地实行图像粗 配准 使用新型的特征点提取方法，特征点的匹配及误匹配的消除来更好地实行图像精配准 采用新型的基 于区域的树状小波活性测度计算来实现树状小波图像融合 利用自生成神经网络来实现模栩图像融合. (For visible light and infrared images of the characteristics and difficulties, a visual and infrared image registration and integration of key technologies, namely: the use of new one-dimensional based on the largest variance between-class connectivity and the largest measuring method of image segmentation source image segmentation to better implementation of coarse image registration the use of a new type of feature point extraction method, feature points of the match and the elimination of false matches to better the implementation of image fine registration the use of new tree-based wavelet calculated to measure the achievement of the activity tree wavelet image fusion the use of self-generating neural network to achieve image fusion Xu mode.)

graphcut的最新改进，在网格上应用graphcut，作者将其称为gridCut,此压缩包内含文章与源代码，出自CVPR2012,关注计算机视觉的同学可以详细参考，代码已调试通过(the new advance of graphcut, named gridCut, derived from CVPR 2012, useful to guys on ComputerVision.The code is runnable.)

说明：  利用GMS对特征点匹配进行约束，降低误匹配率，代码包含python版本，C++版本，matlab版本。(GMS is used to constrain the matching of feature points to reduce the error matching rate. The code includes Python version, C + + version and Matlab version.)

利用欧式度量聚类真实数据集和实际数据集用于对各类数据分类 (European metric clustering real data sets and real data sets for various types of data classification)

用主成分分析来降维，用Kmeans方法聚类；应用于变化检测中(Principal component analysis is used to reduce dimension with k-means algorithm is used to cluster; change detection)

二值化处理图像，自动拟合椭圆并得到长短轴的大小。(Automatically fit the ellipse and get the size of the long and short axes)

这是关于农业方面的遥感SAR图像数据，做SAR处理的可以下载使用(This is the SAR remote sensing image data on agriculture, do SAR processing can download)

Multi-Scale Structural Similarity Index (MS-SSIM). Download here. Please cite the following paper in any published work if you use this software. Z. Wang, E. P. Simoncelli and A. C. Bovik, "Multi-scale structural similarity for image quality assessment," IEEE Asilomar Conference Signals, Systems and Computers, Nov. 2003.

说明：  按照最邻近原则把待分类样本点分到各个簇。然后按平均法重新计算各个簇的质心，从而确定新的簇心。一直迭代，直到簇心的移动距离小于某个给定的值。(According to the nearest neighbor principle, the sample points to be classified are divided into clusters. Then the centroid of each cluster is recalculated according to the average method to determine the new cluster center. Iterate until the moving distance of the cluster center is less than a given value)

Image Matching Fundamentals Method Document PDF Files Slide2