4546

实现对图像平滑模糊，有简单平滑、高斯模糊和中值滤波三种可选，基于OPenCV类库实现，代码可直接运行(Achieve a smooth blur the image, a simple smooth, Gaussian blur and median filtering three options, OPenCV-based library, the code can be run directly)

利用棋盘格对相机进行标定，加入误差判定及像素空间到实际物理空间的距离计算(The camera is calibrated by checkerboard, the error is added and the distance of pixel space to the actual physical space is calculated)

EDLines是一种快速直线检测算子，2012年在ICCV上提出，也是目前处理直线检测最快的算法之一，该算法包含三个步骤：（1）边缘提取：利用Edge Drawing (ED)算法[28,29]从灰度图像中提取边缘片段；（2）线段检测：利用最小二乘法提取直线段；（3）线段确认：遵循Helmholtz定律，从已提取的直线段中摒弃虚假线段。EDLines算法的优越性得益于Edge Drawing (ED)算法能够从灰度图像中准确、快速、稳定地提取出光滑、完整的边缘片段。Edge Drawing (ED)算法包含以下步骤： （1）采用size=5*5,σ=1的高斯核对灰度图像进行平滑滤波，去除噪声； （2）采用一种常用的梯度算子，如Prewitt、Sobel或Scharr等计算平滑后图像中每个像素点的梯度幅度和梯度方向； （3）将梯度图中邻域内幅度最大的像素点标记为锚点，这些锚点成为图像边缘点(edge elements)的概率很大； （4）将相邻的锚点连接成边缘线。从一个锚点起始，ED利用相邻像素的梯度幅度和方向在梯度为最大值的锚点之间游走。 (Edge Drawing (ED) is our recently-proposed, novel, fast edge detection algorithm. What makes ED stand out the existing edge detectors, e.g., Canny, is the following: While the other edge detectors give out a binary edge image as output, where the etected edge pixels are usually independent, discontinuous entities ED produces a set of edge segments, which are clean, contiguous, i.e., connected, chains of edge pixels. Thus, while the output of the other edge detectors requires urther processing to generate potential object boundaries, which may not even be possible or result in inaccuracies ED not only produces perfectly connected object boundaries by default, but it also achieves this in blazing speed compared to other edge detector.)

类似PChunter的内核工具。本工具是应用层的源码。适合内核新手(Similar PChunter core tools. This tool is the source application layer. Suitable for novice kernel)

本文介绍了一种测量大气能见度的方法，双亮度差法，代码中给出了详细的注释，并且包括OSTU方法等等(In this paper, a measuring method of atmospheric visibility double brightness difference method, the code is given detailed annotations, and including the OSTU method and so on)

自己毕业设计做的改进的基于某vc视频处理框架代码的重心多目标跟踪代码(The center of gravity of a vc video processing framework code-based target tracking code own graduation design improvements do)

：数字水印将感觉不到的信号嵌入到声频、视频和图像中以实现不同的目的。例如: 添加标题和版权保护。首先介绍 了有关数字水印的基本原理、重要属性及其主体框架。然后,将数字水印按不同角度划分为不同种类。讨论了各种各样的数 字水印算法以及数字水印在不同领域的应用,并简要介绍了对数字水印的攻击。最后,给出了数字水印当前的研究现状和发 展形式及前景。(: Digital watermark embedding imperceptible signals to the audio, video and images to achieve different purposes. Example: Add a title and copyright protection. Firstly, the basic principle about digital watermarking, and the main framework of the important attributes. Then, the digital watermark according to different angles into different types. Discussed a wide range of digital watermarking algorithms and digital watermarking applications in different fields, and a brief introduction of the digital watermarking attacks. Finally, the digital watermark of the current situation and development in the form of research and prospects.)

在两个控件里实现自动的字幕滚动，点击取消后，停止(In the two controls in the subtitles automatically scroll, click Cancel, stop)

EM算法以及混合高斯模型，c++实现，控制台程序，函数调用很简单方便。可以在低版本vc6.0运行。(EM algorithm and hybrid Gauss model, c++ implementation, the console program, function call is very simple and convenient. Can be run at low vc6.0.)

说明：  缺陷检测，定位缺陷位置。主要用于工业之中螺帽的螺纹线的检测(Defect detection, location of defect location. Detection of screw thread for nuts in industry)