Failure of Haar Cascade to detect more than one face in a single frame

[NimishMishra]

Failure of Haar Cascade to detect more than one face in a single frame

[iamdsc]

I think what your code is lacking is a delay time which is required for detecting large number of faces in a frame before we read another frame from video stream, for few faces it should work normally. Try the code attached and let me know if you still face this issue.

import cv2
import time

face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
cap = cv2.VideoCapture(0)
while True:
    ret, img = cap.read()
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray,1.3,5)
    i=0
    for (x,y,w,h) in faces:
        cv2.rectangle(img, (x,y), (x+w, y+h), (255,0,0), 2)
        roi_color = img[y:y+h, x:x+w]
        face_file_name='faces/face_'+str(i)+'.jpg'
        cv2.imwrite(face_file_name, roi_color)
        i+=1
    cv2.imshow('image', img)
    time.sleep(1)
    k = cv2.waitKey(30) & 0xff
    if k==27:
        break
print(str(i)+' faces read')
cap.release()
cv2.destroyAllWindows()

[NimishMishra]

Yes it worked. Thanks.