similarityDescriptor

基于压缩感知的图像恢复重建的实验源代码以及相关图片及文件(Compressed sensing image reconstruction experiment source code and related images and documents)

fbp算法实现CT重建，包括不同投影个数、探测器个数和噪声对重建后图像的质量的影响。(FBP CT reconstruction algorithm, including the number of different projection, and the number of detector noise on the reconstructed image quality.)

自动前背景分割，基于超像素、形状和外观前验概率及图切割(A novel foreground/background segmentation algorithm that attempts to segment the interesting objects from the rest of the image.The model includes a geometric prior and an appearance prior, whose parameters are learnt on the fly from images that are similar to the query image. It uses graphcut based energy minimization to enforce spatial coherence on the model’s output.)

几个大牛对集成了国内外特征提取最前沿的算法，特征提取，DOG,HARRIS,HARRIS-LAPLACE,HARRIS-AFFINE,MSER.描述符，SIFT,AFFINE-SIFT,GLOH.经测试，速度快，描述符准确。(Integration of feature extraction algorithms from several expert of domestic and international, feature extraction： DOG, HARRIS, HARRIS-LAPLACE, HARRIS-AFFINE, MSER； Descriptors： SIFT, AFFINE-SIFT, GLOH. The test reveal the speed and accurate descriptor.)

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ROMP算法，对256*256的lena图处理，比较原图和ROMP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 ROMP algorithm as the reconstruction algorithm. Compare lena figure and the reconstruction results using ROMP algorithm at different sampling ratio (0.74,0.50.3),then each runs 50 times, compare the performance of PSNR and each running time)

共有5个代码其中4个分别实现图像的中值滤波、均值滤波、双边滤波、Lee滤波，另一个是求图像的均值和方差。模板均不固定自己根据需要确定合适的w值。(There are five codes of which four were achieved image median filter, mean filter, bilateral filter, Lee filter, and the other is seeking an image of the mean and variance. Templates are not fixed ourselves w appropriate values as needed.)

说明：  用MATLAB实现数字图像处理的块编码，数字化，锐化，灰度级变换，直方差均衡等等。(Using MATLAB realization of digital image processing block coding, digitization, sharpening, gray-scale transformation, and so straight variance balanced.)

说明：  二进小波变换的图像增强,matlab代码(Dyadic wavelet transform image enhancement, matlab code)

说明：  根据文献Verification of color vegetation indices for automated crop imaging applications所述方法实现的可见光（RGB）的植被提取，效果非常好，压缩文件内附有该文献英文原文，以及部分供测试图片。(According to the method described in the document verification of color vegetation indexes for automated cross imaging applications, the effect of vegetation extraction of visible light (RGB) is very good. The original English version of the document and some test pictures are attached to the compressed file.)

说明：   vc代码,用于图像直方图均衡（以原始girl图像为测试图像） (vc code, for image histogram equalization (in the original girl image for the test images))