01

基于粒子滤波与改进水平集的人手跟踪论文，论文中详细介绍了手势分割的实现算法(Based on particle filter and improve the level set of hand tracking paper, paper introduces the realization of gesture segmentation algorithm)

说明：  实现目标检测的代码，有例程视频，可以运行(Achieve target detection code, there are routine video, you can run)

机器视觉之模糊图像复原，实现inverse Filter, Wiener Filter, Lucy-richardson 算法，里面包括PPT，代码和报告。非常有价值，值得参考！ (Machine vision blurred image restoration, achieve The inverse Filter, Wiener Filter, Lucy-richardson algorithm, which includes the PPT, the code and report. Very valuable and worth considering!)

利用形态学，霍夫（Hough）变换，实现畸变QR码的4个角点的定位。(To correct the distortion of the QR code,use morphology operation, Hough transform, to locat the positioning of the four corner points)

说明：  小波分析增强滤波。小波变换的原理类似傅里叶变换，只是把三角函数基换成了小波基。与傅里叶变换不同，小波变换有两个变量：scale和translation。scale控制小波函数的收缩，其导数即为频率，translation控制小标函数的平移，平移量对应时间。通过信号的伸缩平移，可以得到某种重合情况，这样积分也会得到一个极大值，不同的是，得到频率成分的同时，还可以知道该频率的时间位置。(Wavelet analysis enhances filtering.The wavelet transform works like the Fourier transform, except that the trigonometric basis is replaced by a wavelet basis. Unlike the Fourier transform, the wavelet transform has two variables: scale and Translation. Scale controls the contraction of the wavelet function, its derivative is frequency, translation controls the translation of the small scale function, and the translation corresponds to the time. By stretching and shifting the signal, you can get some kind of coincidence, so that the integral will also get a maximum, but the difference is that when you get the frequency component, you can also know the time position of that frequency.)

图形图像处理中的平滑处理，可以实现部分的功能，但是还可以继续完善(Graphic image processing smoothing, can achieve some of the functions, but can also continue to improve)

凸一维总变差去噪与非凸正则化，内有文献参考。值得学习(One-dimensional convex total variation denoising non-convex regularization, the literature reference. Worth learning)

二维图像的处理，包括加入高斯噪声，椒盐噪声，滤波处理。(Two-dimensional image processing, including Gaussian noise, impulse noise, filtering.)

Graph cut with matlab. It is very powerful

sift匹配与识别演示程序 运行face.m文件，载入图片后可提取sift特征点(sift demonstration.rar. run face.m)