HU不变矩

将空间点的大地坐标投影到椭球面上，进行分带，计算坐标，最后输出高斯投影结果(gauss projection)

Visual Image Quality Assessment Technique using FSIM

说明：  人脸检测算法对Haar特征推进，我们已经改善了大幅利用作为弱分类器的阈值中的累积概率分布点。(A face detector based on VJ algorithm (Boosting on HAAR features). We have improved the performance drastically by using mid cumulative probability distribution point as threshold for weak classifiers. )

document about computer vision - image processing

该代码实现了基于graph cut的图象分割算法,具体代码是用c++编写的,但提供了matlab接口,分割效果较好.(The code based on the graph cut image segmentation algorithm, the specific code is used c++ Prepared, but provides a matlab interface, better segmentation.)

它不仅具有Gabor变换的六个方向选择性,而且有更小的冗余度(It is not only selective Gabor Transform six directions, but also smaller redundancy )

说明：  ORB-SLAM 基本延续了 PTAM 的算法框架,但对框架中的大部分组件都做了改进, 归纳起来主要有 4 点: ORB-SLAM 选用了 ORB 特征, 基于 ORB 描述量的特征匹配和重定位, 都比 PTAM 具有更好的视角不变性。此外, 新增三维点的特征匹配效率更高, 因此能更及时地扩展场景。扩展场景及时与否决定了后续帧是否能稳定跟踪。ORBSLAM 加入了循环回路的检测和闭合机制, 以消除误差累积。系统采用与重定位相同的方法来检测回路(匹配回路两侧关键帧上的公共点), 通过方位图 (Pose Graph) 优化来闭合回路。PTAM 需要用户指定 2 帧来初始化系统, 2 帧间既要有足够的公共点, 又要有足够的平移量. 平移运动为这些公共点提供视差 (Parallax) , 只有足够的视差才能三角化出精确的三维位置。ORB-SLAM 通过检测视差来自动选择初始化的 2 帧。PTAM 扩展场景时也要求新加入的关键帧提供足够的视差, 导致场景往往难以扩展. ORB-SLAM 采用一种更鲁棒的关键帧和三维点的选择机制——先用宽松的判断条件尽可能及时地加入新的关键帧和三维点, 以保证后续帧的鲁棒跟踪; 再用严格的判断条件删除冗余的关键帧和不稳定的三维点，以保证 BA 的效率和精度。(Orb-slam basically continues the algorithm framework of PTAM, but most of the components in the framework have been improved, which mainly includes four points:)

Colored-Noise Kalman Filter for Vibration Mitigation of Position Attitude Estimation Systems

2个matlab的源代码：身份证号码识别源代码与matlab截取图像批处理源代码(ID number identification graduation design reply demo program source code and MATLAB intercept image batch source code)

MATLAB编写的角点检测程序，用于对目标的检测和稳定的跟踪。很适合对于运动目标的精确跟踪。(Corner detection procedures written in MATLAB for target detection and tracking. Very suitable for the accurate tracking of moving targets.)