opencv TypeError: 'int' object is not iterable

Question

I am trying to detect a face using OpenCV. I have a file recognizer.py as follows:

import cv2

faceDetect = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
cam = cv2.VideoCapture(0)
rec = cv2.face.createLBPHFaceRecognizer()
rec.load('recognizer/trainningData.yml')
id = 0
font = cv2.FONT_HERSHEY_SIMPLEX
while True:
    ret, img = cam.read()
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = faceDetect.detectMultiScale(gray, 1.3, 5)
    for (x, y, w, h) in faces:
        cv2.rectangle(img, (x, y), (x + w, y + h), (0, 0, 255), 2)
        id, conf = rec.predict(gray[y:y + h, x:x + w])
        cv2.putText(img, str(id), (x, y + h), font, 255, (255, 0, 0))
    cv2.imshow("Face", img)
    if cv2.waitKey(1) == ord('q'):
        break
cam.release()
cv2.destroyAllWindows()

When I am trying to run this code, the program is running successfully and opening a camera window.

But whenever, I am trying to show my face in front of the camera, the program is terminating with exit code 1 and showing the following error:

Traceback (most recent call last):
  File "/home/prateek/recognizer.py", line 15, in <module>
    id, conf = rec.predict(gray[y:y + h, x:x + w])

TypeError: 'int' object is not iterable

Process finished with exit code 1

Means, I am getting the error on line 15 which is as follows:

id, conf = rec.predict(gray[y:y + h, x:x + w])

I don't know how to resolve this problem. I am using Python3 and OpenCV3.3.

Maybe if you could demonstrate the problem in a Jupyter notebook, maybe on Google Colaboratory — Stefan Dragnev, Apr 18 '18 at 20:21
Well, you know the problem statement, so how about doing some debugging? Say, investigate the value of all the variables you use there? — Dan Mašek, Apr 18 '18 at 21:09

score 1 · Accepted Answer · answered May 07 '18 at 06:23

Finally, I have got the solution. The problem with was version of opencv. This code is for opencv2.4 and I was trying to run it on opencv3.

Well, The final code for opencv3 is as following:

import cv2

faceDetect = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
cam = cv2.VideoCapture(0)
rec = cv2.face.createLBPHFaceRecognizer()
rec.load('recognizer/trainningData.yml')
id = 0
font = cv2.FONT_HERSHEY_SIMPLEX
while True:
    ret, img = cam.read()
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = faceDetect.detectMultiScale(gray, 1.3, 5)
    for (x, y, w, h) in faces:
        cv2.rectangle(img, (x, y), (x + w, y + h), (0, 0, 255), 2)
        id= rec.predict(gray[y:y + h, x:x + w])
        cv2.putText(img, str(id), (x, y + h), font, 255, (255, 0, 0))
    cv2.imshow("Face", img)
    if cv2.waitKey(1) == ord('q'):
        break
cam.release()
cv2.destroyAllWindows()

There is no need to mention the variable conf.

rec.predict(gray[y:y + h, x:x + w]) is returning the id of the person from the database.

opencv TypeError: 'int' object is not iterable

1 Answers1