ColorImageProcessing

图像处理源程序，实现二值化变换，经一幅图像灰度化后，变成二值化图像，包括大津法、最大类间方差法、一般阈值法、及文本识别最有用的Niblack法(Image processing program and realized binarization transformation, after by a gray-scale image into binary image, including the Otsu method, Otsu method, the general threshold, and text to identify the most useful Niblack method)

椭圆拟合，输入中心坐标及椭圆长半轴和短半轴即可画出相应椭圆(ellipse fitting)

说明：  物体运动的跟踪，比如行人和车辆等物体的跟踪(Tracking the motion of an object, such as a pedestrian or vehicle)

主成分分析PCA源代码（C++，matlab）主成分分析PCA源代码（C++，matlab）(Principal Component Analysis PCA source code (C++, Matlab), principal component analysis PCA source code (C++, 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.)

基于opencv的MHT的多目标跟踪程序(Based on the MHT multi-target tracking program)

对视频进行基本的处理，例如载入视频，显示视频，控制播放(Basic video processing, such as loading the video, show video, control playback)

针对万工显螺旋显微镜视场图像特点，编写了Matlab 语言的图像处理算法用于万工显自动读数( The program which is developed by MATLAB language can be used for auto-reading of universal tools microscope measurement result)

摄影测量的一个开源代码，内部含有后方交会、前方交会、相对定向、立体量测、像点匹配等功能源代码。(An Photogrametry open source project, including intersection, relative oriention, stereo measure, image matching source code.)

根据RBM深度网络（Hinton，2006）进行MINST手写文字的分类器的训练，利用训练得到的权值制作了这个小程序，通过这个程序可以看出训练结果对数据集内的测试样本和训练样本都能进行很好的识别，但是对其他的手写字体识别就没有那么好了。(According to RBM depth network (Hinton, 2006) conducted MINST handwritten text classifier training, using the training to get the right value to produce this small program, this program can be seen through the results of the training data set and the training sample test samples are can be well identified, but on the other handwriting recognition is not so good.)