kdtree

自主选择性的查看一幅图像中的部分区域的颜色直方图：允许用户在一幅图像中选择一个矩形区域，通过按住鼠标键画一个矩形，当鼠标放开是，高亮显示矩形框，同时在另一个独立的窗口中，使用画图函数画一个图表（选定区域的颜色直方图），分别用蓝，绿，红表示选中区域中每种颜色的像素数量。(Self-selective color in an image to view a partial area of ​ ​ the histogram: Allows the user to select a rectangular area in an image by holding down the mouse button to draw a rectangle when the mouse is released, the highlighted rectangle, Meanwhile in a separate window, using the drawing functions to draw a chart (selected color histogram region), respectively, with blue, green, red indicates the number of pixels in the selected area of ​ ​ each color.)

通过点云数据的格网化，建立格网分块索引，这是一种有效的点云数据存储方式。( Through the point cloud data grid , the establishment of a grid block index, which is a valid point cloud data storage. )

VisualC++数字图像处理技术详解第2版光盘，第十章(VisualC++ digital image processing technology Detailed Version 2 discs, Chapter X)

该代码用于对错误匹配点进行过滤操作，即去除错误的匹配点(The code is used to remove the wrong match points,and make sure the right matching.)

：植物种类识别方法主要是根据叶片低维特征进行自动化鉴定。然而，低维特征不能全面描述叶片信息，识别准确率低，本文提 出一种基于多特征降维的植物叶片识别方法。首先通过数字图像处理技术对植物叶片彩色样本图像进行预处理，获得去除颜色、虫洞、 叶柄和背景的叶片二值图像、灰度图像和纹理图像。然后对二值图像提取几何特征和结构特征，对灰度图像提取 Hu不变矩特征、灰 度共生矩阵特征、局部二值模式特征和 Gabor 特征，对纹理图像提取分形维数，共得到 2183 维特征参数。再采用主成分分析与线性 评判分析相结合的方法对叶片多特征进行特征降维，将叶片高维特征数据降到低维空间。使用降维后的训练样本特征数据对支持向量 机分类器进行训练(plant species identification method is mainly based on blade automatic identification of low dimensional characteristics.However, can not fully describe blade low-dimensional feature information, identification accuracy is low, in this paper A kind of plant leaves recognition method based on multiple feature dimension reduction.First by digital image processing technology to the plant leaf color sample image preprocessing, obtain background color removal, wormhole, petioles, and the blades of a binary image, gray image and texture image.Then the binary image to extract the geometric characteristics and characteristics of structure and characteristics of gray image extraction Hu moment invariants, gray co-occurrence matrix feature, local binary pattern features and Gabor, to extract the fractal dimension of texture image, get 2183 d characteristic parameters.By principal component analysis and linear uation analysis method of combining the characteristics of blade more feature dimensi)

利用k—mean算法根据U、V进行聚类分块，最后完成图像分割，分割出得块用不同的灰度等级表示出来。(K-mean algorithm to cluster sub-blocks according to the U, V, to finalize the image segmentation, segmentation have blocks with different gray levels represented.)

读取dxf文件，并利用opencv画出2D形状(Read the DXF file, and draw a 2D shape using OpenCV)

绣花问题是连续型的填充，在不同区域的缝制过程中，缝针不能提针，因此不能用一般的离散型区 域填充方法处理。本文运用几何计算和图论理论提出了一个绣花缝针轨迹自动生成算法：先对轮廓走向进行 定义，通过轮廓铅垂方向的局部极值点的分割线将图案从上向下进行分割，采用交点的特征值比较彻底的解 决了分割时的重点问题，将图案区域准确的划分成缝针能一次完成的若干个节点。在此基础上根据节点的邻 接关系建立节点的邻接“图”，通过图论中半哈密尔顿路径或深度遍历方法找到节点的遍历（缝制）序列和每 个节点的缝制方向，最后可对设定的起点、终点和缝针间隔的条件自动提供缝针的走向轨迹。(In the process of embroidering, needle can not hang up for changing to a different area. Therefore, Embroider problem could be abstract as a continuous area-filling work. Considering disperse area-filling methods can not process this problem well. Based on geometry computing and graph theory, an algorithm of finding path of embroidering needle are proposed in this paper. First, outline orientations are defined, and finding all local extreme points of inner outline on their gravitational orientation to build sectioning lines so as to divide the picture. By using intersection point character the overlap point problem was solved perfectly. Therefore, the picture is divided into some nodes which can be finished alone. Then, based on connections of these nodes, an adjacency graph of nodes was built. Using half-Hamilton path or depth-first search method, both embroidering sequence and direction of these nodes could be got from the graph. Finally, from a defined start-point, end-point)

Application of the Fourier-Mellin transform to translation-, rotationand scale-invariant plant leaf identification

说明：  对3D数据运用gpu实现八叉树，完成分割并进行渲染。(The use of 3D data on the GPU octree to achieve complete segmentation and rendering.)