criminisi

说明：  本程序基于MFC，VS2010编写，是一款可以打开任意视频格式的播放器，具有打开视频（任意格式，avi，mp4, rmvb,asf,avi,mpeg等）， 具有快进，快退，暂停，播放，上一帧，下一帧，截图，拍照，快速播放慢速播放功能，同时提供图像处理功能（视频图像增强，视频图像去雾，海上目标检测功能）。(This program is based on MFC, VS2010. It is a player that can open any video format. It has open video (arbitrary format, avi, mp4, rmvb, asf, avi, mpeg, etc.). It has the functions of fast forward, fast backward, pause, playback, last frame, next frame, screenshot, photograph, fast playback and slow playback. It also provides image processing functions (video image enhancement, video image defogging, sea target detection).)

用Kalman滤波方法对单个目标航迹进行预测，并借助于Matlab仿真工具，对实验的效果进行评估。 (Target tracking application context radar data processing, radar in the search to the goals and objectives of the record location data of the measured target position data (called a point of the track) processing, automatic formation flight path, and the target in the next The moment the position prediction. This article briefly discusses the Kalman filtering method to predict a single target track, and by means of Matlab simulation tools to assess the effect of the experimental.)

这是一个口形特征点粗定位程序，首先对唇部图象进行边缘检测，然后利用几何特征进行定位。(This is a lip feature points coarse positioning procedures, first of all on the lip image edge detection, and then positioning the use of geometrical features.)

主要用来对矩阵进行奇异值分解，与MATLAB有同样的效果(It is mainly used to perform singular value decomposition on matrices and has the same effect as MATLAB.)

医学图像配准，医学图像2D_3D配准，基于vc++开发。(The registration of pre-operative volumetric datasets to intra-operative two-dimensional images provides an im- provedway of verifying patient positionandmedical instru- ment location. In applications from orthopedics to neuro- surgery, it has a great value in maintaining up-to-date in- formation about changes due to intervention. We propose a mutual information-based registration algorithm which es- tablishes the proper alignment via a stochastic gradient as- centstrategy. Ourmaincontributionliesinestimatingprob- ability density measures of image intensities with a sparse histogrammingmethodwhichcouldlead to potentialspeed- up over existing registration procedures and deriving the gradient estimates required by the maximization procedure. Experimental results are presented on fluoroscopy and CT datasets of a real skull, and on a CT-derived dataset of a real skull, a plastic skull and a plastic lumbar spine seg- ment.)

关于图像处理的一些基本操作，空间、频域图像增强，形态学处理，边缘检测等(About some of the basic image processing operations, space, frequency domain image enhancement, morphological processing, edge detection, etc.)

Retinex算法对较暗区域的图像处 理有明显效果,改进的Retinex方法则是基于经典Retinex,对具有较高亮度的遥感图像通过图像变 换方法达到去除模糊的目的。 (Retinex algorithm for image processing on the dark region was effective to improve the Retinex method is based on the classic Retinex, on remote sensing images with high brightness achieved by an image transformation method aims to remove ambiguity.)

灰度图像的属性计算：利用bwlabel和regionprops函数对度量二值图像中目标对象的属性。(Attribute gray image: Using bwlabel and regionprops function measure binary image of the target object attributes.)

基于hessian矩阵的眼底图像血管增强滤波(Vessel Enhanced Filtering of Eyeground Images Based on Hessian Matrix)

GLCM feature 1 for image