3

I am trying to align faces before face recognition using Dlibs imutils.face_utils by converting the OpenCV rect to Dlib's rect. But I keep gettng error rectangle is not iterable. Here is the code 

detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor("shape_predictor_68_face_landmarks.dat")

fa = FaceAligner(predictor)

How do I align first using Dlib FaceUtils and then do prediction using OpenCV's recognizer.predict() ?

gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
faces = detector(gray, 2)

# If faces are found, try to recognize them
for (x,y,w,h)  in faces:
    (x1, y1, w1, h1) = rect_to_bb(x,y,w,h)

    faceAligned = fa.align(image, gray, (x1,y1,w1,h1))
    label, confidence = recognizer.predict(faceAligned)

    if confidence < threshold:
        found_faces.append((label, confidence, (x, y, w, h)))

return found_faces
Prabhakar
  • 1,138
  • 2
  • 14
  • 30
Manu BN
  • 53
  • 2
  • 6

1 Answers1

5

dlib rectangle object is not iterable, change your for loop to

for face in faces:
  x = face.left()
  y = face.top() #could be face.bottom() - not sure
  w = face.right() - face.left()
  h = face.bottom() - face.top()
  (x1, y1, w1, h1) = rect_to_bb(x,y,w,h)
  # rest same as above
Sreeragh A R
  • 2,871
  • 3
  • 27
  • 54