资源列表
pro2
- 图像分解，将图像分解成结构和纹理，使图像分块化-Image decomposition, the image is decomposed into structure and texture of the image block
Tonlun-algorithm-
- 同伦算法，解决1范数最小化问题，在稀疏求解时可是使用-Homotopy algorithm, solve the 1 norm minimization problem, but use the sparse solution
Poisson-Image-Editing
- 用Python语言实现Poisson Image Editing（泊松图像编辑）算法-implementation of Poisson Image Editing algorithm with python.
regiongrow
- 区域生长对焊接孔隙检测的应用，分别显示了种子点、已通过阈值测试的像素的二值图像和8连通性分析后的结果-The application of regional growth of weld porosity detection
Depth-from-Defocus
- 本文是计算机视觉的重要分支——计算成像的相关文章，文章对于利用像面离焦获取图像深度信息(DFD/DFF)进行了详细的论述。-This article is a comprehensive review of the computational imaging, which is an important branch of the computer vision. This article includes thorough insight on the Depth Defocus/Focus
deng
- 基于LIP（对数图像处理）模型的图像增强算法，很简单快速的图像处理算法-Based on LIP (logarithmic image processing) model of image enhancement algorithms, very simple and fast image processing algorithms
transfor_img_to_tif
- 批量化处理图像格式转换，即从img、dat、jpeg等格式转换为tiff格式，在ENVI/IDL环境下直接运行即可。-transform the style of the remote sensing miagery data img\dat\jpeg to the tiff style by batch.
img2dcm
- 实现了将JPG格式的图像转换成DICOM的医学图像。使用该文件需要配准DCMTK。-Implements the JPG format of the image is converted into DICOM medical images.Use the file need registration DCMTK.
Sanban-Ganshe
- 散斑干涉实验，解析散斑，计算距离的，附有C++和matlab源码-Speckle interferometry experiments, resolution of speckle, calculated the distance, with MATLAB and C++ source code
gaosi
- 高斯混合模型算法实现c++，高斯混合模型就是用高斯概率密度函数（正态分布曲线）精确地量化事物，它是一个将事物分解为若干的基于高斯概率密度函数（正态分布曲线）形成的模型-Gaussian mixture model algorithm c++, Gaussian mixture model is a Gaussian probability density function (normal distribution curve) to accurately quantify things, it
gunqiufa
- 实现肺实质初始分割及采用滚球法（形态学开运算）进行修补肺实质轮廓凹陷。-Achieve initial segmentation and the use of the pulmonary parenchyma ball method (morphological opening operation) to repair the lung parenchyma contour depression.
source_code_vs2010
- 《OpenCL实战》源代码，在windows环境下实现- OpenCL source code, in the Windows environment to achieve