Description: 利用级联的Haar分类其寻找检测目标。核心函数cvHaarDetectObjects使用针对某目标物体的级联分类器在图像中找到包含目标物体的矩形区域,并将这些区域作为一系列的矩形框返回。-Haar cascade classification using its search for target detection. CvHaarDetectObjects core function for a target object using the cascade classifier found in the image of the rectangle that contains the object region, and these regions as a series of rectangular box to return. Platform: |
Size: 179200 |
Author:孔守斌 |
Hits:
Description: This program is the haar opencv face detector slightly modified for ease of use
There are command line options available to avoid the need to use the gui (see
facedetect.cpp for the command line option format
This program needs fltk installed. It can be downloaded online.
The standard facedetect.cpp works at one scale. Our facedetect pyarmids the
image up and down to allow processing at more scales. This can also be
achieved via the cvHaarDetectObjects function.
This program has only been tested with uncompressed avi files Platform: |
Size: 83968 |
Author:陈忠翔 |
Hits:
Description: 运用C++检测人眼,
2)用opencv中检测人脸、眼睛、嘴巴等都是用的CascadeClassifier分类器,具体使用时可以使用C的函数,也可以使用opencv中使用C++封装好的类。下面是它们检测目标时的函数形式(从opencv官网复制的)
C: CvSeq* cvHaarDetectObjects(const CvArr* image, CvHaarClassifierCascade* cascade, CvMemStorage* storage, double scale_factor=1.1, int min_neighbors=3, int flags=0, CvSize min_size=cvSize(0,0), CvSize max_size=cvSize(0,0) )
C++: void CascadeClassifier::detectMultiScale(const Mat& image, vector<Rect>& objects, double scaleFactor=1.1, int minNeighbors=3, int flags=0, Size minSize=Size(), Size maxSize=Size())
这两者最大的区别在于,用C封装的函数要自己手动分配内存,而用C++的形式则不用自己去分配内存,这就是很多同学在网上找到的代码有些要分配内存,有些又不用分配内存的原因。显然C++的形式更简洁,所以我下面的代码也是用的C++的函数。-
Detected with opencv face, eyes, mouth, etc. are used CascadeClassifier classification, you can use C functions specific use, you can use opencv use C++ classes packaged. Here is the form of the function when they detect target (copied the opencv official website) Platform: |
Size: 2655232 |
Author:刘卓 |
Hits: