gentleBoost

两个l1准则下的噪声干扰信号压缩感知重构举例，两个例子的稀疏矩阵均为DCT矩阵，而观测矩阵分别采用单位阵和随机矩阵，有详细的步骤和使用方法，适用于初步的学习压缩感知方法。(This programme supply two examples by Compressed sensing with l1 norm. The sparse matrix of two examples are all DCT matrix and the obsever matrix are unit matrix and random matrix respectively. We give the detailed usage and steps for the programme which is useful to the beginner.)

matlab函数，将多维矩阵的极值找出并定位，图像处理经常用到，很简单很好用(matlab function, multi-dimensional matrix to identify and locate the extreme, often used in image processing, it is very simple to use)

轻量级的MTCNN实现，无需caffe和tensorflow基本库支持，内部实现卷积运算，速度比普通mtcnn要快一倍。

图像盲去卷积复原程序，matlab6.5验证可以运行(image deconvolution )

ASIFT图像特征提取源代码，有测试图片和demo(ASIFT image feature extraction source code, test images and demo)

说明：  一些快速实现图像模糊增强的的demo，matlab源码。已经测试通过。(Some image blurring rapidly enhanced the demo, matlab source. Have the test.)

Digital Image Processing, stretch of an image with two optional setting via realtime combobox (stretch or default size).

一幅大小为256×256的256级灰度图像（每像素8bit） 如果图像的各个像素之间是统计独立的，求该图像的信息熵 -离散无记忆信源 如果图像的各个像素之间不是统计独立的，求该图像的信息熵 -图像像素的概率分布模型(A 256 gray scale image (8bit per pixel) with a size of 256 x 256 If each pixel of the image is statistically independent, the information entropy of the image is calculated Discrete memoryless source If each pixel of the image is not statistically independent, the information entropy of the image is calculated Probability distribution model of image pixels)

说明：  为了达到较好的隐藏效果，本文采用游程编码的方法在二值图像中隐藏信息。秘密信息嵌入时修改二值图像的游程长度，如果秘密信息为是0，则修改该游程长度为偶数；如果秘密信息的取值与游程长度的奇偶性相匹配，则不改变游程长度。提取时根据游程长度奇偶性提取出秘密信息。在信息隐藏时，改变游程的奇偶性时通过对下一个游程的第一个像素值进行修改，因此当下一个游程长度为1时通过改变当前有成的值实现。(In order to achieve better hiding effect, we use run length encoding method to hide information in two value images. When the secret information is embedded, the length of the travel length of the two value image is modified. If the secret information is 0, the length of the travel length is even even. If the value of the secret information is matched with the parity of the length of the run, the length of the journey is not changed. The secret information is extracted according to the parity of run length. In information hiding, changing the parity of the journey is modified by the first pixel value of the next run, so the current length is 1 by changing the current value.)

有关数字图像退化函数的估计与滤波，维纳滤波器实现，运动模糊等(For digital image degradation function estimation and filtering, Wiener filter implementation, motion blur, etc.)