fenxing

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.)

这是一个关于鲁棒的多传感器图图像配准程序的算法可直接使用。 (This is a robust multi-sensor chart image registration procedures of the algorithm can be used directly.)

HOG特征提取，以通过测试。希望对大家能有所帮助。(HOG feature extraction, in order to pass the test. I hope we can help.)

视频图像处理，采用背景减除法中混合高斯建模进行视频前景和背景的分离(Video image processing, background subtraction method using Gaussian mixture modeling to separate the foreground and background video)

一个基于DFT的水印算法源码；其中有嵌入，提取，测试图片；还有攻击程序，可以用来测试(DFT-based Watermarking Algorithm source including embedding, extraction, testing picture there are attacks on the procedures that can be used to test)

说明：  二值化算法，含otsu,niblack,kapur,kittlerMet等方法(Binarization algorithm, including otsu, niblack, kapur, kittlerMet and other methods)

基于图和流形排名的图像显著性检测算法，MATLAB实现(Manifold ranking based on maps and image saliency detection algorithm, MATLAB realization)

说明：  实现直接序列扩频水印的嵌入与提取。基于待嵌入消息生成二进制水印序列,生成扩频码，用消息序列调制生成水印序列。依次处理灰度图像的每一个载体图像像素，根据相应位置 水印序列完成嵌入修改。(Realize the embedding and extraction of direct sequence spread spectrum watermark. The binary watermark sequence is generated based on the message to be embedded, the spread spectrum code is generated, and the watermark sequence is generated by message sequence modulation. Each carrier image pixel of gray image is processed in turn, and the embedding modification is completed according to the corresponding position watermark sequence.)

主要有图像的聚类分割和Ncut算法的彩色图像分割，对于新人有着很好的效果(There are clustering image segmentation algorithm and Ncut color image segmentation, it has a good effect for newcomers)

编制一个通用的边缘提取函数。通过输入不同的参数，能够实现Sobel算子、Prewitt算子、Roberts算子、Marr算子和Canny边缘检测。 实验图像任选 (Preparation of a common edge extraction function. By entering different parameters to achieve the Sobel operator, Prewitt operator, Roberts, operator, operator of Marr and Canny edge detection. Experimental image optional)