使用Opencv进行人脸识别

Question

使用Opencv进行人脸识别

这是我用来识别网络摄像头中的脸部的代码，但是一旦相机无法识别脸部，它就会停止录制，我希望它是连续的。

import cv2
import logging as log
from time import sleep
import datetime as dt
import numpy as np

cascPath = "haarcascade_frontalface_default.xml"
faceCascade = cv2.CascadeClassifier(cascPath)
cam = cv2.VideoCapture(0);
anterior = 0
log.basicConfig(filename='webcam.log',level=log.INFO)


rec = cv2.face.LBPHFaceRecognizer_create();
rec.read('recognizer/trainningData.yml')
id=0

font = cv2.FONT_HERSHEY_SIMPLEX
fontscale = 1
fontcolor = (255,255,255)

while(True):
    if not cam.isOpened():
        print('Unable to load camera.')
        sleep(5)
        pass
    ret, img = cam.read();
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = faceCascade.detectMultiScale(gray, scaleFactor=1.1,minNeighbors=5,minSize=(30, 30))
    for(x, y, w, h) in faces:
        cv2.rectangle(img, (x,y), (x+w, y+h), (0,255,0),2)
        id, conf = rec.predict(gray[y:y+h,x:x+w])
        if(id == 1):
            id = "Nome do usuário detectado";
        cv2.putText(img,str(id),(x,y-10),font,0.55,(0,255,0),1);
        cv2.imshow("Face", img);
        if(conf<=20):
            if(id!=None):
                cv2.putText(img,str(id),(x,y-10),font,0.55,(0,255,0),1);
        else:
            cv2.putText(img,"Unknown",(x,y+h-10),font,0.55, (0,255,0),1);
        if anterior != len(faces):
            anterior = len(faces)
            log.info("ID: " + str(id) + " faces: "+str(len(faces))+" at "+str(dt.datetime.now()))
        if(cv2.waitKey(1)==ord('q')):
            break;
cam.release()
cv2.destroyAllWindows()

Answer 1

仔细查看您的代码......您正在调用imshow()方法，该方法负责在处理检测到的面部的for循环内显示图像。

这意味着如果未检测到faces，则不会执行for循环，因此不会调用imshow()。

如果要显示图像而不考虑检测结果，请将imshow()调用移至while循环

Opencv人脸检测。无法识别脸部时视频无效。如何进行连续录制？

使用Opencv进行人脸识别

1 个答案: