树莓派3B+ 人脸检测（OpenCV）

树莓派3B+ 人脸检测（OpenCV）

---

安装完OpenCV是不是已经等不急要试试它的强大能力了？这里教大家使用自带的Haar级联分类器来进行人脸检测。

---

对于没有安装OpenCV的伙伴，可参考：
树莓派3B+ 安装计算机视觉库（OpenCV_2.4.9官方源）
树莓派3B+ 安装计算机视觉库（OpenCV_3+OpenCV_Contrib_3）

1.找到Haar级联数据

对于官方源安装的OpenCV，可以在 “/usr/share/opencv/” 目录下找到，对于自行编译安装的，请找到下载的源文件解压目录。（一般会在 “/home/pi/opencv-3.3.1/data/”）
在这里，默认是使用官方源版路径，其它请行修改。

2.静态图像中的人脸检测

人脸检测首先是加载图像并检测人脸，这也是最基本的一步。为了使所得到的结果直观显示，这里对原始图像的人脸周围绘制矩形框。

注意：OpenCV3.x版本的，请自行修改(接收返回值)
cv2.rectangle—>img=cv2.rectangle...

// 以下为python脚本，请保存为detectface.py后缀
#!/usr/bin/env python
#coding=utf-8
import cv2
import sys

# rectangle color and stroke
color = (0,0,255)       # reverse of RGB (B,G,R) - weird
strokeWeight = 2        # thickness of outline

def detect(filename):
    face_cascade=cv2.CascadeClassifier('/usr/share/opencv/haarcascades/haarcascade_frontalface_default.xml')
    # 载入要检测的图片
    img = cv2.imread(filename)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces=face_cascade.detectMultiScale(gray,1.3,5)
    for x,y,w,h in faces:
        #这里要注意，OpenCV3.x版本需要接收返回值
        #即img=cv2.rectangle(img, (x,y), (x+w, y+h), color, strokeWeight)
        cv2.rectangle(img, (x,y), (x+w, y+h), color, strokeWeight)

    cv2.imshow('faces',img)
    #cv2.imwrite(filename+"-faces.jpg", img)
    if cv2.waitKey(1000 // 12) & 0xff == ord("q"):
        break


if __name__ == '__main__':
    if len(sys.argv)>1:
        i=1;
        while iprint 'img:'+sys.argv[i]
            detect(sys.argv[i])
            i+=1

    if len(sys.argv)==1:
        print "USAGE: detectface.py <待检测图片存放路径>"

保存后，执行 python detectface.py photo.png这里photo.png为待检测图片。如果你要保存检测的结果，可去掉注释cv2.imwrite(filename+"-faces.jpg", img)

3.静态图像中的人脸检测和人眼检测

注意：OpenCV3.x版本的，请自行修改(接收返回值)
cv2.rectangle—>img=cv2.rectangle...

// 以下为python脚本，请保存为detecteye.py后缀
#!/usr/bin/env python
#coding=utf-8
import cv2
import sys

# rectangle color and stroke
face_color = (192,220,240)       # reverse of RGB (B,G,R) - weird
eye_color = (160,160,164)
strokeWeight = 2        # thickness of outline

def detect(filename):
    face_cascade=cv2.CascadeClassifier('/usr/share/opencv/haarcascades/haarcascade_frontalface_default.xml')
    eye_cascade=cv2.CascadeClassifier('/usr/share/opencv/haarcascades/haarcascade_eye.xml')
    # 载入要检测的图片
    img = cv2.imread(filename)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces=face_cascade.detectMultiScale(gray,1.3,5)
    for x,y,w,h in faces:
        cv2.rectangle(img, (x,y), (x+w, y+h), face_color, strokeWeight)
        face_gray=gray[y:y+h,x:x+w]
        eyes=eye_cascade.detectMultiScale(face_gray,1.03,5,0,(40,40))
        for ex,ey,ew,eh in eyes:
            cv2.rectangle(img,(x+ex,y+ey),(x+ex+ew,y+ey+eh),eye_color,strokeWeight)


    #cv2.namedWindow('detect_face')
    cv2.imshow('faces-eyes',img)
    #cv2.imwrite(filename+"-eyes.jpg", img)
    if cv2.waitKey(1000 // 12) & 0xff == ord("q"):
        break


if __name__ == '__main__':
    if len(sys.argv)>1:
        i=1;
        while iprint 'img:'+sys.argv[i]
            detect(sys.argv[i])
            i+=1

    if len(sys.argv)==1:
        print "USAGE: detecteye.py <待检测图片存放路径>"

保存后，执行 python detecteye.py photo.png这里photo.png为待检测图片。如果你要保存检测的结果，可去掉注释cv2.imwrite(filename+"-eyes.jpg", img)

4.视频中的人脸检测和人眼检测

这里直接提供一个多线程的检测方案，保证帧率更高。
注意：OpenCV3.x版本的，请自行修改(接收返回值)
cv2.rectangle—>img=cv2.rectangle...

