Feature Detection and Description & OpenCV 2.4.10.0 documentation
Navigation
Feature Detection and Description
An example explaining keypoint detection and description can be found at opencv_source_code/samples/cpp/descriptor_extractor_matcher.cpp
Detects corners using the FAST algorithm
C++: void FAST(InputArray image, vector&KeyPoint&& keypoints, int threshold, bool nonmaxSuppression=true )
C++: void FASTX(InputArray image, vector&KeyPoint&& keypoints, int threshold, bool nonmaxSuppression, int type)
Parameters:
image – grayscale image where keypoints (corners) are detected.
keypoints – keypoints detected on the image.
threshold – threshold on difference between intensity of the central pixel and pixels of a circle around this pixel.
nonmaxSuppression – if true, non-maximum suppression is applied to detected corners (keypoints).
type – one of the three neighborhoods as defined in the paper: FastFeatureDetector::TYPE_9_16, FastFeatureDetector::TYPE_7_12, FastFeatureDetector::TYPE_5_8
Detects corners using the FAST algorithm by .
Rosten. Machine Learning for High-speed Corner Detection, 2006.
class MSER : public FeatureDetector
Maximally stable extremal region extractor.
class MSER : public CvMSERParams
// default constructor
// constructor that initializes all the algorithm parameters
MSER( int _delta, int _min_area, int _max_area,
float _max_variation, float _min_diversity,
int _max_evolution, double _area_threshold,
double _min_margin, int _edge_blur_size );
// runs the extractor on returns the MSERs,
// each encoded as a contour (vector&Point&, see findContours)
// the optional mask marks the area where MSERs are searched for
void operator()( const Mat& image, vector&vector&Point& && msers, const Mat& mask ) const;
The class encapsulates all the parameters of the MSER extraction algorithm (see
). Also see
for useful comments and parameters description.
(Python) A complete example showing the use of the MSER detector can be found at opencv_source_code/samples/python2/mser.py
class ORB : public Feature2D
Class implementing the ORB (oriented BRIEF) keypoint detector and descriptor extractor, described in . The algorithm uses FAST in pyramids to detect stable keypoints, selects the strongest features using FAST or Harris response, finds their orientation using first-order moments and computes the descriptors using BRIEF (where the coordinates of random point pairs (or k-tuples) are rotated according to the measured orientation).
Ethan Rublee, Vincent Rabaud, Kurt Konolige, Gary R. Bradski: ORB: An efficient alternative to SIFT or SURF. ICCV -2571.
The ORB constructor
ORB::ORB(int nfeatures=500, float scaleFactor=1.2f, int nlevels=8, int edgeThreshold=31, int firstLevel=0, int WTA_K=2, int scoreType=ORB::HARRIS_SCORE, int patchSize=31)
Parameters:
nfeatures – The maximum number of features to retain.
scaleFactor – Pyramid decimation ratio, greater than 1. scaleFactor==2 means the classical pyramid, where each next level has 4x less pixels than the previous, but such a big scale factor will degrade feature matching scores dramatically. On the other hand, too close to 1 scale factor will mean that to cover certain scale range you will need more pyramid levels and so the speed will suffer.
nlevels – The number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels).
edgeThreshold – This is size of the border where the features are not detected. It should roughly match the patchSize parameter.
firstLevel – It should be 0 in the current implementation.
WTA_K – The number of points that produce each element of the oriented BRIEF descriptor. The default value 2 means the BRIEF where we take a random point pair and compare their brightnesses, so we get 0/1 response. Other possible values are 3 and 4. For example, 3 means that we take 3 random points (of course, those point coordinates are random, but they are generated from the pre-defined seed, so each element of BRIEF descriptor is computed deterministically from the pixel rectangle), find point of maximum brightness and output index of the winner (0, 1 or 2). Such output will occupy 2 bits, and therefore it will need a special variant of Hamming distance, denoted as NORM_HAMMING2 (2 bits per bin).
When WTA_K=4, we take 4 random points to compute each bin (that will also occupy 2 bits with possible values 0, 1, 2 or 3).
scoreType – The default HARRIS_SCORE means that Harris algorithm is used to rank features (the score is written to KeyPoint::score and is used to retain best nfeatures features); FAST_SCORE is alternative value of the parameter that produces slightly less stable keypoints, but it is a little faster to compute.
patchSize – size of the patch used by the oriented BRIEF descriptor. Of course, on smaller pyramid layers the perceived image area covered by a feature will be larger.
