liziqun

说明：  特征选择算法，防止分类结果出现过拟合，提前对多维的特征向量进行选择筛选(A feature selection algorithm)

L0梯度最小化算法，2011年由xuli提出的算法(L0 gradient minimization algorithm, in 2011 xuli put forward the algorithm )

简化数据模型、减少数据处理时间、提高成型效率。算法无需建立三角面片之间的拓扑关系，可直接进行切片分层，切平面与网格面片所得的交线段也无需排序，节省了生成轮廓线时对交线段重新排序所需的时间，提高了分层处理的效率。(Simplify the data model, and to reduce the data processing time and improve the molding efficiency. Algorithm without establishing the topological relationships between the triangular dough piece, can be directly slice layered tangential plane with the grid cross-segment of the dough piece obtained without sorting, save when the contour line is generated on the cross segment reordering the time required, improve the efficiency of the hierarchical processing.)

半自动分割彩色图像的颜色相同区域，可以达到PS的魔棒效果(Semi-automatic segmentation of color images the same color region can reach the magic wand effect of PS)

彩色图像转为灰度图像，灰度图像的傅里叶低通滤波，彩色图像的傅里叶低通滤波，三种滤波器的三维表示(Transforming a color image to a grayscale image Do low-pass filtering to a grayscale or color image by Fourier transform The three-dimensional representation of three types of filters )

CT反投影重建的R-L滤波函数与S-L函数，应用对象为matlab自带shepp-logan模型图像(R-L function and S-L function applying to CT backproject reconstruction)

基于最大类间方差准则的阈值分割算法。其基本思想是对像素进行划分，通过划分得到的各类之间的距离达到最大，来确定合适的门限。(Based on the maximum between-cluster variance criteria threshold segmentation algorithm. The basic idea is to divide pixels, obtained through the division of the distance between the various types of maximum, to determine the appropriate threshold.)

用偏微分方法进行图像修复，可以修复灰度和彩色图像(By partial differential method for image restoration, can repair gray and color images)

数字图像邻域平均法去噪的实现(包括有Ｍ文件和图像)(neighborhood Digital Image Denoising the average realized (including M documents and images))

说明：  SIFT特征点的提取和匹配，SIFT算法首先在尺度空间上进行关键点检测，确定关键点的位置和关键点所处的尺度，然后使用关键点邻域梯度的主方向作为该点的方向特征，最后由关键点邻域梯度信息生成关键点的特征向量(SIFT algorithm firstly detects the key points in the scale space, determines the location of the key points and the scale of the key points, then uses the main direction of the key point neighborhood gradient as the direction feature of the point, and finally generates the feature vector of the key points from the key point neighborhood gradient information)