linear-filtering-andmedian-filtering

此算法是图像之间的转换，二值图，RGB等的相互转换源代码(This algorithm is the conversion between the images, the two value of the map, RGB, and so on the conversion of the source code)

基于图像处理的识别技术，对扑克牌的自动识别，效果很好。(Recognition technology based on image processing,automatic identification of playing cards, the effect is very good. )

John Wiley & Sons - JPEG2000 Standard for Image Compression Concepts Algorithms and VLSI Architectures 2005(John Wiley )

经典的斑块分析算法，计算Blob的源码，算法很好。(Classical plaque analysis algorithms to calculate Blob source code, algorithms very well.)

说明：  （1）图像基本操作：不同格式（大于3种）图像的读入与存盘、文字叠加、不同彩色空间的转换、图像的DCT及FFT变换等； （2）图像增强：包括直方图拉升（线性和非线性）、直方图均衡、平滑与锐化（采用不同的滤镜），美颜（加分项）； （3）图像恢复：几何操作（如旋转、缩放、投影校正等）、模糊恢复（如运动模糊消除等，加分项）； （4）图像合成（加分项）：实现换头、换背景、图像拼接等功能。((1) Basic operation of image: reading and saving of images in different formats (more than 3 kinds), text superposition, conversion of different color spaces, DCT and FFT transformation of images, etc; (2) Image enhancement: including histogram lifting (linear and non-linear), histogram equalization, smoothing and sharpening (using different filters), beauty (bonus item); (3) Image restoration: geometric operations (such as rotation, scaling, projection correction, etc.), blur restoration (such as motion blur elimination, etc., plus points); (4) Image synthesis (Bonus): realize the functions of head changing, background changing, image splicing, etc.)

说明：  图像频域处理 CT技术与图像的重建 通过一维投影复原二维图像 Matlab实现 (Frequency domain image processing and image reconstruction of CT one-dimensional projection by Matlab to achieve two-dimensional image restoration)

集成了多种块运动估计算法，对刚接触运动估计算法的同学非常具有参考价值。(Integration of a variety of block motion estimation algorithm for motion estimation algorithm刚接触students have great reference value.)

基于分层的HOG的行人检测，具有很高的研究价值。(HOG based pedestrian detection layered with high research value.)

运用于人脸图像预处理中，主要实现功能有：人脸检测，人脸对齐，人脸图像放缩，人脸剪切。(Applied to the face image preprocessing, the main features are: face detection, face alignment, face image zoom, face cuts.)

压缩感知CS——采用小波变换进行稀疏表示，高斯随机矩阵为观测矩阵，重构算法为SP算法，对256*256的lena图处理，比较原图和SP算法在不同采样比例(0.74、0.5、0.3)下的重构效果，并各运行50次，比较算法性能PSNR和每次的运行时间(Compressed sensing CS- using wavelet transform as sparse representation, Gaussian random matrix as the observation matrix and SP algorithm as the reconstruction algorithm. Compare lena figure and the reconstruction results using SP algorithm at different sampling ratio (0.74,0.50.3),then each runs 50 times, compare the performance of PSNR and each running time)