BPI-M2 Ultra use OpenCV and face recognition

Banana Pi SBCs design BPI-M2 Ultra / BPI-M2 Berry(A40i)
1

1, install OpenCV on BPI-M2 Ultra

sudo apt-get update
sudo apt-get install libcv-dev

test opencv version:

#include <opencv2/core/core.hpp>
#include <stdio.h>
using namespace cv;
int main()
{
    printf("OpenCV version is:%s\n",CV_VERSION);
    return 0;
}

compile and run:

g++ -o testVersion.cpp ./testVersion.cpp -lopencv_core

2,install SimpleCV lib

sudo apt-get install ipython python-opencv python-scipy python-numpy python-setuptools
python-pip
sudo pip install https://github.com/ingenuitas/SimpleCV/zipball/master
sudo apt-get install python-pygame
sudo apt-get install python-imaging

3, inert UVC camera and test it;

4,Python realize face recognition program

#!/usr/bin/env python
from SimpleCV import *
from time import sleep
myCamera = Camera(prop_set={'width':320, 'height': 240})
myDisplay = Display(resolution=(320, 240))
while not myDisplay.isDone():
   frame = myCamera.getImage()
   faces = frame.findHaarFeatures('face')
   if faces:
     for face in faces:
        print "Face at: " + str(face.coordinates())
        facelayer = DrawingLayer((frame.width,frame.height))
        w=face.width()
        h=face.height()
        print "x:"+str(w)+" y:"+str(h)
        facebox_dim = (w,h)
        facebox = facelayer.centeredRectangle(face.coordinates(),facebox_dim)
        frame.addDrawingLayer(facelayer)
        frame.applyLayers()
                print "faces has detected."
   else:
        print "No faces detected."
   frame.save(myDisplay)
   sleep(.1)
1 Like