ImageRetrieval

图像分割处理的小波变换算法源代码，使用vc++(Wavelet transform image segmentation algorithm source code vc++)

用CUDA并行处理方法改写的图像降噪算法，包括KNN,NLM,以及改进的NLM方法。配置环境适合VS2010+CUDA5.0,对使用CUDA的同学来说是很好的教材。(Image denoising algorithms including KNN,NLM and refined NLM run on CUDA, useful demo for who learns CUDA based parallel programming.)

源码包括了常用的图像处理方法，代码详细，适合初学者(Source code, including the commonly used image processing method, the code in detail, suitable for beginners)

基于openCV的gabor函数,一位牛人编写的。希望对大家有用(gabor function based on openCV)

此程序利用openCV中人脸识别于模版匹配实现机器人的运动控制功能，其中机器人控制用了Aria的库和模拟器，使用者可根据控制需要替换这部分程序。 本程序的核心部分一直用于只能轮椅的人脸控制。(This process us face recognition in openCV and template matching to achieve robot motion control functions, which used the Aria library and robot simulator, user need replace this part of the control procedures to achieve their application.)

红外图像的亚像素边缘检测，检测边缘，用于图像配准。(Infrared image of the sub-pixel edge detection, edge detection for image registration.)

Opencv处理图像，用ostu法实现图像的二值化(Opencv image processing, using ostu method to achieve image binarization)

打开BMP图像 IHS Brovey图像融合(Open the BMP image IHS Brovey Image Fusion)

图像处理系列之边缘检测篇 涵盖内容： 1>Roberts算子 2>Prewitt算子 3>Sobel算子 4>Laplacian算子(Edge Detection)

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.)