b-splines

缺陷检测，顶帽变换，底帽变换，halcon，可以直接使用(Defect detection, top hat transformation, and bottom cap transform, Halcon, can be used directly)

在保证图像质量的前提下，为了提高可逆信息隐藏的容量，提出了一种基于差值扩 展的可逆信息隐藏新算法(The premise of guaranteeing the image quality, in order to improve the reversible capacity of information hiding, a difference expansion based on new algorithm for reversible information hiding)

图像处理，手写数字识别，GUI界面内自写数字，可以用来学习。(Image processing, digital handwriting recognition, digital write within the GUI interface, can be used to learn.)

稀疏自适应匹配追踪算法，无需稀疏度，就可以重构原始信号。(Sparse adaptive matching pursuit algorithm, without sparsity, we can reconstruct the original signal.)

介绍Opencv这个图像处理库环境下的GMM建模与EM算法，从数学的角度深入分析高斯建模和EM算法(Introduce the the Opencv this image processing GMM modeling the EM algorithm in the library environment, in-depth analysis from a mathematical point of the Gaussian model and the EM algorithm)

数字图像处理第二版中文版（冈萨雷斯）Digital Image Processing(Digital Image Processing 2nd Edition Chinese (Gonzalez))

说明：  用于MATLAB的支持向量机的工具箱，用于训练与验证(Support vector machine (SVM) for MATLAB toolbox, used for training and validation)

稀疏表示的毕业参考论文，在图像去噪、图像修复、人脸识别及压缩感知等图像处理领域中的应用进行了总结.(Sparse representation of graduation reference papers, summarized in the image denoising, image restoration, face recognition and compressed sensing and other image processing applications)

2016华为软件精英挑战赛，采用迪杰斯特拉算法，效率高，但需要自行修改(HUAWEI software challenge 2016)

三维激光点云配准是点云三维建模的关键问题之一。经典的 ICP 算法对点云初始位置要求较高且配准 效率较低，提出了一种改进的 ICP 点云配准算法。该算法首先利用主成分分析法实现点云的初始配准，获得较好 的点云初始位置，然后在经典 ICP 算法的基础上，采用 k － d tree 结构实现加速搜索，并利用方向向量夹角阈值去除 错误点对，提高算法的效率。实验表明，本算法流程在保证配准精度的前提下，显著提高了配准效率。 (Three-dimensional laser point cloud registration is one of the key three-dimensional point cloud model. High classical ICP algorithm to the initial position of the point cloud registration requirements and low efficiency, proposed an improved ICP point cloud registration algorithm. Firstly, the use of principal component analysis of the initial point cloud registration, get a better initial position of the point cloud, then the basis of classical ICP algorithm using k- d tree structure to achieve speed up the search, and using the direction vector angle the removal of the threshold point error and improve the efficiency of the algorithm. Experiments show that the algorithm processes to ensure the accuracy of registration under the premise, significantly improve the efficiency of registration.)