I am gettig an error in my program of face recognition. (-215:Assertion failed) !empty() in function 'cv::CascadeClassifier::detectMultiScale'

Question

I am using LBPH algorithm for face detection. The part of collecting the data and training is working fine but in the testing part, there is an error

This is code for testing

import cv2
import numpy as np
import webbrowser


face_classifier = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')

def face_detector(img, size=0.5):

    faces = ()
    # Convert image to grayscale
    gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
    cv2.imshow('Printe1r', gray )
    if np.count_nonzero(gray) >= 0:
        print("in face detector")
        faces = face_classifier.detectMultiScale(gray, 1.3, 5)

    if faces is ():
        return img, []

    for (x,y,w,h) in faces:
        cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,255),2)
        roi = img[y:y+h, x:x+w]
        roi = cv2.resize(roi, (200, 200))
    return img, roi



# Open Webcam
cap = cv2.VideoCapture(0)
print("WebCam opened")
while True:

    ret, frame = cap.read()
    cv2.imshow('Printe1rwer', frame )
    image, face = face_detector(frame)
    cv2.imshow('Printe1aas r', image )
    print(face)

    try:
        print("hell1o")
        face = cv2.cvtColor(face, cv2.COLOR_BGR2GRAY)
        print("hello")
        # Pass face to prediction model
        # "results" comprises of a tuple containing the label and the confidence value
        results = model.predict(face)
        print("Helo",results)

        if results[1] < 500:
            print("in results < 500")
            confidence = int( 100 * (1 - (results[1])/400) )
            display_string = str(confidence) + '% Confident it is User'

        cv2.putText(face, display_string, (100, 120), cv2.FONT_HERSHEY_COMPLEX, 1, (255,120,150), 2)

        if confidence > 75:
            print("in confidence < 75")
            cv2.putText(face, "Hey Vimal", (250, 450), cv2.FONT_HERSHEY_COMPLEX, 1, (0,255,0), 2)
            cv2.imshow('Face Recognition', face )
            webbrowser.open('')
            break
        else:
            print("in else")
            cv2.putText(face, "Locked", (250, 450), cv2.FONT_HERSHEY_COMPLEX, 1, (0,0,255), 2)
            cv2.imshow('Face Recognition', face )

    except Exception as e:
        print(e)
        cv2.putText(frame, "No Face Found", (220, 120) , cv2.FONT_HERSHEY_COMPLEX, 1, (0,0,255), 2)
        cv2.putText(frame, "Locked", (250, 450), cv2.FONT_HERSHEY_COMPLEX, 1, (0,0,255), 2)
        cv2.imshow('Face Recognition', frame )
        pass

    if cv2.waitKey(1) == 13: #13 is the Enter Key
        break

cap.release()
cv2.destroyAllWindows() 

The error I am getting is:

---------------------------------------------------------------------------
error                                     Traceback (most recent call last)
<ipython-input-1-3a076399e5b1> in <module>
     34     ret, frame = cap.read()
     35     cv2.imshow('Printe1rwer', frame )
---> 36     image, face = face_detector(frame)
     37     cv2.imshow('Printe1aas r', image )
     38     print(face)

<ipython-input-1-3a076399e5b1> in face_detector(img, size)
     14     if np.count_nonzero(gray) >= 0:
     15         print("in face detector")
---> 16         faces = face_classifier.detectMultiScale(gray, 1.3, 5)
     17 
     18     if faces is ():

error: OpenCV(4.2.0) C:\projects\opencv-python\opencv\modules\objdetect\src\cascadedetect.cpp:1689: 
error: (-215:Assertion failed) !empty() in function 'cv::CascadeClassifier::detectMultiScale'`

Could somebody help me out?? I am using the OpenCV version 4.2.0 One thing is the value of the variable gray in the face detector function is always a numpy array with all values as zero. I have checked that but it is always zero.

Answer 1

I've tested the first part of your code. It seems to be working, printing gray I get:

TEMP.py:20: SyntaxWarning: "is" with a literal. Did you mean "=="?
  if faces is ():
WebCam opened
[[162 162 162 ...  97  97  97]
 [161 161 160 ...  95  95  95]
 [159 159 161 ...  95  95  95]
 ...
 [252 252 252 ... 164 164 164]
 [236 233 229 ... 165 164 164]
 [164 158 153 ... 164 164 164]]

Apart from correcting () with == as suggested by the interpreter, I would check:

1. That the img that comes in face detector is nonzero (just print it, mine is ok).
2. That you're actually loading the right input source in cap = cv2.VideoCapture(0) (do you have multiple webcams attached?)
3. Try inserting a if frame: block just after ret, frame = cap.read(). Probably only the first frame is None and it is giving you all the problems.

If the above are ok, the only suspect remains gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)...

A side note: ret, frame = cap.read() reads all the input continuously from the camera, but the pc may be slower than your algorithm in processing every frame. I usually avoid the creation of a long buffer using a trick. After you solve the above, have a look at this.

Answer 2

I tried changing the file path for "haarcascade_frontalface_default.xml" and it worked for me. I mean I provided the exact path for the location.