ORB::operator()
Finds keypoints in an image and computes their descriptors
C++: void ORB::operator()(InputArray image, InputArray mask, vector&KeyPoint&& keypoints, OutputArray descriptors, bool useProvidedKeypoints=false ) const
Parameters:
image – The input 8-bit grayscale image.
mask – The operation mask.
keypoints – The output vector of keypoints.
descriptors – The output descriptors. Pass cv::noArray() if you do not need it.
useProvidedKeypoints – If it is true, then the method will use the provided vector of keypoints instead of detecting them.
class BRISK : public Feature2D
Class implementing the BRISK keypoint detector and descriptor extractor, described in .
Stefan Leutenegger, Margarita Chli and Roland Siegwart: BRISK: Binary Robust Invariant Scalable Keypoints. ICCV -2555.
BRISK::BRISK
The BRISK constructor
BRISK::BRISK(int thresh=30, int octaves=3, float patternScale=1.0f)
Parameters:
thresh – FAST/AGAST detection threshold score.
octaves – detection octaves. Use 0 to do single scale.
patternScale – apply this scale to the pattern used for sampling the neighbourhood of a keypoint.
BRISK::BRISK
The BRISK constructor for a custom pattern
BRISK::BRISK(std::vector&float&& radiusList, std::vector&int&& numberList, float dMax=5.85f, float dMin=8.2f, std::vector&int& indexChange=std::vector&int&())
Parameters:
radiusList – defines the radii (in pixels) where the samples around a keypoint are taken (for keypoint scale 1).
numberList – defines the number of sampling points on the sampling circle. Must be the same size as radiusList..
dMax – threshold for the short pairings used for descriptor formation (in pixels for keypoint scale 1).
dMin – threshold for the long pairings used for orientation determination (in pixels for keypoint scale 1).
indexChanges – index remapping of the bits.
BRISK::operator()
Finds keypoints in an image and computes their descriptors
C++: void BRISK::operator()(InputArray image, InputArray mask, vector&KeyPoint&& keypoints, OutputArray descriptors, bool useProvidedKeypoints=false ) const
Parameters:
image – The input 8-bit grayscale image.
mask – The operation mask.
keypoints – The output vector of keypoints.
descriptors – The output descriptors. Pass cv::noArray() if you do not need it.
useProvidedKeypoints – If it is true, then the method will use the provided vector of keypoints instead of detecting them.
class FREAK : public DescriptorExtractor
Class implementing the FREAK (Fast Retina Keypoint) keypoint descriptor, described in . The algorithm propose a novel keypoint descriptor inspired by the human visual system and more precisely the retina, coined Fast Retina Key- point (FREAK). A cascade of binary strings is computed by efficiently comparing image intensities over a retinal sampling pattern. FREAKs are in general faster to compute with lower memory load and also more robust than SIFT, SURF or BRISK. They are competitive alternatives to existing keypoints in particular for embedded applications.
Alahi, R. Ortiz, and P. Vandergheynst. FREAK: Fast Retina Keypoint. In IEEE Conference on Computer Vision and Pattern Recognition, 2012. CVPR 2012 Open Source Award Winner.
An example on how to use the FREAK descriptor can be found at opencv_source_code/samples/cpp/freak_demo.cpp
FREAK::FREAK
The FREAK constructor
FREAK::FREAK(bool orientationNormalized=true, bool scaleNormalized=true, float patternScale=22.0f, int nOctaves=4, const vector&int&& selectedPairs=vector&int&() )
Parameters:
orientationNormalized – Enable orientation normalization.
scaleNormalized – Enable scale normalization.
patternScale – Scaling of the description pattern.
nOctaves – Number of octaves covered by the detected keypoints.
selectedPairs – (Optional) user defined selected pairs indexes,
FREAK::selectPairs
Select the 512 best description pair indexes from an input (grayscale) image set. FREAK is available with a set of pairs learned off-line. Researchers can run a training process to learn their own set of pair. For more details read section 4.2 in: A. Alahi, R. Ortiz, and P. Vandergheynst. FREAK: Fast Retina Keypoint. In IEEE Conference on Computer Vision and Pattern Recognition, 2012.
