CRF2D

高光谱图像的地物分类技术，对光谱分析并对比检测出地景的算法(Fifth hyperspectral image classification techniques, algorithms for spectral analysis and contrast detect landscapes)

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)

基于半色调图像的数据隐藏即加数字水印，针对半色调图像，所以使用的是DHSPT算法，算法较容易理解，简单，嵌入效果相对较好(Hidden based on the halftone image data plus digital watermark for halftone images, use DHSPT algorithm, the algorithm is easy to understand, simple, embedded effect is relatively good)

用matlab做的基于小波降噪和自适应滤波的程序，已经调试可以使用。(Program based on wavelet noise reduction and adaptive filtering using matlab, debugging can use.)

基于马尔科夫链的图像分割，较以往经典图像分割性能有很大提高(Markov chain-based image segmentation, image segmentation performance than the classical past has greatly improved)

图像匹配的实现，其中match.m：测试程序，sift.m :尺度不变特征变换（SIFT算法）的核心算法程序，appendimages.m: 该函数创建一个新的图像分别包含两个匹配的图像和他们之间的匹配对的连接直线，可以运行。 (The realization of image matching, which match.m: test program, sift.m: scale-invariant feature transform (SIFT algorithm) of the core algorithm, appendimages.m: This function creates a new image each consists of two images and matching match between them on the connection line, you can run.)

说明：  计算机图形学基本算法 DDA直线 中点直线 BRESEMHAM圆 正负法圆 B样条曲线 B曲线 (DDA line algorithm for computer graphics, the midpoint of the basic straight-line method BRESEMHAM circle round the positive and negative B-spline curve B curve)

Multi-Scale Structural Similarity Index (MS-SSIM). Download here. Please cite the following paper in any published work if you use this software. Z. Wang, E. P. Simoncelli and A. C. Bovik, "Multi-scale structural similarity for image quality assessment," IEEE Asilomar Conference Signals, Systems and Computers, Nov. 2003.

实现高斯模糊，运动模糊等的点扩展函数psf的估计，并复原(The estimation of point spread function PSF, such as Gauss blur and motion blur, is realized and restored.)

non-local means denoising 自己实现的非局部均值图像去噪的原始算法，对理解算法原理有一定帮助(Non-local means denoising： an implementation of the non-local means denoising of the original algorithm, some help understanding algorithm)