基于openCV实现人脸检测

openCV的人脸识别主要通过Haar分类器实现，当然，这是在已有训练数据的基础上。openCV安装在 opencv/opencv/sources/data/haarcascades_cuda（或haarcascades）中存在预先训练好的物体检测器（xml格式），包括正脸、侧脸、眼睛、微笑、上半身、下半身、全身等。

openCV的的Haar分类器是一个监督分类器，首先对图像进行直方图均衡化并归一化到同样大小，然后标记里面是否包含要监测的物体。它首先由Paul Viola和Michael Jones设计，称为Viola Jones检测器。Viola Jones分类器在级联的每个节点中使用AdaBoost来学习一个高检测率低拒绝率的多层树分类器。它使用了以下一些新的特征：

1. 使用类Haar输入特征：对矩形图像区域的和或者差进行阈值化。 
2. 积分图像技术加速了矩形区域的45°旋转的值的计算，用来加速类Haar输入特征的计算。
3. 使用统计boosting来创建两类问题（人脸和非人脸）的分类器节点（高通过率，低拒绝率）
4. 把弱分类器节点组成筛选式级联。即，第一组分类器最优，能通过包含物体的图像区域，同时允许一些不包含物体通过的图像通过；第二组分

类器次优分类器，也是有较低的拒绝率；以此类推。也就是说，对于每个boosting分类器，只要有人脸都能检测到，同时拒绝一小部分非人脸，并将其传给下一个分类器，是为低拒绝率。以此类推，最后一个分类器将几乎所有的非人脸都拒绝掉，只剩下人脸区域。只要图像区域通过了整个级联，则认为里面有物体。

此技术虽然适用于人脸检测，但不限于人脸检测，还可用于其他物体的检测，如汽车、飞机等的正面、侧面、后面检测。在检测时，先导入训练好的参数文件，其中haarcascade_frontalface_alt2.xml对正面脸的识别效果较好haarcascade_profileface.xml对侧脸的检测效果较好。当然，如果要达到更高的分类精度，可以收集更多的数据进行训练，这是后话。

以下代码基本实现了正脸、眼睛、微笑、侧脸的识别，若要添加其他功能，可以自行调整。

// faceDetector.h 
// This is just the face, eye, smile, profile detector from OpenCV's samples/c directory 
// 
 
 
#include "cv.h" 
#include "highgui.h" 
 
#include  
#include  
#include  
#include  
#include  
#include  
#include  
#include  
#include  
#include  
using namespace std; 
 
 
static CvMemStorage* storage = 0; 
static CvHaarClassifierCascade* cascade = 0; 
static CvHaarClassifierCascade* nested_cascade = 0; 
static CvHaarClassifierCascade* smile_cascade = 0; 
static CvHaarClassifierCascade* profile = 0; 
int use_nested_cascade = 0; 
 
void detect_and_draw( IplImage* image ); 
 
 
 
const char* cascade_name = 
  "../faceDetect/haarcascade_frontalface_alt2.xml"; 
const char* nested_cascade_name = 
  "../faceDetect/haarcascade_eye_tree_eyeglasses.xml"; 
const char* smile_cascade_name =  
  "../faceDetect/haarcascade_smile.xml"; 
const char* profile_name =  
  "../faceDetect/haarcascade_profileface.xml"; 
double scale = 1; 
 
int faceDetector(const char* imageName, int nNested, int nSmile, int nProfile) 
{ 
  CvCapture* capture = 0; 
  IplImage *frame, *frame_copy = 0; 
  IplImage *image = 0; 
  const char* scale_opt = "--scale="; 
  int scale_opt_len = (int)strlen(scale_opt); 
  const char* cascade_opt = "--cascade="; 
  int cascade_opt_len = (int)strlen(cascade_opt); 
  const char* nested_cascade_opt = "--nested-cascade"; 
  int nested_cascade_opt_len = (int)strlen(nested_cascade_opt); 
  const char* smile_cascade_opt = "--smile-cascade"; 
  int smile_cascade_opt_len = (int)strlen(smile_cascade_opt); 
  const char* profile_opt = "--profile"; 
  int profile_opt_len = (int)strlen(profile_opt); 
  int i; 
  const char* input_name = 0; 
 
 
  int opt_num = 7; 
  char** opts = new char*[7]; 
  opts[0] = "compile_opencv.exe"; 
  opts[1] = "--scale=1"; 
  opts[2] = "--cascade=1"; 
  if (nNested == 1) 
    opts[3] = "--nested-cascade=1"; 
  else 
    opts[3] = "--nested-cascade=0"; 
  if (nSmile == 1) 
    opts[4] = "--smile-cascade=1"; 
  else 
    opts[4] = "--smile-cascade=0"; 
  if (nProfile == 1) 
    opts[5] = "--profile=1"; 
  else 
    opts[5] = "--profile=0"; 
  opts[6] = (char*)imageName; 
   
