C++ OpenCV Reading HaarCascades Slowing Down Computer - c++

Question

I'm writing a program using C++ and OpenCV. It's actually my first so what I'm asking is probably something very basic I've overlooked. Much of it is copied - not copy+pasted mind you, but copied by hand, going line by line, understanding what each line was doing as I wrote it - from some of OpenCV's tutorials. I'll paste the code below.
The problem I'm encountering is that as soon as the webcam starts trying to implement facial recognition, everything just SLOWS. DOWN. As I understand it, its because the .exe is trying to read from two MASSIVE .xml files every frame update, but I don't have any idea how to fix it. It was worse before I constrained the height, width, and framerate of the video.
If anyone has any ideas at this point, I'd love to hear them. I'm very new to software programming - until now I've mostly done web development, so I'm not used to worrying about system memory and other factors.
Thanks in advance!
EDIT: Here are my system specs: Mac, OSX 10.9.4, 2.5 GHz Intel Core i5, 4 GB 1600 MHz DDR3 RAM.
#include "opencv2/objdetect.hpp"
#include "opencv2/videoio.hpp"
#include "opencv2/highgui.hpp"
#include "opencv2/imgproc.hpp"
#include <iostream>
#include <stdio.h>
using namespace std;
using namespace cv;
/** Function Headers */
void detectAndDisplay( Mat frame );
/** Global variables */
String face_cascade_name = "haarcascade_frontalface_alt.xml";
String eyes_cascade_name = "haarcascade_eye_tree_eyeglasses.xml";
CascadeClassifier face_cascade;
CascadeClassifier eyes_cascade;
String window_name = "Capture - Face detection";
/** #function main */
int main( void )
{
cv::VideoCapture capture;
Mat frame;
//-- 1. Load the cascades
if( !face_cascade.load( face_cascade_name ) ){ printf("--(!)Error loading face cascade\n"); return -1; };
if( !eyes_cascade.load( eyes_cascade_name ) ){ printf("--(!)Error loading eyes cascade\n"); return -1; };
//-- 2. Read the video stream
capture.open( -1 );
if ( ! capture.isOpened() ) { printf("--(!)Error opening video capture\n"); return -1; }
capture.set(CV_CAP_PROP_FRAME_WIDTH,640);
capture.set(CV_CAP_PROP_FRAME_HEIGHT,480);
capture.set(CV_CAP_PROP_FPS, 15);
while ( capture.read(frame) )
{
if( frame.empty() )
{
printf(" --(!) No captured frame -- Break!");
break;
}
//-- 3. Apply the classifier to the frame
detectAndDisplay( frame );
int c = waitKey(10);
if( (char)c == 27 ) { break; } // escape
}
return 0;
}
/** #function detectAndDisplay */
void detectAndDisplay( Mat frame )
{
std::vector<Rect> faces;
Mat frame_gray;
cvtColor( frame, frame_gray, COLOR_BGR2GRAY );
equalizeHist( frame_gray, frame_gray );
//-- Detect faces
face_cascade.detectMultiScale( frame_gray, faces, 1.1, 2, 0|CASCADE_SCALE_IMAGE, Size(30, 30) );
for ( size_t i = 0; i < faces.size(); i++ )
{
Point center( faces[i].x + faces[i].width/2, faces[i].y + faces[i].height/2 );
ellipse( frame, center, Size( faces[i].width/2, faces[i].height/2 ), 0, 0, 360, Scalar( 255, 0, 255 ), 4, 8, 0 );
Mat faceROI = frame_gray( faces[i] );
std::vector<Rect> eyes;
//-- In each face, detect eyes
eyes_cascade.detectMultiScale( faceROI, eyes, 1.1, 2, 0 |CASCADE_SCALE_IMAGE, Size(30, 30) );
for ( size_t j = 0; j < eyes.size(); j++ )
{
Point eye_center( faces[i].x + eyes[j].x + eyes[j].width/2, faces[i].y + eyes[j].y + eyes[j].height/2 );
int radius = cvRound( (eyes[j].width + eyes[j].height)*0.25 );
circle( frame, eye_center, radius, Scalar( 255, 0, 0 ), 4, 8, 0 );
}
}
//-- Show what you got
imshow( window_name, frame );
}

Answer 1

A quick solution would be to replace:
eyes_cascade.detectMultiScale( faceROI, eyes, 1.1, 2, 0 |CASCADE_SCALE_IMAGE, Size(30, 30) );
by
eyes_cascade.detectMultiScale( faceROI, eyes, 1.3, 2, 0 |CASCADE_SCALE_IMAGE, Size(60, 60), Size(350, 350) );
1.3 is the scale factor, Size(60, 60) the min windows size and Size(350, 350) the max one. It means basically that it will start to search for 60*60 faces then increase size by oldWindowSize*1.3 until it reach 350*350. It is assumed there that your faces are min 60*60 and max 350 * 350.
You can tune it even more depending what you want. The minSize will have a the most impact on performance as well as scale (but 1.3 is already high). The maxSize will have less impact.
After this update, your prog should be twice faster or decrease CPU usage by half. However, I am still surprise that with your current tunings and you computer you have performances problems...
Give us a feedback if it works.