SIFT

说明：  (1)利用matlab函数进行噪声模拟，并用matlab自带函数进行图像滤波。 (2)利用给定图像自己编程实现使用均值滤波器、中值滤波器对不同强度的高斯噪声和椒盐噪声，进行滤波处理，并对结果进行评价分析，并解释结果。 (3)自己编程实现laplacian算子图像的处理，实现图像增强；编程实现sobel算子对图像边缘提取。将结果与matlab自带函数计算结果比较。 (4)利用模糊处理对图的灰度值进行改变实现灰度增强，并与直方图均衡结果比较((1) Matlab function is used to simulate noise, and Matlab function is used to filter image. (2) Using the given image, we use the mean filter and median filter to filter the Gaussian noise and salt and pepper noise with different intensities, evaluate and analyze the results, and interpret the results. (3) The image processing of Laplacian operator and image enhancement are realized by programming Sobel operator is used to extract image edge. The results are compared with those of MATLAB. (4) Fuzzy processing is used to change the gray value of the image to achieve gray enhancement and balance with histogram)

说明：  分析了如何利用小波变换技术对图像进行信息融合使读者从整体上对医学图像融合技术有一个比较清楚直观的理解 (Analysis of how to use wavelet transform to the image information fusion, so that readers from the whole of the medical image fusion technology has a relatively clear and intuitive understanding.)

图像分割，实现水果图像分割，用Matlab(tuxiangfenge)

基于模型匹配的永磁同步电机混沌化控制例子，是本人一点点做出来的。(this is a example for Chaos Anti-Control of Permanent Magnet Synchronous Motor Based on Asymptotic Model Matching. it was completed by myself.)

VapourSynth-BM3D-master BM3D算法的原创代码，运行速度超快，参考文献《Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering》(VapourSynth-BM3D-master BM3D original algorithm code, run super-fast, Reference " Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering" )

这是基于稀疏表示的图像重建，用来做图像去模糊或超分辨，绝对可以用(Sparse Representation for Image Restoration)

gabor_lpb纹理结合了gabor小波和LBP的特征，提取的纹理具有很好的鲁棒性(gabor_lpb texture combines gabor wavelets and LBP features extracted texture with a very robust)

在大图中找小图

非降采样Contourlet域内空间频率激励的PCNN图像融合算法的实现代码(Non-spatial frequency domain down-sampling Contourlet motivated PCNN image fusion algorithm implementation code)

说明：  在计算机视觉领域一种非盲去模糊的方法代码(A non-blind deblurring method code in the field of computer vision)