 
 
  for( i = 1; i < opt_num; i++ ) 
  { 
    if( strncmp( opts[i], cascade_opt, cascade_opt_len) == 0) 
    { 
      cout<<"cascade: "<n" 
    "  [filename|camera_index]n" ); 
    return -1; 
  } 
  storage = cvCreateMemStorage(0); 
   
  if( !input_name || (isdigit(input_name[0]) && input_name[1] == '') ) 
    capture = cvCaptureFromCAM( !input_name ? 0 : input_name[0] - '0' ); 
  else if( input_name ) 
  { 
    image = cvLoadImage( input_name, 1 ); 
    if( !image ) 
      capture = cvCaptureFromAVI( input_name ); 
  } 
  else 
    image = cvLoadImage( "../lena.jpg", 1 ); 
 
  cvNamedWindow( "result", 1 ); 
 
  if( capture ) 
  { 
    for(;;) 
    { 
      if( !cvGrabframe( capture )) 
 break; 
      frame = cvRetrieveframe( capture ); 
      if( !frame ) 
 break; 
      if( !frame_copy ) 
 frame_copy = cvCreateImage( cvSize(frame->width,frame->height), 
 IPL_DEPTH_8U, frame->nChannels ); 
      if( frame->origin == IPL_ORIGIN_TL ) 
 cvCopy( frame, frame_copy, 0 ); 
      else 
 cvFlip( frame, frame_copy, 0 ); 

      detect_and_draw( frame_copy ); 
 
      if( cvWaitKey( 10 ) >= 0 ) 
 goto _cleanup_; 
    } 
 
    cvWaitKey(0); 
_cleanup_: 
    cvReleaseImage( &frame_copy ); 
    cvReleaseCapture( &capture ); 
  } 
  else 
  { 
    if( image ) 
    { 
      detect_and_draw( image ); 
      cvWaitKey(0); 
      cvReleaseImage( &image ); 
    } 
    else if( input_name ) 
    { 
       
      FILE* f = fopen( input_name, "rt" ); 
      if( f ) 
      { 
 char buf[1000+1]; 
 while( fgets( buf, 1000, f ) ) 
 { 
   int len = (int)strlen(buf), c; 
   while( len > 0 && isspace(buf[len-1]) ) 
     len--; 
   buf[len] = ''; 
   printf( "file %sn", buf );  
   image = cvLoadImage( buf, 1 ); 
   if( image ) 
   { 
     detect_and_draw( image ); 
     c = cvWaitKey(0); 
     if( c == 27 || c == 'q' || c == 'Q' ) 
break; 
     cvReleaseImage( &image ); 
   } 
 } 
 fclose(f); 
      } 
    } 
  } 
   
  cvDestroyWindow("result"); 
 
  return 0; 
} 
 
void detect_and_draw( IplImage* img ) 
{ 
  static CvScalar colors[] =  
  { 
    {{0,0,255}}, 
    {{0,128,255}}, 
    {{0,255,255}}, 
    {{0,255,0}}, 
    {{255,128,0}}, 
    {{255,255,0}}, 
    {{255,0,0}}, 
    {{255,0,255}} 
  }; 
 
  IplImage *gray, *small_img; 
  int i, j; 
 
  gray = cvCreateImage( cvSize(img->width,img->height), 8, 1 ); 
  small_img = cvCreateImage( cvSize( cvRound (img->width/scale), 
      cvRound (img->height/scale)), 8, 1 ); 
 
  cvCvtColor( img, gray, CV_BGR2GRAY ); 
  cvResize( gray, small_img, CV_INTER_LINEAR ); 
  cvEqualizeHist( small_img, small_img ); 
  cvClearMemStorage( storage ); 
 
