python結合opencv,dlib實現人臉選中識別

1.pip安裝包

pip install opencv-python opencv-contrib-python   -i http://pypi.douban.com/simple/ --trusted-host pypi.douban.com

2.之前只是安裝這兩個包就能夠實現,但是在更新MacOS後,發現報錯了,錯誤日誌如下:

qt.qpa.plugin: Could not find the Qt platform plugin "cocoa" in ""
This application failed to start because no Qt platform plugin could be initialized. Reinstalling the application may fix this problem.

經過查閱文檔發現是opencv-python版本的問題,執行下面的命令後,程序又恢復正常:

pip install opencv-python-headless   -i http://pypi.douban.com/simple/ --trusted-host pypi.douban.com

人臉定位識別具體代碼如下:

import cv2
import dlib
import numpy as np
import os
def  catchPICFFromVideo(window_name,camera_idx,catch_pic_num,path_name):
    cv2.namedWindow(window_name)
    cap=cv2.VideoCapture(camera_idx)
    calssfier=cv2.CascadeClassifier('/Users/icsoc/.virtualenvs/scientific_calculation/lib/python3.7/site-packages/cv2/data/haarcascade_frontalface_alt.xml')
    color=(0,255,0)
    num=0
    while cap.isOpened():
        ok,frame=cap.read()
        if not ok:
            break
        grey=cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)
        faceRects=calssfier.detectMultiScale(grey,scaleFactor=1.2,minNeighbors=3,minSize=(32,32))
        if len(faceRects)>0:
            for faceRect in faceRects:
                x,y,w,h=faceRect
                image_name='%s%d.jpg'%(path_name,num)
                image=frame[y-10:y+h+10,x-10:x+w+10]
                cv2.imwrite(image_name,image,[int(cv2.IMWRITE_PNG_COMPRESSION),9])
                num+=1
                if num>(catch_pic_num):
                    break
                cv2.rectangle(frame,(x-10,y-10),(x+w+10,y+h+10),color,2)
                font=cv2.FONT_HERSHEY_SIMPLEX
                cv2.putText(frame,'num:%d/100'%(num),(x+20,y+30),font,1,(255,0,255),4)
        if num>(catch_pic_num):break
        cv2.imshow(window_name,frame)
        c=cv2.waitKey(10)
        if c&0xFF==ord('q'):
            break
    cap.release()
    cv2.destroyAllWindows()
catchPICFFromVideo("get face",0,100,".")

注意這裏的路徑:

    calssfier=cv2.CascadeClassifier('/Users/icsoc/.virtualenvs/scientific_calculation/lib/python3.7/site-packages/cv2/data/haarcascade_frontalface_alt.xml')

需要改成自己opencv的python包安裝目錄即可