VisualSFM_windows_cuda_64bit

第8章 图象的检测及模板匹配 图象的分割与检测(识别)实际上是一项非常困难的工作。很难说清楚为什么图象应该分割成这样而不是那样。(Chapter 8 Detection of image template matching and image segmentation and detection (recognition) is actually a very difficult task. It is hard to say clearly why the image should be divided into such and not as.)

一种基于non-sample的纹理合成demo，程序性能还有待优化，效果还不错.(texture synthesis demo.)

本程序实现功能： 1、微机、IBM工作站segy格式文件的a)变面积、b)波形、c)波形加变面积显示； 2、AGC自动均衡显示； 3、用任意多边形选择剖面数据并提取归一化能量、修改选取数据。 (This program function: 1, microcomputer, IBM workstations segy format file of a) become area, b) waveform, c) waveform and become area shows 2, AGC automatic equilibrium display 3, with arbitrary polygon choose profile and extracted data normalization energy, modify, select data.)

sobel segmentation, this algorithme has a great effect for segmenting

C++和halcon结合，用于图形处理时进行三相机标定(C++ and halcon combined for three camera calibration)

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.)

可以自行选择将图片放大或缩小到一定的倍数。(Can select the picture to zoom in or out to a certain multiple of.)

分水岭算法的实现,用VC++语言实现，构成可靠的算法实现(the implement of the watershed)

一个简单的图像浏览器，对初学C++开发图像处理系统的朋友有启迪作用。(A simple image viewer, for beginners C++ image processing system developed friends revealing. )

基于OpenCV实现的图像切割程序，通过程序中参数设置分块的数量和大小(The project is uesd to break an image into block)