demo

在图像边缘点上计算边缘法向量, Compute the norm vector at the boundary(compute the norm vector at the boundary)

浏览图片的缩略图时，点击某张缩略图，被点击的缩略图会在当前视图放大并且全屏显示，背景用黑色透明视图遮挡。再次点击图片，将回到缩略图浏览状态(Media Focus Manager)

说明：  UNet最早发表在2015的MICCAI上，短短3年，引用量目前已经达到了4070，足以见得其影响力。而后成为大多做医疗影像语义分割任务的baseline，也启发了大量研究者去思考U型语义分割网络。而如今在自然影像理解方面，也有越来越多的语义分割和目标检测SOTA模型开始关注和使用U型结构，比如语义分割Discriminative Feature Network(DFN)(CVPR2018)，目标检测Feature Pyramid Networks for Object Detection(FPN)(CVPR 2017)等。(Its influence has reached 70% in 2015. Then it became the baseline that most of the medical image semantic segmentation tasks, and inspired a large number of researchers to think about the U-shaped semantic segmentation network. In the aspect of natural image understanding, more and more SOTA models of semantic segmentation and object detection begin to pay attention to and use U-shaped structure, such as semantic segmentation, discriminative feature network (DFN) (cvpr2018), feature pyramid networks for object detection (FPN) (CVPR 2017), etc.)

说明：  对图像格式进行更改，将mat格式转化为其它格式的程序(Program to change image format and convert mat format to other formats.)

说明：  1、正弦函数 f (t) = K sin(wt +a) 2、矩形脉冲函数 f (t) = u(t) - u(t - t0 ) 3、抽样函数 4、单边指数函数 f (t) = Ke -t 5、已知信号 f1(t) = u(t + 2) - u(t - 2)， f 2 (t) = cos(2pt) ，用 MATLAB 绘制 f1(t) + f 2 (t) 和 f1(t)′ f 2 (t)的波形。(such as : Sine function f (t) = K sin(wt +a) Rectangular pulse function f (t) = u(t)-u(t-t0) Sampling function One-sided exponential function f (t) = Ke -t Known signal f1(t) = u(t + 2)-u(t-2), f 2 (t) = cos(2pt), draw with MATLAB The waveforms of f1(t) + f 2 (t) and f1(t)*f 2 (t))

对微震图像进行去燥，利用同步压缩连续小波变换进行自动微震去噪和起始检测。(Denoising the microseismic image,automatic microseismic denoising and onset detection using the synchrosqueezed continuous wavelet transform.)

经过一系列步骤实现结构光的中心提取，结果还不错(After a series of steps, the center of structured light is extracted, and the result is not bad.)

基于MATLAB的图像二维熵的计算，采用了改进的均值滤波器模板，使结果与物理意义更加契合。(This program calculates the 2-dim entropy of images, which is based on MATLAB. It uses a better average filter template, and makes the result in accordance with the identification of entropy.)

本代码主要关于摄影测量中的单向空间后方交会(resection of photogrammetry)

KPCA是一种PCA的改进方法,很值得一看,很实用!(KPCA is an improved method of PCA, it is worth a visit, it is useful!)