hw

CT重建图像时，先用BM3D滤波，然后运用经典的非局部平均去噪，效果很好。。(CT reconstruction image, the first with BM3D filter, and then use the classical non-local average denoising, very good. .)

pca 特征提取的源代码，对人脸识别很有帮助，(pca feature extraction of the source code, useful for face recognition,)

关于图像分割中分水岭的一个代码，能够实现相应功能，拿出来与大家共享(Image segmentation in the watershed on a code, can achieve the corresponding functions, and show to share with you)

说明：  光流场经典算法-LK算法，通过两幅图像计算光流场。(Lucas – Kanade Motion Estimation using Pyramids)

图片处理 去噪音，去模糊为了实现较好保留图像边缘特征的有效去噪,提出了一种基于边缘检测的Contourlet 变换去噪方法(Picture Deal)

采用radon变换检测直线，有详细注解，具有抗旋转性(Radon transform line detection, and a detailed explanation, with anti-rotational)

说明：  实现图像受混合噪声污染时去除噪声的目的，在6种方法比较之下，得出最优的图像去噪算法(Image by mixed noise pollution when the purpose of removing noise, in the six kinds of methods of comparison, the optimum image denoising algorithm)

点云数据（圆柱面）

C#调用DLL实现图像文字识别(OCR)(C # call DLL realize image character recognition (OCR))

对双目视觉图像对进行匹配获取视差图，为后续三维重建做基础。(Binocular vision images are matched to obtain the disparity map, as a foundation for the subsequent three-dimensional reconstruction.)