Capturing face frames in python

Question

I'm new in python. I'm using python 3.5, and openCV3. I have the following code which is suppose to capture around 20 frames through the webcam:

import cv2
import time
cam = cv2.VideoCapture(0)
print(cam.isOpened())
detector=cv2.CascadeClassifier('haarcascade_frontalface_default.xml')

Id=1 
sampleNum=0

time.sleep(5)
while(True):
    ret, img = cam.read()
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = detector.detectMultiScale(gray, 1.3, 5)

    for (x,y,w,h) in faces:
        cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)

        #incrementing sample number 
        sampleNum=sampleNum+1
        #saving the captured face in the dataset folder
        cv2.imwrite("dataSet/User."+Id +'.'+ str(sampleNum) + ".jpg", gray[y:y+h,x:x+w])

        cv2.imshow('frame',img)
    #wait for 100 miliseconds 
    if cv2.waitKey(100) & 0xFF == ord('q'):
        break
    # break if the sample number is morethan 20
    elif sampleNum>20:
        break
cam.release()
cv2.destroyAllWindows()

However I'm getting this error:

gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

error: ......\modules\imgproc\src\color.cpp:7456: error: (-215) scn == 3 || scn == 4 in function cv::ipp_cvtColor

How can I overcome such error please?

I just double check if the cam is working or not. However my above code failedto capture my photo and save it in a dataset folder! — Mary

achille achille · Accepted Answer · 2017-09-16T16:15:11

This code worked on my machine and tracks my face. Try the following:

make sure the haarcascade xml file is in the same directory as where you run the code. You can also specify the absolute path to the file to be sure.
check if the gray image looks like what you expect cv2.imgshow('gray', gray) (and insert a sleep so you can see it). The cam.isOpened() should return True
check if its datatype is an uint8 np.ndarray: print(gray.dtype)

Capturing face frames in python

1 Answers