Ask Your Question
0

OpenCV2 Python face recognition camera freeze when launching script [closed]

asked 2020-01-12 02:34:56 -0600

I'm trying to use a script i've found on internet for facial recognition, it all works fine and my face is detected and the program knows who I am. But, i can't have the video when i'm launching the script the frame is gray and the python's window just freeze. Can you help me ? Here is the code :

import cv2
import numpy as np
import os 

recognizer = cv2.face.LBPHFaceRecognizer_create()
recognizer.read('trainer.yml')
cascadePath = "haarcascade_frontalface_default.xml"
faceCascade = cv2.CascadeClassifier(cascadePath);

font = cv2.FONT_HERSHEY_SIMPLEX

#iniciate id counter
id = 0

# names related to ids: example ==> John: id=1,  etc
names = ['None', 'John', 'Trump', 'Ilza', 'Z', 'W'] 

# Initialize and start realtime video capture
cam = cv2.VideoCapture(0)
cam.set(3, 740) # set video widht
cam.set(4, 580) # set video height

# Define min window size to be recognized as a face
minW = 0.1*cam.get(3)
minH = 0.1*cam.get(4)

while True:
    ret, img =cam.read()
    gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)

    faces = faceCascade.detectMultiScale(gray,scaleFactor=1.5,minNeighbors=5,minSize=(20,20))


    for(x,y,w,h) in faces:
        cv2.rectangle(img, (x,y), (x+w,y+h), (0,255,0), 2)
        id, confidence = recognizer.predict(gray[y:y+h,x:x+w])

        # Check if confidence is less them 100 ==> "0" is perfect match 
        if (confidence < 100):
           id = names[id]
           confidence = "  {0}%".format(round(100 - confidence))
            print(id)
        else:
           id = "unknown"
            print(id)
            confidence = "  {0}%".format(round(100 - confidence))

        cv2.putText(img, str(id), (x+5,y-5), font, 1, (255,255,255), 2)
        cv2.putText(img, str(confidence), (x+5,y+h-5), font, 1, (255,255,0), 1) 
        cv2.imshow('Frame',img) 

cap.release()
cv2.destroyAllWindows()
edit retag flag offensive reopen merge delete

Closed for the following reason the question is answered, right answer was accepted by RelativeCommand
close date 2020-01-12 03:18:25.072677

1 answer

Sort by ยป oldest newest most voted
1

answered 2020-01-12 02:48:23 -0600

berak gravatar image

updated 2020-01-12 02:57:58 -0600

there needs to be a cv2.waitKey() call after cv2.imshow() once per frame

(that's where the actual drawing happens),

also you only need 1 imshow() call per loop (and it has to show an image regardless if it finds any faces, too), like:

for(x,y,w,h) in faces:
    ...
    cv2.putText(img, str(id), (x+5,y-5), font, 1, (255,255,255), 2)

cv2.imshow('Frame',img) 
k = cv2.waitKey(10) # yield 10 ms back to your OS
if k==27: break # escape
edit flag offensive delete link more

Question Tools

1 follower

Stats

Asked: 2020-01-12 02:34:56 -0600

Seen: 1,706 times

Last updated: Jan 12 '20