face_recognition problem with face_encodings function

Question

I am a newbie and having difficulty on resolving this issue.

What I am trying to do is run the sample code from face_recognition using a webcam. Both of the two example doesn't work on me and keeps on throwing this error.

Traceback (most recent call last):
  File "C:\Users\...\Desktop\face_recognition\demo_webcam.py", line 55, in <module>
    face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\...\AppData\Local\Programs\Python\Python311\Lib\site-packages\face_recognition\api.py", line 214, in face_encodings
    return [np.array(face_encoder.compute_face_descriptor(face_image, raw_landmark_set, num_jitters)) for raw_landmark_set in raw_landmarks]
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\...\AppData\Local\Programs\Python\Python311\Lib\site-packages\face_recognition\api.py", line 214, in <listcomp>  
    return [np.array(face_encoder.compute_face_descriptor(face_image, raw_landmark_set, num_jitters)) for raw_landmark_set in raw_landmarks]
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: compute_face_descriptor(): incompatible function arguments. The following argument types are supported:
    1. (self: _dlib_pybind11.face_recognition_model_v1, img: numpy.ndarray[(rows,cols,3),numpy.uint8], face: _dlib_pybind11.full_object_detection, num_jitters: int = 0, padding: float = 0.25) -> _dlib_pybind11.vector
    2. (self: _dlib_pybind11.face_recognition_model_v1, img: numpy.ndarray[(rows,cols,3),numpy.uint8], num_jitters: int = 0) -> _dlib_pybind11.vector
    3. (self: _dlib_pybind11.face_recognition_model_v1, img: numpy.ndarray[(rows,cols,3),numpy.uint8], faces: _dlib_pybind11.full_object_detections, num_jitters: int = 0, padding: float = 0.25) -> _dlib_pybind11.vectors
    4. (self: _dlib_pybind11.face_recognition_model_v1, batch_img: List[numpy.ndarray[(rows,cols,3),numpy.uint8]], batch_faces: List[_dlib_pybind11.full_object_detections], num_jitters: int = 0, padding: float = 0.25) -> _dlib_pybind11.vectorss
    5. (self: _dlib_pybind11.face_recognition_model_v1, batch_img: List[numpy.ndarray[(rows,cols,3),numpy.uint8]], num_jitters: int = 0) -> _dlib_pybind11.vectors

Invoked with: <_dlib_pybind11.face_recognition_model_v1 object at 0x000001DAB486B7B0>, array([[[208, 223, 240],
        [204, 213, 234],
        [191, 208, 229],
        ...,
        [ 87,  76,  74],
        [ 94,  78,  77],
        [ 82,  72,  70]],

       [[214, 223, 245],
        [208, 221, 240],
        [197, 217, 235],
        ...,
        [100,  63,  68],
        [104,  74,  71],
        [ 87,  78,  75]],

       [[220, 231, 249],
        [218, 228, 245],
        [208, 224, 239],
        ...,
        [ 96,  86,  84],
        [102,  83,  82],
        [ 86,  83,  80]],

       ...,

       [[ 36,  36,  35],
        [ 41,  37,  36],
        [ 40,  35,  33],
        ...,
        [107,  65,  41],
        [109,  67,  44],
        [109,  68,  50]],

       [[ 41,  39,  38],
        [ 42,  36,  35],
        [ 44,  39,  38],
        ...,
        [107,  64,  45],
        [106,  62,  42],
        [108,  64,  42]],

       [[ 46,  42,  41],
        [ 45,  39,  38],
        [ 43,  38,  36],
        ...,
        [104,  67,  51],
        [100,  64,  46],
        [108,  64,  40]]], dtype=uint8), <_dlib_pybind11.full_object_detection object at 0x000001DAB4EF0370>, 1 

I am using Python 3.11.2 running on Windows 11. I have face_recognition v1.3.0 and dlib v19.24.1.

I already tried reinstalling everything based on the installation guide from face_recognition.

Eveliaevelin

you may consider to adopt deepface. It has a stream function running facial recognition on webcam directly. – Wingate

Answer 1

Please replace the code line,

rgb_small_frame = frame_process[:, :, ::-1]

with below code line,

rgb_small_frame = numpy.ascontiguousarray(frame_process[:, :, ::-1])

Hautboy

alternatively: rgb_small_frame = cv2.cvtColor(small_frame, cv2.COLOR_BGR2RGB) – Bromeosin

Answer 2

Load the reference face image:

reference_image = face_recognition.load_image_file("/home/computer/Imagens/profile.jpeg")
reference_encoding = face_recognition.face_encodings(reference_image)[0]

Open a connection to the webcam (you may need to adjust the index based on your system):

cap = cv2.VideoCapture(0)

Video capture read loop:

while True:
    ret, frame = cap.read()

Convert the frame to RGB for face recognition:

    rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)

Perform face detection:

    face_locations = face_recognition.face_locations(rgb_frame)
    face_encodings = face_recognition.face_encodings(rgb_frame, face_locations)

Compare the current face with the reference face:

    for face_encoding in face_encodings:
        results = face_recognition.compare_faces([reference_encoding], face_encoding)
        name = "Match" if True in results else "No Match"
...

Falla

Answer 3

This is the answer

rgb_small_frame = cv2.cvtColor(small_frame, cv2.COLOR_BGR2RGB)

your code worked bex

Fizzy

Your answer could be improved with additional supporting information. Please edit to add further details, such as citations or documentation, so that others can confirm that your answer is correct. You can find more information on how to write good answers in the help center. – Whig