work

说明：  完成基于各向异性的自适应超声图像去噪和边缘增强方法，参考Adaptive Anisotropic Diffusion for Ultrasonic Image Denoising and Edge Enhancement.pdf，加入了m参数(The completion of ultrasound-based adaptive anisotropic image denoising and edge enhancement method, reference Adaptive Anisotropic Diffusion for Ultrasonic Image Denoising and Edge Enhancement.pdf, joined the m parameters)

说明：  很好的图像边缘检测程序，MATLAB环境，里面的程序我都试过了，无报错，并附带图片，可直接运行。(Good edge detection procedure, MATLAB environment, which I have tried the procedure, and without error, and attached picture, can be directly run.)

说明：  matlab输入CAD图像文件，matlab中图形导入CAD，matlab与CAD互转(Matlab Input CAD Image File or graphics Import into CAD in matlab or matlab and CAD Interchange)

基于遥感光学图像的宽网道路检索，能够快速的实现半自动道路提取，给出种子点对输入方向进行快速检索(Optical remote sensing images based on a wide network of roads retrieval, the realization of fast semi-automatic road extraction, given the input direction of the seed point for rapid retrieval)

上课时做的一个小程序，表达式计算程序，采用vc++，可能有点儿小瑕疵，但基本运行是没问题的(Class to do a small procedure, expression of the calculation procedure for the vc++, may be a bit small flaws, but the basic operation is no problem of)

26个不同影像处理程序,以VC++开发,是了解影像入门好帮手(26 different image processing procedures to VC++ Development is helpful to understand the image entry)

基于多帧图像插值（Interpolation）技术的方法是SR恢复技术当中最直观 的方法。这类方法首先估计各帧图像之间的相对运动信息，获得HR图像在非均 匀间距采样点上的象素值，接着通过非均匀插值得到HR栅格上的象素值，最后 采用图像恢复技术来去除模糊和降低噪声（运动估计!非均匀插值!去模糊和 噪声）。(In this paper, we propose a novel method for solv- ing single-image super-resolution problems. Given a low-resolution image as input, we recover its high- resolution counterpart using a set of training exam- ples. While this formulation resembles other learning- based methods for super-resolution, our method has been inspired by recent manifold learning methods, par- ticularly locally linear embedding (LLE). Speci?cally, small image patches in the low- and high-resolution images form manifolds with similar local geometry in two distinct feature spaces. As in LLE, local geometry is characterized by how a feature vector correspond- ing to a patch can be reconstructed by its neighbors in the feature space. Besides using the training image pairs to estimate the high-resolution embedding, we also enforce local compatibility and smoothness con- straints between patches in the target high-resolution image through overlapping. Experiments show that our method is very ?exible )

使用C++和CUDA编写的双边滤波器。在平滑图像的同时可以保持边界(Using bilateral filter the C++ and CUDA written. Boundary can be kept in the smooth image while)

实验两张图片的拼接，对于图片中的匹配对，用ransac方法消除错配，并估计出仿射矩阵。然后将一张图进行仿射变换，再实现拼接(Experiment two pictures of the stitching, matching pairs for the picture, with ransac way to eliminate mismatches, and to estimate the affine matrix. Then an affine transformation diagram, and then realize splicing)

实现给定图像中目标的有效监测，并根据颜色对目标分割。(The object can be detector, and it is segmented by the color.)