图像处理

图像融合，加权平均值，PCA方法，拉普拉斯方法，源程序(Image fusion, weighted average, PCA method, Laplace method, source)

使用tensorflow框架搭建神经网络，从单目图像中估计深度值(Using tensorflow framework to build a neural network to estimate depth from monocular images)

利用NSCT对脑CT图像增强的例子 ，代码可编辑，本例为适用于灰度图像(Using NSCT for brain CT image enhancement example, the code can be edited. This example applies to grayscale images.)

利用K均值聚类的方法实现人体的检测，混合高斯模型建立背景并实时更新(The use of K-means clustering method to achieve the human body detection, Gaussian mixture model to establish the background and real-time updates)

说明：  视频动态报警开发,动态处理视频轨迹(Dynamic development of video alarm, dynamic video trajectory treatment)

亚像素边缘检测，基于zernike 灰度矩，实现精度可达0.05个pixel(sub-pixel edge detect)

实现了迭代盲反卷积的图像去模糊，自己写的代码，没有调用matlab已有函数(Iterative blind deconvolution of images blurred, write your own code, without calling matlab existing function)

采用ESIHE算法增强图像对比度，适用于夜间道路拍摄的图像(ESIHE algorithm is used to enhance image contrast, which is suitable for night road images.)

说明：  可以对光谱数据进行预处理，除了偏最小二乘法之外，也有一些其他方法(Besides the partial least square method, there are also some other methods)

说明：  文献 "Deblurring Text Images via L0-Regularized Intensity and Gradient Prior" 的参考代码 用Lp正则化方法做盲复原的代码 demo_text_deblurring 是主函数(refer to "Deblurring Text Images via L0-Regularized Intensity and Gradient Prior" main function: demo_text_deblurring)