SP_Liu_TCSVT_code2014

说明：  RGB-IHS变换：图像进行 RGB-HIS 正变换，分别对明度、饱和度、色调进行线性 拉伸显示；然后再进行反变换 (RGB-IHS transformation: the image is RGB-HIS transformation, respectively, lightness, saturation, hue, a linear stretch display then the inverse transform)

说明：  python实现双目立体匹配SGBM算法(SGBM algorithm for binocular stereo matching based on Python)

变分偏微分方程图像处理工具包，包括计算曲率，方差，L1,L2范数等29个实用算法(variational PDE image processing tool kit, including the calculation of curvature, variance, L1, L2 norm, and other practical algorithms 29)

基于YCgCr色彩空间与几何信息的人眼定位方法(YCgCr color space and geometry based on the information the human eye location methods)

这是运用matlab进行图像处理时会遇到的基本操作，包括图像的代数运算、几何运算、空间变换、区域操作等(This is for image processing using matlab will encounter the basic operations, including images of algebra, geometry operations, space transformation, regional operations, etc.)

压缩感知和超分辨率论文，关于如何将低分辨率的图像如何重建成高分辨率图像，很有用(compressed sensing and super resolution)

这是基于动态规划的立体匹配的代码，是当前立体匹配中很好的一种实现方式(This is the stereo matching based on dynamic programming code that is currently in a good stereo matching method to implement)

泊松融合在某种意义上解决了图像融合的问题，但其在融合的过程中仅仅考虑了融入图像的梯度，而没有利用背景图像的梯度，因此，在使用泊松融合的过程中，需要对融入区域的标记较为准确，否则，会造成背景纹理的丢失，视觉上可以明显觉察图像融入的痕迹。因此，对公式稍作修改，在考虑前景的同时考虑背景的变化，可以得到更优的结果。(Poisson convergence in a sense solved the problem of image fusion, but it only considers the integration of image gradient in the integration process, but not the use of a background image gradient, therefore, the use of the Poisson integration process, the need for more accurate marker into the area, otherwise, it will result in the loss of background texture, image integration can clearly perceive the visual traces. Therefore, the formula slightly modified, in considering the prospect of taking into account the changes in the background, you can get better results.)

用Graph cuts 来解决磁共振图像的 phase unwrapping。(Graph cuts used to solve the magnetic resonance images of the phase unwrapping.)

针对大尺度图像配准和不同传感器图像配准问题, 介绍了一种基于 SIFT 的图像配准方 法。(For large-scale image registration and image registration problem from different sensors, introduces a SIFT-based image registration method.)