// 以下为python脚本，请保存为detectcamera.py后缀
#!/usr/bin/env python
#coding=utf-8
### Imports ###################################################################

import multiprocessing as mp
import cv2
import os
import time


### Setup #####################################################################

resX = 480
resY = 320


# The face cascade file to be used
face_cascade=cv2.CascadeClassifier('/usr/share/opencv/haarcascades/haarcascade_frontalface_default.xml')

eye_cascade=cv2.CascadeClassifier('/usr/share/opencv/haarcascades/haarcascade_eye.xml')

face_color = (192,220,240)   
eye_color = (200,160,164)
strokeWeight = 2 
t_start = time.time()
fps = 0


### Helper Functions ##########################################################

def get_faces( img ):

    gray = cv2.cvtColor( img, cv2.COLOR_BGR2GRAY )
    faces = face_cascade.detectMultiScale(gray, 1.3, 5)

    return faces, img, gray

def draw_frame( faces, img, gray):

    global xdeg
    global ydeg
    global fps
    global time_t

    for x, y, w, h in faces:

        cv2.rectangle( img, ( x, y ),( x + w, y + h ), face_color, strokeWeight)
        cv2.putText(img, "Face No." + str( len( faces ) ), ( x, y ), cv2.FONT_HERSHEY_SIMPLEX, 0.5, ( 0, 0, 255 ), 2 )
        face_gray=gray[y:y+h,x:x+w]
        eyes=eye_cascade.detectMultiScale(face_gray,1.03,5,0,(40,40))
        for ex,ey,ew,eh in eyes:
            cv2.rectangle(img,(x+ex,y+ey),(x+ex+ew,y+ey+eh),eye_color,strokeWeight)

    # Calculate and show the FPS
    fps = fps + 1
    sfps = fps / (time.time() - t_start)
    cv2.putText(img, "FPS : " + str( int( sfps ) ), ( 10, 10 ), cv2.FONT_HERSHEY_SIMPLEX, 0.5, ( 0, 0, 255 ), 2 )

    cv2.imshow( "Frame", img )


### Main ######################################################################

if __name__ == '__main__':

    camera = cv2.VideoCapture(0)
    camera.set(cv2.cv.CV_CAP_PROP_FRAME_WIDTH,resX)  
    camera.set(cv2.cv.CV_CAP_PROP_FRAME_HEIGHT,resY) 

    pool = mp.Pool( processes=4 )

    read, img = camera.read()
    pr1 = pool.apply_async( get_faces, [ img ] )   
    read, img = camera.read()
    pr2 = pool.apply_async( get_faces, [ img ] )  
    read, img = camera.read() 
    pr3 = pool.apply_async( get_faces, [ img ] )   
    read, img = camera.read()
    pr4 = pool.apply_async( get_faces, [ img ] )   

    fcount = 1

    while (True):
        read, img = camera.read()

        if   fcount == 1:
            pr1 = pool.apply_async( get_faces, [ img ] )
            faces, img, gray=pr2.get()
            draw_frame( faces, img, gray )

        elif fcount == 2:
            pr2 = pool.apply_async( get_faces, [ img ] )
            faces, img, gray=pr3.get()
            draw_frame( faces, img, gray )

        elif fcount == 3:
            pr3 = pool.apply_async( get_faces, [ img ] )
            faces, img, gray=pr4.get()
            draw_frame( faces, img, gray )

        elif fcount == 4:
            pr4 = pool.apply_async( get_faces, [ img ] )
            faces, img, gray=pr1.get()
            draw_frame( faces, img, gray )
            fcount = 0

        fcount += 1

        if cv2.waitKey(1000 // 12) & 0xff == ord("q"):
            break

    cv2.destroyAllWindows()

保存后，执行 python detectcamera.py

演示效果：

5.后续文章

人脸识别：
http://blog.csdn.net/kxwinxp/article/details/78522545