TemplateTran

车道偏离识别的程序，采用的是动态规划算法，对弯道也有比较高的识别率(lane departure algorithm, which has good performance even for curve lane.)

提取SIFT特征，进行特征提取和匹配，包括特征点的定位，特征点描述子的生成，特征点的匹配，(extract SIFT feature，and feature matching)

多媒体图形图像正交变换语言是VC++,源码正交变换(Multimedia graphic image orthogonal transform language is VC++ source orthogonal transformation)

最小二乘图像影像匹配方法，一个很详细的源码例程，有过程有结果，希望对初学者有帮助。高斯解方程，以及最小二乘匹配，里面都很详细。(Squares image image matching method, a very detailed source code routines, the outcome of the process, I hope to help beginners. Gaussian solution of equations, and least squares matching, which is very detailed.)

使用光流法对运动目标进行估计，要使用opencv一起实现。效果还不错(Using optical flow method to estimate the moving target, to use opencv implemented together. Results were pretty good)

利用Artoolkit实现了虚拟现实的算法，VS2008下测试通过(Use Artoolkit algorithm to achieve a virtual reality, VS2008 under test)

中值滤波，取出奇数个数据进行排序，用排序后的中值取代要处理的数据即可(median filtering.rar)

基于DQ效应的JPEG图像真伪检测算法，通过检测图像DCT直方图的DQ效应计算图像的概率图，该算法快速、准确，能自动定位篡改区域(JPEG image detection algorithm based on the authenticity of DQ effect, calculated image by DQ effect detection probability map image DCT histogram, the algorithm is fast, accurate, and can automatically locate tampered area)

《医学图像编程技术》，周振环。一书的源码(the source code of the "medical picture programing")

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.)