用高斯函数实现的Harris角点检测

opencv3 的java开发资源，内附opencv的示例，包含图片和java工程，每个例子，一个小工程

说明：  根据左右相机拍摄的图片，先进行单目标定，再进行双目标定，之后通过立体校正和立体匹配得到视差图，计算深度(According to the pictures taken by the left and right cameras, monocular calibration is performed first, and then binocular calibration is carried out. Then the parallax map is obtained by stereo correction and stereo matching, and the depth is calculated)

opencv图像特征检测算法akaze，包含测试视频等。

基于opencv开发的sift匹配的原码程序,可以用,希望大家在次基础上写出图象拼接的程序.(opencv .sift matching)

说明：  行人的检测使用库函数OpenCV里已经内置的行人检测方法，调用OpenCV预先训练好了的HOG+线性SVM模型，能够对图像和视频中的行人进行检测，系统会分别使用两种算法通过矩形条框将图片中的行人框出来。(Pedestrian detection uses the built-in pedestrian detection method in OpenCV library function, calling the pre-trained HOG + linear SVM model of OpenCV, which can detect the pedestrians in images and videos. The system uses two algorithms to frame the pedestrians in pictures through rectangular bars.)

通过调用OpenCV库，采用计算相关性大小进行视频跟踪。在源码中输入要跟踪的图样，运行文件，程序可以识别跟踪摄像头摄取场景内与图样相关性最高的目标(By calling the OpenCV library, using a case-by-difference method for video tracking. Input source you want to track the pattern, run the file, the program can identify tracking camera scene and drawings highest goal intake)

个人整理的opencv最基本入门资料，推荐想入门的小白学习(Personally collated basic introductory information for opencv and recommended for white learning for beginners)

opencv显示图像，记得配置库文件和包含文件，我用的是opencv2.4.9,包括目录为：opencv_ml249d.lib opencv_calib3d249d.lib opencv_contrib249d.lib opencv_core249d.lib opencv_features2d249d.lib opencv_flann249d.lib opencv_gpu249d.lib opencv_highgui249d.lib opencv_imgproc249d.lib opencv_legacy249d.lib opencv_objdetect249d.lib opencv_ts249d.lib opencv_video249d.lib opencv_nonfree249d.lib opencv_ocl249d.lib opencv_photo249d.lib opencv_stitching249d.lib opencv_superres249d.lib opencv_videostab249d.lib

命令行程序，参考论文Image abstraction by flow-based ，实现图片卡通化的程序，效果十分理想，但美中不足的是运算速度较慢qvq

基于OpenCV的人脸识别演示程序。目前实现了Gabor+Fisherface算法，还有几何和光照归一化。 -->请到 http://code.google.com/p/facerecog/ 下载最新版本。<-- 功能：对摄像头拍摄的或用户指定的图像，检测其中人脸，然后在已存储的人脸库中找到最匹配的人脸并显示。 在VS 2008 SP1上编写，使用了OpenCV 2.0和MFC，通过消息处理函数与用户进行交互，利用多线程来实时显示图像。 数据处理分为了CFaceAlign（人脸检测+几何归一化）、CLightPrep（光照归一化）、CFaceFeature（Gabor特征提取）、CSubspace（计算Fisherface子空间）四个类，还有一个类 CFaceMngr 负责管理界面与数据之间的交流。注释很详细 程序中使用了OpenCV1.0和2.0，如果你没有安装这两者的库，或者想要看看运行效果，请到 http://code.google.com/p/facerecog/ 下载安装包。(An OpenCV-based face recognition demo. Gabor+Fisherface algorithm, face alignment and light normalization is implemented. Please go to http://code.google.com/p/facerecog/ to download latest codes, demo installer and OpenCV dlls.)