We notice that for keypoint matching applications, image content has little effect on the selected pairs unless very specific what does matter is the detector type (blobs, corners,...) and the options used (scale/rotation invariance,...). Reduce corrThresh if not enough pairs are selected (43 points –& 903 possible pairs)
C++: vector&int& FREAK::selectPairs(const vector&Mat&& images, vector&vector&KeyPoint&&& keypoints, const double corrThresh=0.7, bool verbose=true)
Parameters:
images – Grayscale image input set.
keypoints – Set of detected keypoints
corrThresh – Correlation threshold.
verbose – Prints pair selection informations.
Help and Feedback
You did not find what you were looking for?
Ask a question on the .
If you think something is missing or wrong in the documentation,
please file a .
Previous topic
Next topic
NavigationOpenCV学习笔记（九）——2维特征Feature2D
我的图书馆
OpenCV学习笔记（九）——2维特征Feature2D
基于特征点的图像匹配是图像处理中经常会遇到的问题，手动选取特征点太麻烦了。比较经典常用的特征点自动提取的办法有Harris特征、SIFT特征、SURF特征。先介绍利用SURF特征的特征描述办法，其操作封装在类SurfFeatureDetector中，利用类内的detect函数可以检测出SURF特征的关键点，保存在vector容器中。第二部利用SurfDescriptorExtractor类进行特征向量的相关计算。将之前的vector变量变成向量矩阵形式保存在Mat中。最后强行匹配两幅图像的特征向量，利用了类BruteForceMatcher中的函数match。代码如下：当然，进行强匹配的效果不够理想，这里再介绍一种FLANN特征匹配算法。前两步与上述代码相同，第三步利用FlannBasedMatcher类进行特征匹配，并只保留好的特征匹配点，代码如下：在FLANN特征匹配的基础上，还可以进一步利用Homography映射找出已知物体。具体来说就是利用findHomography函数利用匹配的关键点找出相应的变换，再利用perspectiveTransform函数映射点群。具体代码如下：然后再看一下Harris特征检测，在计算机视觉中，通常需要找出两帧图像的匹配点，如果能找到两幅图像如何相关，就能提取出两幅图像的信息。我们说的特征的最大特点就是它具有唯一可识别这一特点，图像特征的类型通常指边界、角点（兴趣点）、斑点（兴趣区域）。角点就是图像的一个局部特征，应用广泛。harris角点检测是一种直接基于灰度图像的角点提取算法，稳定性高，尤其对L型角点检测精度高，但由于采用了高斯滤波，运算速度相对较慢，角点信息有丢失和位置偏移的现象，而且角点提取有聚簇现象。具体实现就是使用函数cornerHarris实现。除了利用Harris进行角点检测，还可以利用Shi-Tomasi方法进行角点检测。使用函数goodFeaturesToTrack对角点进行检测，效果也不错。也可以自己制作角点检测的函数，需要用到cornerMinEigenVal函数和minMaxLoc函数，最后的特征点选取，判断条件要根据自己的情况编辑。如果对特征点，角点的精度要求更高，可以用cornerSubPix函数将角点定位到子像素。
TA的最新馆藏[转]&[转]&[转]&[转]&[转]&[转]&您所在位置： &
&nbsp&&nbsp&nbsp&&nbsp
opencv2.4.x简要介绍.docx 8页
本文档一共被下载：
次 ,您可全文免费在线阅读后下载本文档。
下载提示
1.本站不保证该用户上传的文档完整性，不预览、不比对内容而直接下载产生的反悔问题本站不予受理。
2.该文档所得收入(下载+内容+预览三)归上传者、原创者。
3.登录后可充值，立即自动返金币，充值渠道很便利
需要金币：100 &&
你可能关注的文档：
