ImageTool

本文是中值滤波的一些应用，个人觉得中值滤波比一些算子滤波效果要好得多(This article is median filtering applications, personal feel median filter is much better than some of the filtering effect of the operator)

这本是用VC++来实现图像处理的书藉,对于学习图像处理的来说是非常有用的.(This is VC++ to realize image processing books, for learning image processing is very useful.)

实现了三维超声PNN算法的GPU加速；实现GPU加速的CT圆轨道平板探测器FDK重建算法；提供对canny边缘检测算法的支持；提供交互式graph cut分割方法；实现OSTU分割算法；(Three dimensional ultrasound PNN algorithm GPU acceleration to achieve GPU accelerated CT reconstruction algorithm for circular orbits FDK flat panel detector provide support for canny edge detection algorithm provide interactive graph cut segmentation achieve OSTU segmentation )

人脸检测：可自动检测人脸，速度还可以吧！(Face Detection : can automatically detect faces and can also speed!)

本程序利用SIFT算法实现影像匹配的基础上，实现全景图的拼接，实用性很强，大家可以把拍摄的相邻的几张有重叠度的照片拼接成一张全景图。(The program uses SIFT image matching algorithm based on the realization of panorama stitching, very practical, we can put a few have taken the overlap of adjacent photos into a panoramic mosaic map.)

说明：  采用积分图算法的归一化互相关匹配，大大减少了计算时间。(Normalized cross correlation matching)

盒状滤波器，可以用来用来对图像进行滤波，对图像的预处理(Box-shaped filter can be used for image filtering, pre-processing of the image)

sar图像的基于R-D模型的几何纠正，主要是利用RD模型的数学公式进行相关的几何纠正(Geometric rectification based on RD model of SAR)

三维点云配准kd-tree搜索算法，用于特征点的搜索匹配(3 d point cloud registration kd- tree search algorithm, is used to search of feature point matching)

这是用C++实现图像立体匹配的一个完整的论文代码，主要特性是提出了一种全新的跨规模代价聚合方法，适合对于图像的立体匹配有一定基础的人学习(Cross-Scale Cost Aggregation for Stereo Matching)