HoughMFC

三维最大Renyi熵的灰度图像阈值分割算法(Maximum Renyi entropy of three-dimensional gray-scale image segmentation algorithm)

这个函数分配一个数据缓冲区与多个颜色指定系统上的乐队。这种类型的缓冲区允许表示彩色图像(例如,RGB)。 这个函数为每个指定分配缓冲区,一个二维表面颜色乐队。您可以使用MbufAlloc1d()和MbufAlloc2d()来创建单独的乐队一或二维 数据缓冲区,分别。 分配一个缓冲区后,我们建议您检查是否操作成功,使用MappGetError(),或通过验证,不是M_NULL返回的缓冲区的标识符。(This function allocates a data buffer with multiple color bands on the specified system. This type of buffer allows for the representation of color images (for example, RGB). This function allocates buffers that have a two-dimensional surface for each specified color band. You can use MbufAlloc1d() and MbufAlloc2d() to create single band one- or two-dimensional data buffers, respectively. After allocating a buffer, we recommend that you check if the operation was successful, using MappGetError(), or by verifying that the buffer identifier returned is not M_NULL.)

opencv SIFT源码详细分析，代码能够准确实现(opencv SIFT detailed analysis of the source code can achieve accurate)

Implementations of image processing algorithms(This project can be built by Visual Studio 2012. Project description file included. Currently it is for Windows only.)

采集RGB-D深度图像生成点云矩阵，属于RGB-D SLAM的前端处理过程(Collecting depth image to generate point cloud)

讨论了OpenCV(Open Source Computer Vision Library)相对于现有的计算机视觉软件包所具有的优势，描述了OpenCV的 环境配置、数据定义、图像元素访问方式。OpenCV成为一种源码开放、包含丰富的高级数学计算函数、图像处理函数和计算机视觉 函数、不断更新和平台无关性的计算机视觉软件包。(Discussed the OpenCV (Open Source Computer Vision Library) relative to the existing computer vision, the advantages of packages, description of OpenCV environment configuration, data definition, the image element access mode. OpenCV become an open-source, contains a wealth of advanced mathematical calculations, functions, image processing functions, and computer vision functions, continuously updated, and platform-independent package of computer vision.)

刚体配准方法中，通常使用互信息函数作为相似性测度，此类提供计算的封装。(rigid registration method, which is commonly used as a mutual information function similar measure, the provision of such calculation package.)

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)

运动目标的给总与识别，可以实时显示目标的运动轨迹，支持高速相机实时处理视频数据，并可以获得运动目标的轮廓矩等信息(Moving target to the total and the identification of moving targets in real-time display track, real-time processing to support high-speed video camera and moving target access to information such as contour moments)

一种快速图像阈值分割法，不是otsu或迭代法，Wellner 1993快速自适应的图像二值化方法，有具体使用方法，很详细(A fast image thresholding segmentation method, not otsu or iterative methods, Wellner 1993 fast adaptive image binarization method)