OpenCV2.4.x简要介绍罗海风目录1.OpenCV历史22.OpenCV简介23.OpenCV目录结构24.OpenCV算法模块34.1.【calib3d】34.2.【contrib】34.3.【core】34.4.【imgproc】34.5.【features2d】34.6.【flann】44.7.【gpu】44.8.【highgui】44.9.【legacy】44.10.【ml】44.11.【nonfree】44.12.【objdetect】44.13.【ocl】44.14.【photo】44.15.【stitching】44.16.【superres】54.17.【ts】54.18.【video】54.19.【Videostab】55.OpenCV主要数据结构56.OpenCV应用图例56.1图像阈值分割56.2分水岭算法56.3几何形态抽取66.4GraphCut分割66.5特征点匹配66.6图像拼接66.7特征点跟踪76.8kinect支持下的3D重建77.最新进展88.小结81.OpenCV历史1999年1月，CVL项目启动。主要目标是人机界面，能被UI调用的实时计算机视觉库，为Intel处理器做了特定优化。2000年6月，第一个开源版本OpenCValpha3发布。2000年12月，针对linux平台的OpenCVbeta1发布。2006年，支持MacOS的OpenCV1.0发布。2009年9月，OpenCV1.2（beta2.0）发布。日，Version2.0发布。日，OpenCV2.2发布。2011年8月，OpenCV2.3发布。日，发布OpenCV2.4.截至至日，发布了最新版本的OpenCV2.4.9.2.OpenCV简介OpenCV采用C及C++语言编写，可以在windows,linux,macOSX系统上面运行。该库的所有代码都经过优化，计算效率较高，因为，它更专注于设计成为一种用于实时系统的开源库。OpenCV采用C语言进行优化，而且，在多核机器上面，其运行速度会更快。它的一个目标是提供友好的机器视觉接口函数，从而使得复杂的机器视觉产品可以加速面世。OpenCV包含了横跨工业产品检测、医学图像处理、安防、智能交通、体感游戏、用户界面、摄像头标定、三维成像、机器视觉、机器学习等领域的超过500个接口函数，典型应用案例有：谷歌地图，谷歌街景，谷歌地球，斯坦福大学stanley机器人项目等，百度图像搜索等。OpenCV使用类BSDlicense，对非商业应用和商业应用都是免费（FREE）的。3.OpenCV目录结构OpenCVwindows版本，版本号2.4.8，解压安装完成后在系统中的目录结构如下所示：opencv|--build编译好的库文件，头文件及文档||--doc相关文档||--include库文件所需的头文件集合||--javaopencv的java版本，编译后的库文件||--pythonopencv的python版本，编译后的库文件||--x6464位系统下使用的编译后库文件||--x8632位系统下使用的编译后库文件||--sources源代码文件集合||--3rdparty第三方工具集合||--appHaar分类器的训练代码||--cmake编译配置文件集合||--data已经训练好的分类器||--doc文档集合||--include头文件集合||--modules各种opencv算法模块文件，具体介绍见下节“4.OpenCV算法模块”||--platforms进行其他平台交叉编译所需要的工具链，包括android/ios/linux/winrt等||--samples演示样例源码集合4.OpenCV算法模块OpenCV组件架构中所有具体模块如下：4.1.【calib3d】——这个模块主要是相机校准和三维重建相关的内容。基本的多视角几何算法，单个立体摄像头标定，物体姿态估计，立体相似性算法，3D信息的重建等等。4.2.【contrib】——Contributed/ExperimentalStuf的缩写，该模块包含了一些最近添加的不太稳定的可选功能，不用去多管。2.4.8里的这个模块有新型人脸识别，立体匹配，人工视网膜模型等技术。4.3.【core】——核心功能模块，包含如下内容：OpenCV基本数据结构动态数据结构绘图函数数组操作相关函数辅助功能与系统函数和宏与OpenGL的互操作4.4.【imgproc】——图像处理模块，这个模块包含了如下内容：线性和非线性的图像滤波图像的几何变换其它（Miscellaneous）图像转换直方图相关结构分析和形状描述运动分析和对象跟踪特征检测目标检测等内容4.5
正在加载中，请稍后...opencv（24）
FaceRecognizer::onInit时直接创建了描述符对象：
descriptor_detector_ = new cv::GridAdaptedFeatureDetector();
descriptor_extractor_ = new cv::SurfDescriptorE
bowExtractor_ = new cv::BOWImgDescriptorExtractor();
训练过程，首先根据样本图像生成提取描述符。然后使用svm分类器。
1.cvtColor 将原始图像转换为灰度图像。
2.归一化直方图。
3.检测灰度图像的关键点，生成关键点。descriptor_detector_-&detect
4.根据关键点，从灰度图像提取描述符。生成提取描述符。descriptor_extractor_-&compute
5.将生成的提取描述符作为人的描述符。如果模型中没有描述符则直接赋值，如果已有至少一个则匹配插入。
识别检测过程：根据输入图像生成提取描述符，然后使用SVM进行预测。
FeatureDetector
class FeatureDetector :
public Algorithm
Abstract base class for 2D image feature detectors.
