cv-project

图像的复制剪切粘贴，Visual C++编程技巧精选，很好的参考资料。(Copy cut and paste image, Visual C++ programming skills selected, a good reference.)

3D 点云建筑物分割代码3D 点云建筑物分割代码3D 点云建筑物分割代码(3D point cloud, buildign segmentation3D point cloud, buildign segmentation3D point cloud, buildign segmentation)

对三角网格进行驱动形变，使用Deformation transfer of Triangular Mesh算法(Driving Deformation of Triangular Mesh)

说明：  轻量级的三维画图控件，便于C/C++或C#等平台/语言中引用和开发(Lightweight 3D drawing control, convenient for reference and development in platforms / languages such as C/C++ or C#)

本例程通过matlab编写，显示一个GUI。在GUI中将输入到程序中的数据进行绘图。本例程能够实时进行绘图，并且可以将数据进行显示。同时还可以将输入到程序中的数据进行保存。在GUI中设置有控制开关，能够通过点击开关，将数据保存在不同的文本中便于后续处理使用。(This routine is written by matlab and displays a GUI. The data input into the program is drawn in the GUI. This routine can be plotted in real time and data can be displayed. At the same time, the data input into the program can also be saved. A control switch is set in the GUI, and the data can be saved in different texts by clicking the switch to facilitate subsequent processing.)

说明：  UNet最早发表在2015的MICCAI上，短短3年，引用量目前已经达到了4070，足以见得其影响力。而后成为大多做医疗影像语义分割任务的baseline，也启发了大量研究者去思考U型语义分割网络。而如今在自然影像理解方面，也有越来越多的语义分割和目标检测SOTA模型开始关注和使用U型结构，比如语义分割Discriminative Feature Network(DFN)(CVPR2018)，目标检测Feature Pyramid Networks for Object Detection(FPN)(CVPR 2017)等。(Its influence has reached 70% in 2015. Then it became the baseline that most of the medical image semantic segmentation tasks, and inspired a large number of researchers to think about the U-shaped semantic segmentation network. In the aspect of natural image understanding, more and more SOTA models of semantic segmentation and object detection begin to pay attention to and use U-shaped structure, such as semantic segmentation, discriminative feature network (DFN) (cvpr2018), feature pyramid networks for object detection (FPN) (CVPR 2017), etc.)

PCB板检测的大概流程如下：首先存储一个标准PCB板图像作为参考标准，然后将待检测的PCB板图像进行处理，比较与标准PCB图像的差异。根据差异的情况来判断缺陷类型。(The approximate process of PCB board detection is as follows: first, a standard PCB board image is stored as a reference standard, and then the PCB board image to be detected is processed to compare the difference between the standard PCB image and the standard image. The type of defect is judged according to the difference.)

深度学习的Toolbox,使用mnist_uint8手写字数据库，适合初学者使用。(Deeplearning of the Toolbox, use mnist_uint8 handwritten word , for beginners.)

影像融合评价程序，计算标准偏差，平均梯度，相关系数，光谱扭曲度等融合指标。(Image fusion evaluation, calculation of standard deviation, average gradient, correlation coefficient, spectral distortions, such as integration targets.)

说明：  常见的图像处理算法都有介绍，包括分割、插值、平滑、锐化、图像增强、几何变换、图像金字塔，图像配准、模板匹配等(Common image processing algorithms are introduced, including segmentation, interpolation, smoothing, sharpening, image enhancement, geometric transformation, image pyramid, image registration, template matching, etc)