dct-svd

基于SUFT的特征提取与匹配，内涵详细的文档说明，很好的实现了特征提取与匹配，该方法较基本的SIFT有很大的提高(Extraction and matching of features based on SUFT, detailed content of the documentation, very good realization of the feature extraction and matching, SIFT the method is basic is greatly improved)

说明：  Matlab代码文字识别：包括图像分割,粘连字符切分,文字识别(Using MATLAB to realize the code of recovering scene view distance map (depth map) from binocular map)

click energie of image , we can use it to calculate markov field ... and other

同态滤波增强暗部细节，通过分解为照射分量和反射分量处理图片(Homomorphic filtering enhances the details of the dark portion by decomposing the image as an irradiated component and a reflection component)

Graph Cuts是一个图像分割方法，具有交互式分割，分割效果很好。(Graph Cuts is an image segmentation method, with interactive segmentation, segmentation works well.)

一种二维Otsu快速算法的Matlab实现，该算法的原文参见《二维直方图区域斜分阈值分割及快速递推算法》，该文已附在内。(A two-dimensional Otsu fast algorithm Matlab realize that the original algorithm see " Two-dimensional histogram oblique segmentation area and fast recursive algorithm" , the paper has been attached into account.)

对视频中的几帧进行移动目标检测，着重标记出移动目标。(Moving targets are detected for several frames in the video, with emphasis on the moving target.)

立体匹配，包括计算基本矩阵，极线校正，和SSD计算匹配点(Matching, including the calculation of fundamental matrix, epipolar correction, and SSD calculation of matching points)

用MATLAN实现了FLL（锁频环）的热噪声误差、动态应力误差、总的跟踪误差与带宽、预检积分时间等的关系图(MATLAN achieve FLL (frequency-locked loop) thermal noise error and dynamic stress error, the total tracking error and bandwidth, preflight integration time diagram)

说明：  matlab开发的粒子滤波目标跟踪程序，跟踪目标良好。(Matlab development of particle filtering procedures。)