搜索资源列表
hog_extraction.rar
- 基于OPENCV的静止图像的HOG特征提取算法的全部程序,完全可用于各种图像的HOG特征提取,以进一步训练分类器进行行人检测,source code that apply to the pedestrian detection based on OPENCV.this document can help you extract HOG features from any type image which include human in it
hog
- HOG特征的实现方案,用于人脸识别,已经被opencv采用-the feature of HOG
HOG
- 基于HOG的行人检测,作者的源代码有错误,现代码已经进行了改变,并可以调试通-Histograms of Oriented Gradients for Human Detection, the writer s code has some errors, and I have correct the errors, and the code is right under C++ buidler
HumanDetect
- this file combines c++ and opencv,it can detect humanbody in a seris of images,the image can be a video file。It uses HOG operater to make the moving object is human。
PedestrianDetectionHoG_NET2005-2008_07_19
- 基于HOG的人体检测程序,使用VC2005 功能强大-HOG-based human detection procedures, the use of powerful VC2005
hog
- 鉴于目标的特征提取,一种采用HOG作为特征的行人检测方法-Histograms of Oriented Gradients for Human Detection
ImageRetrieval
- 毕业设计,基于内容的图像检索,支持的检索特征包括 sift,颜色直方图,灰度矩阵,HU不变矩,边缘方向直方图,检索方法使用K-means和K-D树两种,需要OPENCV支持,运行时请先选定一个文件夹来生成特征库,特征库用access数据库保存,只支持JPG文件-Graduate design, content-based image retrieval, search features, including support sift, color histogram, gray matrix,
OpenCV2.2_API_Specification
- 本文档包括了OpenCV2.2版(2010年12月推出,目前最新版)中所有API函数的说明,包括C、C++、Python中调用OpenCV的所有接口函数,是大家开发计算机视觉、图像处理、模式识别程序的好参考。OpenCV2.2提供了支持Visual Studio 2010的可执行版本,并且添加了HOG行人检测器,真是不可多得的好东西。-This document includes OpenCV2.2 edition (December 2010 launch, the latest versio
de
- 基于HOG和SVM的行人检测代码,需要配置opencv-HOG and SVM-based pedestrian detection code need to configure opencv
HOG-pedestrian-detection-OpenCV
- 利用hog特征向量进行行人检测opencv visual2010(入门)-Use hog feature vectors detect pedestrians opencv visual2010 (entry)
HOG
- 将这330个3780维的HOG特征当做测试样本,用支持向量机(SVM)分类器来判别出,这些窗口的HOG特征是否有行人,有行人的用矩形框标记起来。HOG行人特征及所对应的SVM分类器的参数,在opencv中已经训练好了,我们只需要得到HOG特征,然后调用SVM即可得到判别结果(The 330 Hera features of 3780 dimensions are used as test samples, and the support vector machine (SVM) classifi
svm
- 使用hog特征进行分类,采用opencv里的svm算法(By using the hog feature,we classfy the face images with svm algorithm.)