partical-filter

说明：  针对一维最大类间方差算法(1-Otsu)抗噪性能较低、二维最大类间方差算法(2-Otsu)计算复杂度高、实时性差的问题,提出一种基于改进的萤火虫算法(FA)优化二维Otsu图像分割算法(FA-2-Otsu).(In order to solve the problems of low anti noise performance of 1-otsu, high computational complexity and poor real-time performance of 2-otsu, an improved firefly algorithm (FA) is proposed to optimize the 2-otsu image segmentation algorithm (fa-2-otsu).)

各种图像处理技术举例。其中原代码可以直接使用，非常不错。(various image processing technology, for example. The original code which can be used directly, very good.)

采用最大后验（MAP）算法来实现图像的超分辨率算法(The super-resolution algorithm using the maximum a posteriori (MAP) algorithm to achieve image)

svd图像压缩，程序中使用了三种方法的SVD，包括直接svd，分块svd和小波svd(3 svd comprecessions.)

c++实现的sift，可以分步观看实现效果(c++ implementation of the sift, you can watch step by step to achieve results)

相机标定源代码，包含张正友，Tsai等基于matlab的相机标定方法。(Camera calibration source code, including Zhang Zhengyou, Tsai camera calibration method based on Matlab.)

用wpf实现一个简单的手滑切换图片的实例

三维点云包围盒精简算法，内包含点云数据与处理结果，直观可用，效果良好。(Three dimensional point cloud bounding box reduction algorithm, which contains point cloud data and processing results, is intuitive and available, and the effect is good.)

读取一幅图像，对其进行DCT高通、低通滤波，输出处理后图像(Read an image, do the DCT high-pass, low-pass filtering, output processed image .)

根据Dalal提出的HOG特征算法编写，代码简单，注释清楚，根据所处理图像的名称路径修改后可生成36*105的特征向量。(The algorithm proposed by Dalal HOG feature writing code simple, clear annotation feature vector can generate 36* 105, modified according to the name of the image processing path.)