资源列表
bgslibrary
- 各种背景相减的算法，目前已经收录27中，大家可以少花力气，一个老外中间的背景相减代码库-Various background subtraction algorithm, has been included in the 27, you can spend less effort, a foreigner in the middle of the background subtraction code library
LIBSVM
- svmlib训练步骤及所需要的各种安装文件，在本机上成功运行。-svmlib procedures and training needs of the various installation files on the local machine to run successfully.
OrbTest
- 最新的图像匹配算法ORB，特征匹配速度比sift提高两个数量级。需要安装opencv2.3.1以上版本。-The latest image matching algorithm ORB
myOpenCV20
- 采用opencv2.2和vs2010，图像形态学膨胀与腐蚀-Using opencv2.2 and VS2010, image morphological dilation and erosion
OpenGL_NeHe_part_two
- Nehe 个人网站上OpenGL的源代码，其中是lesson9至lesson18的部分。-openGL codes for Nehe
bofAndColor
- 采用bag of word 特征加上颜色特征共同匹配的图像对匹配算法，具有匹配精度高的特点。-Bag of word feature by feature with the color image matching algorithm matches together, with matching high accuracy.
3d
- 3D效果软件。使用2个摄像头用USBhub连接后，打开该软件，可以实现《阿凡达》类似的3D效果，自己在家也可以阿凡达了-3D effects software. The use of two cameras with USBhub connected, open the software, can have a " Affan up" similar to the 3D effect, his own at home can also be reached by Affan
SVM
- Hog+SVM是速度和效果综合平衡性能较好的一种行人检测方法。后来，虽然很多研究人员也提出了很多改进的行人检测算法，但基本都以该算法为基础框架。因此，Hog+SVM也成为一个里程表式的算法被写入到OpenCV中。在OpenCV2.0之后的版本，都有Hog特征描述算子的API，而至于SVM，早在OpenCV1.0版本就已经集成进去了；OpenCV虽然提供了Hog和SVM的API，也提供了行人检测的sample，遗憾的是，OpenCV并没有提供样本训练的sample。这也就意味着，很多人只能用Ope
Algorithmsforimageprocessing
- Algorithms for image processing and computer vision书中的源代码-Algorithms for image processing and computer vision
SVM_Train_Predict_HOG
- 样本训练 以及训练完成后生成的xml文件 正样本1200个 负样本2400个-Xml file sample training and after training is completed generated negative samples positive samples 1200 2400
Licenseplaterecognitionprogram
- 此程序为Matlab编写的车牌识别程序，功能强大，充分利用图像处理强大的功能，能识别车牌上的数学和字母，值得学习。-This program for Matlab license plate recognition, powerful function, make full use of the powerful image processing function, math and can identify letters, worth learning.
DigitalImageProcessing
- 数字图象处理，平移，反转，灰度变化，频域滤波-Digital image processing, translation, reverse, gray change, frequency domain filtering