class CV_EXPORTS FeatureDetector
virtual ~FeatureDetector();
void detect( const Mat& image, vector&KeyPoint&& keypoints,
const Mat& mask=Mat() ) const;
void detect( const vector&Mat&& images,
vector&vector&KeyPoint& && keypoints,
const vector&Mat&& masks=vector&Mat&() ) const;
virtual void read(const FileNode&);
virtual void write(FileStorage&) const;
static Ptr&FeatureDetector& create( const string& detectorType );
protected:
Parameters:detectorType
– Feature detector type.The following detector types are supported:&FAST& – &STAR& – &SIFT& –
(nonfree module)&SURF& –
(nonfree module)&ORB& – &BRISK& – &MSER& – &GFTT& – &HARRIS& –
with Harris detector enabled&Dense& – &SimpleBlob& – BOWImgDescriptorExtractor::compute&
参考知识库
* 以上用户言论只代表其个人观点，不代表CSDN网站的观点或立场
访问：99701次
积分：3081
积分：3081
排名：第9200名
原创：203篇
转载：58篇
评论：11条
(1)(2)(1)(8)(6)(2)(3)(1)(1)(13)(6)(7)(3)(1)(3)(7)(26)(29)(4)(10)(23)(7)(18)(12)(19)(22)(27)关于OpenCV3.0 beta 编译出现ORB那边的错误的解决_Linux编程_Linux公社-Linux系统门户网站
你好，游客
关于OpenCV3.0 beta 编译出现ORB那边的错误的解决
来源：Linux社区&
作者：xizero00
好久没碰opencv了，现在已经3.0 beta了。
今天编译遇到了error: cannot declare variable &orb& to be of abstract type &cv::ORB
原因是ORB这个类不能再这么调用了。
在opencv 根目录找到opencvroot/samples/gpu/performance/tests.cpp
修改成如下代码。
TEST(ORB){& & Mat src = imread(abspath("../data/aloeL.jpg"), IMREAD_GRAYSCALE);& & if (src.empty()) throw runtime_error("can't open ../data/aloeL.jpg");
& & //ORB orb(4000);& & Ptr&ORB& orb = ORB::create(f,8,31,0,2,ORB::HARRIS_SCORE,31,20);& & vector&KeyPoint&& & M& & & & orb-&detectAndCompute(src, Mat(), keypoints, descriptors);
& & //orb(src, Mat(), keypoints, descriptors);
& & CPU_ON;& & //orb(src, Mat(), keypoints, descriptors);& & orb-&detectAndCompute(src, Mat(), keypoints, descriptors);& & CPU_OFF;
& & cuda::ORB_CUDA d_& & cuda::GpuMat d_src(src);& & cuda::GpuMat d_& & cuda::GpuMat d_
& & d_orb(d_src, cuda::GpuMat(), d_keypoints, d_descriptors);
& & CUDA_ON;& & d_orb(d_src, cuda::GpuMat(), d_keypoints, d_descriptors);& & CUDA_OFF;}
这里说明原因，我查看了opencv3.0的feature2d.hpp代码发现
class CV_EXPORTS_W ORB : public Feature2D& {& public:& & & enum { kBytes = 32, HARRIS_SCORE=0, FAST_SCORE=1 };& & & & CV_WRAP static Ptr&ORB& create(int nfeatures=500, float scaleFactor=1.2f, int nlevels=8, int edgeThreshold=31,& & & & & int firstLevel=0, int WTA_K=2, int scoreType=ORB::HARRIS_SCORE, int patchSize=31, int fastThreshold=20);& & & CV_WRAP virtual void setMaxFeatures(int maxFeatures) = 0;& & & CV_WRAP virtual int getMaxFeatures() const = 0;& & & & CV_WRAP virtual void setScaleFactor(double scaleFactor) = 0;& & & CV_WRAP virtual double getScaleFactor() const = 0;& & & & CV_WRAP virtual void setNLevels(int nlevels) = 0;& & & CV_WRAP virtual int getNLevels() const = 0;& & & & CV_WRAP virtual void setEdgeThreshold(int edgeThreshold) = 0;& & & CV_WRAP virtual int getEdgeThreshold() const = 0;& & & & CV_WRAP virtual void setFirstLevel(int firstLevel) = 0;& & & CV_WRAP virtual int getFirstLevel() const = 0;& & & & CV_WRAP virtual void setWTA_K(int wta_k) = 0;& & & CV_WRAP virtual int getWTA_K() const = 0;& & & & CV_WRAP virtual void setScoreType(int scoreType) = 0;& & & CV_WRAP virtual int getScoreType() const = 0;& & & & CV_WRAP virtual void setPatchSize(int patchSize) = 0;& & & CV_WRAP virtual int getPatchSize() const = 0;& & & & CV_WRAP virtual void setFastThreshold(int fastThreshold) = 0;& & & CV_WRAP virtual int getFastThreshold() const = 0;& };&
