MNF

基于最小相位雷克子波反褶积的matlab程序，有脉冲反褶积，最小平方反褶积和预测反褶积(Matlab program based on the the Leike Zi wave pulse deconvolution)

利用全卷积神经网络，实现图像的语义分割，基于tensorflow的keras可以直接运行(Using the full convolutional neural network to achieve semantic segmentation of images, keras based on tensorflow can be run directly)

图像处理程序，基于K均值聚类的图像分割——灰度图像，基于中位数算法的运动目标检测(Image processing program, image segmentation based on k-means clustering -- gray image, moving target detection based on median algorithm)

将语音文件.wav转化为FPGA所需的.mif文件(The voice file. Wav into the FPGA required. Mif file)

利用非线性结构张量处理一些图形问题，能够有效的解决和优化现成的处理方法(In this article, we introduce nonlinear versions of the popular structure tensor, also known as second moment matrix. These nonlinear structure tensors replace the Gaussian smoothing of the classical structure tensor by discontinuity-preserving nonlinear diffusions)

混沌系统中得logistic映射分岔图源程序，可以看到分岔效果，具有混沌特性(Chaotic systems have in the logistic map bifurcation diagram source, you can see the bifurcation effect the character of chaos)

点云的配准实验s-icp算法 实现两个点云数据的对准(A scale stretch method based on ICP for 3D data registration)

二维窗口函数，包含汉宁窗，布莱克曼窗，契比雪夫窗等(it creates a 2 dimentional window for a sample image)

收集的一些关于阴影去除的论文，对于做阴影去除的学者来说有用，至少可以节省论文的查阅时间(Collected a number of papers on the shadow removal, useful for scholars to do shadow removal, at least you can save paper inspection time)

一种基于半监督的svm的图像分类方法。该方法通过聚类核的方法利用无标记样本局部正则化训练核的表达式。这种方法通过图像直接学习一个自适应的核。该程序仿真的是文章：Semi-supervised Remote Sensing Image Classification with Cluster Kernels。大家可以参考下。(A semi-supervised SVM is presented for the classification of remote sensing images. The method exploits the wealth of unlabeled samples for regularizing the training kernel representation locally by means of cluster kernels. The method learns a suitable kernel directly from the image, and thus avoids assuming a priori signal relations by using a predefined kernel structure. Good results are obtained in image classification examples when few labeled samples are available. The method scales almost linearly with the number of unlabeled samples and provides out-of-sample predictionsds)