  if( cascade ) 
  { 
    double t = (double)cvGetTickCount(); 
    CvSeq* faces = cvHaarDetectObjects( small_img, cascade, storage, 
 1.1, 2, 0 
 //|CV_HAAR_FIND_BIGGEST_OBJECT 
 //|CV_HAAR_DO_ROUGH_SEARCH 
 |CV_HAAR_DO_CANNY_PRUNING 
 //|CV_HAAR_SCALE_IMAGE 
 , 
 cvSize(30, 30) ); 
    t = (double)cvGetTickCount() - t; 
    printf( "faces detection time = %gmsn", t/((double)cvGetTickFrequency()*1000.) ); 
    for( i = 0; i < (faces ? faces->total : 0); i++ ) 
    { 
      CvRect* r = (CvRect*)cvGetSeqElem( faces, i ); 
      CvMat small_img_roi; 
      CvSeq* nested_objects; 
      CvSeq* smile_objects; 
      CvPoint center; 
      CvScalar color = colors[i%8]; 
      int radius; 
      center.x = cvRound((r->x + r->width*0.5)*scale); 
      center.y = cvRound((r->y + r->height*0.5)*scale); 
      radius = cvRound((r->width + r->height)*0.25*scale); 
      cvCircle( img, center, radius, color, 3, 8, 0 ); 
 
      //eye 
      if( nested_cascade != 0) 
      { 
 cvGetSubRect( small_img, &small_img_roi, *r ); 
 nested_objects = cvHaarDetectObjects( &small_img_roi, nested_cascade, storage, 
   1.1, 2, 0 
   //|CV_HAAR_FIND_BIGGEST_OBJECT 
   //|CV_HAAR_DO_ROUGH_SEARCH 
   //|CV_HAAR_DO_CANNY_PRUNING 
   //|CV_HAAR_SCALE_IMAGE 
   , 
   cvSize(0, 0) ); 
 for( j = 0; j < (nested_objects ? nested_objects->total : 0); j++ ) 
 { 
   CvRect* nr = (CvRect*)cvGetSeqElem( nested_objects, j ); 
   center.x = cvRound((r->x + nr->x + nr->width*0.5)*scale); 
   center.y = cvRound((r->y + nr->y + nr->height*0.5)*scale); 
   radius = cvRound((nr->width + nr->height)*0.25*scale); 
   cvCircle( img, center, radius, color, 3, 8, 0 ); 
 } 
      } 
      //smile 
      if (smile_cascade != 0) 
      { 
 cvGetSubRect( small_img, &small_img_roi, *r ); 
 smile_objects = cvHaarDetectObjects( &small_img_roi, smile_cascade, storage, 
   1.1, 2, 0 
   //|CV_HAAR_FIND_BIGGEST_OBJECT 
   //|CV_HAAR_DO_ROUGH_SEARCH 
   //|CV_HAAR_DO_CANNY_PRUNING 
   //|CV_HAAR_SCALE_IMAGE 
   , 
   cvSize(0, 0) ); 
 for( j = 0; j < (smile_objects ? smile_objects->total : 0); j++ ) 
 { 
   CvRect* nr = (CvRect*)cvGetSeqElem( smile_objects, j ); 
   center.x = cvRound((r->x + nr->x + nr->width*0.5)*scale); 
   center.y = cvRound((r->y + nr->y + nr->height*0.5)*scale); 
   radius = cvRound((nr->width + nr->height)*0.25*scale); 
   cvCircle( img, center, radius, color, 3, 8, 0 ); 
 } 
      } 
    } 
  } 
 
  if( profile ) 
  { 
    double t = (double)cvGetTickCount(); 
    CvSeq* faces = cvHaarDetectObjects( small_img, profile, storage, 
      1.1, 2, 0 
      //|CV_HAAR_FIND_BIGGEST_OBJECT 
      //|CV_HAAR_DO_ROUGH_SEARCH 
      |CV_HAAR_DO_CANNY_PRUNING 
      //|CV_HAAR_SCALE_IMAGE 
      , 
      cvSize(30, 30) ); 
    t = (double)cvGetTickCount() - t; 
    printf( "profile faces detection time = %gmsn", t/((double)cvGetTickFrequency()*1000.) ); 
    for( i = 0; i < (faces ? faces->total : 0); i++ ) 
    { 
      CvRect* r = (CvRect*)cvGetSeqElem( faces, i ); 
      CvMat small_img_roi; 
      CvSeq* nested_objects; 
      CvSeq* smile_objects; 
      CvPoint center; 
      CvScalar color = colors[(7-i)%8]; 
      int radius; 
      center.x = cvRound((r->x + r->width*0.5)*scale); 
      center.y = cvRound((r->y + r->height*0.5)*scale); 
      radius = cvRound((r->width + r->height)*0.25*scale); 
      cvCircle( img, center, radius, color, 3, 8, 0 ); 
 