没有构造函数，只有一个静态的create。
此外，检测函数也不能用原来的操作符重载的检测函数了。
class ORB_Impl : public ORB& {& public:& & & explicit ORB_Impl(int _nfeatures, float _scaleFactor, int _nlevels, int _edgeThreshold,& & & & & & &
int _firstLevel, int _WTA_K, int _scoreType, int _patchSize, int _fastThreshold) :& & & & & nfeatures(_nfeatures), scaleFactor(_scaleFactor), nlevels(_nlevels),& & & & & edgeThreshold(_edgeThreshold), firstLevel(_firstLevel), wta_k(_WTA_K),& & & & & scoreType(_scoreType), patchSize(_patchSize), fastThreshold(_fastThreshold)& & & {}& & & & void setMaxFeatures(int maxFeatures) { nfeatures = maxF }& & & int getMaxFeatures() const { }& & & & void setScaleFactor(double scaleFactor_) { scaleFactor = scaleFactor_; }& & & double getScaleFactor() const { return scaleF }& & & & void setNLevels(int nlevels_) { nlevels = nlevels_; }& & & int getNLevels() const { }& & & & void setEdgeThreshold(int edgeThreshold_) { edgeThreshold = edgeThreshold_; }& & & int getEdgeThreshold() const { return edgeT }& & & & void setFirstLevel(int firstLevel_) { firstLevel = firstLevel_; }& & & int getFirstLevel() const { return firstL }& & & & void setWTA_K(int wta_k_) { wta_k = wta_k_; }& & & int getWTA_K() const { return wta_k; }& & & & void setScoreType(int scoreType_) { scoreType = scoreType_; }& & & int getScoreType() const { return scoreT }& & & & void setPatchSize(int patchSize_) { patchSize = patchSize_; }& & & int getPatchSize() const { return patchS }& & & & void setFastThreshold(int fastThreshold_) { fastThreshold = fastThreshold_; }& & & int getFastThreshold() const { return fastT }& & & & // returns the descriptor size in bytes&
& & int descriptorSize()& & & // returns the descriptor type&
& & int descriptorType()& & & // returns the default norm type&
& & int defaultNorm()& & & & // Compute the ORB_Impl features and descriptors on an image&
& & &strong&void detectAndCompute( InputArray image, InputArray mask, std::vector&KeyPoint&& keypoints,& & & & & & & & & & &
OutputArray descriptors, bool useProvidedKeypoints=false );&/strong&& & protected:& & & && & & double scaleF& & && & & int edgeT& & & int firstL& & & int wta_k;& & & int scoreT& & & int patchS& & & int fastT& };& &
希望有人遇到这样的问题的时候，能够得到解答。
此外还有就是使用最新的cuda6.5的时候一定要在gui的cmake 中
将CUDA_ARCH_BIN 设置为2.0 2.1(2.0) 3.0 3.5
不要带1.1 .1.2 1.3等等之类的，因为cuda6.5不支持这些老显卡了。
--------------------------------------分割线 --------------------------------------
Linux下安装OpenCV2.4.1所需包
Ubuntu 12.04 安装 OpenCV2.4.2
下OpenCV无法读取视频文件
Ubuntu 12.04下安装OpenCV 2.4.5总结
Ubuntu 10.04中安装OpenCv2.1九步曲
基于QT和OpenCV的人脸识别系统
[翻译]Ubuntu 14.04, 13.10 下安装 OpenCV 2.4.9&
--------------------------------------分割线 --------------------------------------
OpenCV的详细介绍：OpenCV的下载地址：
本文永久更新链接地址：
相关资讯 & & &
& (12/27/:52)
& (09/08/:09)
& (12/31/:28)
& (12/15/:37)
& (09/08/:09)
　　　同意评论声明
　　　发表
尊重网上道德，遵守中华人民共和国的各项有关法律法规
承担一切因您的行为而直接或间接导致的民事或刑事法律责任
本站管理人员有权保留或删除其管辖留言中的任意内容
本站有权在网站内转载或引用您的评论
参与本评论即表明您已经阅读并接受上述条款