evaluatefusion

自己编的nsct和pcnn结合的融合程序,简单易懂，pcnn采用的不是改进型的，传上来供大家参考，运算复杂，出结果很慢。(A fusion algorithm based on NSCT-PCNN.It is easy to understand,but the quantity of arithmetic is large, and it costs a long time.)

图像处理领域中用于处理LDR为HDR图像的程序，即从低动态范围的图像转成高动态范围的图像(The field of image processing procedures for handling LDR HDR images turn into a high dynamic range image from the low dynamic range image)

这个文件包里包含了几乎所有的聚类的工具箱，包含采用混合高斯模型的运动物体检测方面的源代码。(This document contains the bag almost all the clustering of the toolbox, including the use of Gaussian Mixture Model of Moving Objects for testing source code.)

说明：  线形骨架的综述类文献，着重强调定义属性和应用(Curve-skeleton properties, applications, and algorithms)

说明：  基于压缩感知理论的目标跟踪算法，实现对可视目标的稳健跟踪(Target tracking algorithm based on compressed sensing theory)

wpf各种统计图展示（直方图，饼图，折线图）

SPCA The SPCA algorithm for computing sparse principal components.

全局法图像垂直条纹去除程序。可以处理高光谱图像、RGB图像，注释详尽。对于倾斜的条纹噪声图像，需要西安进行旋转，再使用该程序去除。内涵循环低速版和无循环高速版，通过比较（处理高光谱数据），高速版的速度比低速版快上近20倍。(Global image vertical stripes removal procedures. Can process the hyperspectral image, RGB image, detailed notes. The stripe noise images of Xi an, need to rotate, then use the program to remove. Connotation of circular low version and loop free high speed version, by comparing (hyperspectral data processing), high speed rate nearly 20 times than the low-speed model.)

数字图像相关方法中的一种亚像素求解算法，通过此算法可以获得全场位移，继而得到全场形变。(A sub-pixel algorithm in digital image correlation method, which can obtain the full field displacement, and then get the full field deformation.)

三维激光点云配准是点云三维建模的关键问题之一。经典的 ICP 算法对点云初始位置要求较高且配准 效率较低，提出了一种改进的 ICP 点云配准算法。该算法首先利用主成分分析法实现点云的初始配准，获得较好 的点云初始位置，然后在经典 ICP 算法的基础上，采用 k － d tree 结构实现加速搜索，并利用方向向量夹角阈值去除 错误点对，提高算法的效率。实验表明，本算法流程在保证配准精度的前提下，显著提高了配准效率。 (Three-dimensional laser point cloud registration is one of the key three-dimensional point cloud model. High classical ICP algorithm to the initial position of the point cloud registration requirements and low efficiency, proposed an improved ICP point cloud registration algorithm. Firstly, the use of principal component analysis of the initial point cloud registration, get a better initial position of the point cloud, then the basis of classical ICP algorithm using k- d tree structure to achieve speed up the search, and using the direction vector angle the removal of the threshold point error and improve the efficiency of the algorithm. Experiments show that the algorithm processes to ensure the accuracy of registration under the premise, significantly improve the efficiency of registration.)