digital-image-processing

这是用C++实现图像立体匹配的一个完整的论文代码，主要特性是提出了一种全新的跨规模代价聚合方法，适合对于图像的立体匹配有一定基础的人学习(Cross-Scale Cost Aggregation for Stereo Matching)

【实例简介】 里面包含了DataGrid与ListBox的从主表样式设计，并绑定好数据，还有拓展菜单显示和隐藏-还有状态灯样式-系统托盘设计

随着生产和工艺的进步，人们对产品的质量要求越来越高，基于机器视觉的在线 检测系统成为一种重要的质量控制手段。本文对应用于宽幅面、高精度的基于分布式 机器视觉的产品表面缺陷在线检测理论与算法进行了研究，并在此基础上以印刷品和 浮法玻璃的缺陷检测为例，完成了模式产品和非模式产品的缺陷在线检测系统。(With the progress of production and technology, people are increasingly demanding high quality products, based on machine vision for online 检测 system into one kind of Zhong Yao quality Kongzhishouduan. This article applies to wide format, high-precision machine vision products based on distributed-line surface defect detection theory and algorithms are studied, and on this basis, and float glass in print defect detection, for example, completed a model of products and non-model product line defect detection system.)

亚像素提取边缘源代码，可以进行准确的边缘检测(Subpixel edge source code)

说明：  数学地角度来看，信号与图像处理可以统一看作是信号处理（图像可以看作是二维信号），在小波分析地许多分析的许多应用中，都可以归结为信号处理问题。对于其性质随时间是稳定不变的信号，处理的理想工具仍然是傅立叶分析。但是在实际应用中的绝大多数信号是非稳定的，而特别适用于非稳定信号的工具就是小波分析。(Mathematically, signal and image processing can be regarded as signal processing (image can be regarded as two-dimensional signal). In many applications of wavelet analysis, they can be reduced to signal processing. For signals whose properties are stable over time, the ideal tool for processing is still Fourier analysis. However, most of the signals in practical applications are unstable, and the tool especially suitable for unstable signals is wavelet analysis.)

说明：  图像分块处理和计算图像灰度平均值的算法，可用于路面识别预处理(Average value of image block calculation)

desing and develop a cube rotation

Choen-Sutherland算法裁剪线段 计算机图形学中使用Choen-Sutherland算法进行图形多边形裁剪，并用MFC实现(Choen-Sutherland )

利用MATLAB实现NSCT非下采样轮廓波变换(Realization of Nonsubsampled Contour Transform by Using MATLAB.)

利用奇异值分解（SUV）对图像信号分行降噪！(Singular value decomposition (SUV) of the image signal branch noise!)