      //eye 
      if( nested_cascade != 0) 
      { 
 cvGetSubRect( small_img, &small_img_roi, *r ); 
 nested_objects = cvHaarDetectObjects( &small_img_roi, nested_cascade, storage, 
   1.1, 2, 0 
   //|CV_HAAR_FIND_BIGGEST_OBJECT 
   //|CV_HAAR_DO_ROUGH_SEARCH 
   //|CV_HAAR_DO_CANNY_PRUNING 
   //|CV_HAAR_SCALE_IMAGE 
   , 
   cvSize(0, 0) ); 
 for( j = 0; j < (nested_objects ? nested_objects->total : 0); j++ ) 
 { 
   CvRect* nr = (CvRect*)cvGetSeqElem( nested_objects, j ); 
   center.x = cvRound((r->x + nr->x + nr->width*0.5)*scale); 
   center.y = cvRound((r->y + nr->y + nr->height*0.5)*scale); 
   radius = cvRound((nr->width + nr->height)*0.25*scale); 
   cvCircle( img, center, radius, color, 3, 8, 0 ); 
 } 
      } 
      //smile 
      if (smile_cascade != 0) 
      { 
 cvGetSubRect( small_img, &small_img_roi, *r ); 
 smile_objects = cvHaarDetectObjects( &small_img_roi, smile_cascade, storage, 
   1.1, 2, 0 
   //|CV_HAAR_FIND_BIGGEST_OBJECT 
   //|CV_HAAR_DO_ROUGH_SEARCH 
   //|CV_HAAR_DO_CANNY_PRUNING 
   //|CV_HAAR_SCALE_IMAGE 
   , 
   cvSize(0, 0) ); 
 for( j = 0; j < (smile_objects ? smile_objects->total : 0); j++ ) 
 { 
   CvRect* nr = (CvRect*)cvGetSeqElem( smile_objects, j ); 
   center.x = cvRound((r->x + nr->x + nr->width*0.5)*scale); 
   center.y = cvRound((r->y + nr->y + nr->height*0.5)*scale); 
   radius = cvRound((nr->width + nr->height)*0.25*scale); 
   cvCircle( img, center, radius, color, 3, 8, 0 ); 
 } 
      } 
    } 
  } 
 
  cvShowImage( "result", img ); 
  cvReleaseImage( &gray ); 
  cvReleaseImage( &small_img ); 
} 

//main.cpp 
//openCV配置 
//附加包含目录: include, include/opencv, include/opencv2 
//附加库目录: lib  
//附加依赖项: debug:--> opencv_calib3d243d.lib;...; 
//     release:--> opencv_calib3d243.lib;...; 
 
#include 
#include  
 
#include "CV2_compile.h" 
#include "CV_compile.h" 
 
#include "face_detector.h" 
 
using namespace cv; 
using namespace std; 
 
int main(int argc, char** argv) 
{ 
  const char* imagename = "../lena.jpg"; 
  faceDetector(imagename,1,0,0); 
 
  return 0; 
} 

调整主函数中faceDetect(const char* imageName, int nNested, int nSmile, int nProfile)函数中的参数，分别表示图像文件名，是否检测眼睛，是否检测微笑，是否检测侧脸。以检测正脸、眼睛为例：

再来看一张合影。

========华丽丽的分割线==========

如果对分类器的参数不满意，或者说想识别其他的物体例如车、人、飞机、苹果等等等等，只需要选择适当的样本训练，获取该物体的各个方面的参数，训练过程可以通过openCV的haartraining实现（参考haartraining参考文档，opencv/apps/traincascade），主要包括个步骤：

1. 收集打算学习的物体数据集（如正面人脸图，侧面汽车图等， 1000~10000个正样本为宜），把它们存储在一个或多个目录下面。
2. 使用createsamples来建立正样本的向量输出文件，通过这个文件可以重复训练过程，使用同一个向量输出文件尝试各种参数。
3. 获取负样本，即不包含该物体的图像。
4. 训练。命令行实现。

 以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持考高分网。