信号检测与估计理论

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.)

主要适用于图像分割，用的是马尔科夫随机场，非常好用(Mainly applicable to image segmentation, using the Markov random field, very easy to use)

以心电信号检测为例，通过小波模极大值奇异性检测和求取Lipschitz指数确定心电信号R波的位置(Taking the ECG signal detection as an example, the position of the R wave of the ECG signal was determined by the singularity detection of the wavelet modulus and the Lipschitz index)

说明：  高斯尺度差角点检测算法 将轮廓曲线在不同尺度下的演化差异的变化量作为角点响应函数并提出相应的 DoG 检测算子(Gauss scale difference corner detection algorithm)

基于遗传算法的图像增强代码，亲测好用，值得下载(Based on the genetic algorithm image enhancement code, pro-measurement easy to use, it is worth downloading)

说明：  基于python-opencv的图像匹配代码，包含了SIFT、SURF、AKAZE、ORB方法。43-48行修改图像路径，74-81修改匹配方法。(dev: python3.6+opencv_python==3.4.2+opencv-contrib-python==3.4.2)

图像融合工具包：包含多种基本图像融合方法 开发环境：matlab(Image Fusion tool kits : a mixture of basic image fusion method development environment : Matlab)

基于红外图像的弱小目标检测与跟踪:计算图像的局域灰度概率矩阵,在图像上标出检测到的奇异点,标出最终检测到的小目标(Weak target detection and tracking based on infrared images: calculate the the local grayscale image probability matrix, detected singular points marked on the image, marked the final detected small goals)

。基于Wirtinger流的相位恢复算法是由Emmanuel J. Candes等于2015年提出的新的相位恢复算法，该方法不再将光场函数局限于非凸集中，而是利用一种新的初始化方式以及迭代规则来寻找最优解。(a new approach about phase retri which is published in 2015)

asift算法进行图像配准，具有较好的结果，调试完成，可用(image registration, asift algorithm has a better result, debugging is complete, the available)