基於openCV實現人臉檢測
阿新 • • 發佈：2019-01-03
openCV的人臉識別主要通過Haar分類器實現，當然，這是在已有訓練資料的基礎上。openCV安裝在 opencv/opencv/sources/data/haarcascades_cuda（或haarcascades）中存在預先訓練好的物體檢測器（xml格式），包括正臉、側臉、眼睛、微笑、上半身、下半身、全身等。
openCV的的Haar分類器是一個監督分類器，首先對影象進行直方圖均衡化並歸一化到同樣大小，然後標記裡面是否包含要監測的物體。它首先由Paul
Viola和Michael Jones設計，稱為Viola Jones檢測器。Viola Jones分類器在級聯的每個節點中使用AdaBoost來學習一個高檢測率低拒絕率的多層樹分類器。它使用了以下一些新的特徵 ：
1. 使用類Haar輸入特徵：對矩形影象區域的和或者差進行閾值化。
2. 積分影象技術加速了矩形區域的45°旋轉的值的計算，用來加速類Haar輸入特徵的計算。
3. 使用統計boosting來建立兩類問題（人臉和非人臉）的分類器節點（高通過率，低拒絕率）
4. 把弱分類器節點組成篩選式級聯。即，第一組分類器最優，能通過包含物體的影象區域，同時允許一些不包含物體通過的影象通過；第二組分類器次優分類器，也是有較低的拒絕率；以此類推。也就是說，對於每個boosting分類器，只要有人臉都能檢測到，同時拒絕一小部分非人臉，並將其傳給下一個分類器，是為低拒絕率。以此類推，最後一個分類器將幾乎所有的非人臉都拒絕掉，只剩下人臉區域。只要影象區域通過了整個級聯，則認為裡面有物體。
此技術雖然適用於人臉檢測，但不限於人臉檢測，還可用於其他物體的檢測，如汽車、飛機等的正面、側面、後面檢測。在檢測時，先匯入訓練好的引數檔案，其中haarcascade_frontalface_alt2.xml對正面臉的識別效果較好，haarcascade_profileface.xml對側臉的檢測效果較好。當然，如果要達到更高的分類精度，可以收集更多的資料進行訓練，這是後話。
以下程式碼基本實現了正臉、眼睛、微笑、側臉的識別，若要新增其他功能，可以自行調整。
// faceDetector.h // This is just the face, eye, smile, profile detector from OpenCV's samples/c directory // /* *************** License:************************** Jul. 18, 2016 Author: Liuph Right to use this code in any way you want without warranty, support or any guarantee of it working. OTHER OPENCV SITES: * The source code is on sourceforge at: http://sourceforge.net/projects/opencvlibrary/ * The OpenCV wiki page (As of Oct 1, 2008 this is down for changing over servers, but should come back): http://opencvlibrary.sourceforge.net/ * An active user group is at: http://tech.groups.yahoo.com/group/OpenCV/ * The minutes of weekly OpenCV development meetings are at: http://pr.willowgarage.com/wiki/OpenCV ************************************************** */ #include "cv.h" #include "highgui.h" #include <stdio.h> #include <stdlib.h> #include <string.h> #include <assert.h> #include <math.h> #include <float.h> #include <limits.h> #include <time.h> #include <ctype.h> #include <iostream> 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 ); /* The path that stores the trained parameter files. After openCv is installed, the file path is "opencv/opencv/sources/data/haarcascades_cuda" or "opencv/opencv/sources/data/haarcascades" */ 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: "<<cascade_name<<endl; } else if( strncmp( opts[i], nested_cascade_opt, nested_cascade_opt_len ) == 0) { if( opts[i][nested_cascade_opt_len + 1] == '1') { cout<<"nested: "<<nested_cascade_name<<endl; nested_cascade = (CvHaarClassifierCascade*)cvLoad( nested_cascade_name, 0, 0, 0 ); } if( !nested_cascade ) fprintf( stderr, "WARNING: Could not load classifier cascade for nested objects\n" ); } else if( strncmp( opts[i], scale_opt, scale_opt_len ) == 0 ) { cout<< "scale: "<< scale<<endl; if( !sscanf( opts[i] + scale_opt_len, "%lf", &scale ) || scale < 1 ) scale = 1; } else if (strncmp( opts[i], smile_cascade_opt, smile_cascade_opt_len ) == 0) { if( opts[i][smile_cascade_opt_len + 1] == '1') { cout<<"smile: "<<smile_cascade_name<<endl; smile_cascade = (CvHaarClassifierCascade*)cvLoad( smile_cascade_name, 0, 0, 0 ); } if( !smile_cascade ) fprintf( stderr, "WARNING: Could not load classifier cascade for smile objects\n" ); } else if (strncmp( opts[i], profile_opt, profile_opt_len ) == 0) { if( opts[i][profile_opt_len + 1] == '1') { cout<<"profile: "<<profile_name<<endl; profile = (CvHaarClassifierCascade*)cvLoad( profile_name, 0, 0, 0 ); } if( !profile ) fprintf( stderr, "WARNING: Could not load classifier cascade for profile objects\n" ); } else if( opts[i][0] == '-' ) { fprintf( stderr, "WARNING: Unknown option %s\n", opts[i] ); } else { input_name = imageName; printf("input_name: %s\n", imageName); } } cascade = (CvHaarClassifierCascade*)cvLoad( cascade_name, 0, 0, 0 ); if( !cascade ) { fprintf( stderr, "ERROR: Could not load classifier cascade\n" ); fprintf( stderr, "Usage: facedetect [--cascade=\"<cascade_path>\"]\n" " [--nested-cascade[=\"nested_cascade_path\"]]\n" " [--scale[=<image scale>\n" " [filename|camera_index]\n" ); return -1; } storage = cvCreateMemStorage(0); if( !input_name || (isdigit(input_name[0]) && input_name[1] == '\0') ) 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 ) { /* assume it is a text file containing the list of the image filenames to be processed - one per line */ 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] = '\0'; printf( "file %s\n", 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 = %gms\n", 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 = %gms\n", 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
//附加包含目錄: include, include/opencv, include/opencv2
//附加庫目錄: lib
//附加依賴項: debug:--> opencv_calib3d243d.lib;...;
// release:--> opencv_calib3d243.lib;...;
#include<string>
#include <opencv2\opencv.hpp>
#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;
}調整主函式中faceDetect(const char* imageName, int nNested, int nSmile, int nProfile)函式中的引數，分別表示影象檔名，是否檢測眼睛，是否檢測微笑，是否檢測側臉。以檢測正臉、眼睛為例：
再來看一張合影。
===========================================================================================
華麗麗的分割線
===========================================================================================
如果對分類器的引數不滿意，或者說想識別其他的物體例如車、人、飛機、蘋果等等等等，只需要選擇適當的樣本訓練，獲取該物體的各個方面的引數，訓練過程可以通過openCV的haartraining實現（參考haartraining參考文件，opencv/apps/traincascade），主要包括個步驟：
1. 收集打算學習的物體資料集（如正面人臉圖，側面汽車圖等， 1000~10000個正樣本為宜），把它們儲存在一個或多個目錄下面。
2. 使用createsamples來建立正樣本的向量輸出檔案，通過這個檔案可以重複訓練過程，使用同一個向量輸出檔案嘗試各種引數。
3. 獲取負樣本，即不包含該物體的影象。
4. 訓練。命令列實現。
後更。