Python OpenCV face detection code sometimes raises `'tuple' object has no attribute 'shape'`

Question

I am trying to build a face detection application in python using opencv.
Please see below for my code snippets:

 # Loading the Haar Cascade Classifier
c         


        

Answer 1

From your error understand that you are trying to read the shape. But shape is the attribute of numpy.ndarray. You are trying to read the shape from the result of face detection. But that will only return the position only. Look at the types. Here img is an image and faces is the result of face detection. I hope you got the problem.

Updated with full code. For more clarification

In [1]: import cv2
In [2]: cap = cv2.VideoCapture(0)
In [3]: ret,img = cap.read()
In [4]: cascadePath = "/home/bikz05/Desktop/SNA_work/opencv-2.4.9/data/haarcascades/haarcascade_frontalface_default.xml"
In [5]: faceCascade = cv2.CascadeClassifier(cascadePath) 
In [6]: faces = faceCascade.detectMultiScale(img)
In [7]: type(img)
Out[1]: numpy.ndarray
In [8]: type(faces)
Out[2]: tuple

Look at the diffrence.

In [9]: img.shape
Out[3]: (480, 640, 3)
In [10]: faces.shape
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
 in ()
----> 1 faces.shape
AttributeError: 'tuple' object has no attribute 'shape'

If you want the number of faces. It's in the form of list of tuple. You can find the number of faces using len like len(faces)