cv2.error: /home/pi/opencv-3.1.0/modules/imgproc/src/imgwarp.cpp:3229: error: (-215) ssize.area() > 0 in function resize about face_recognition HOT 7 CLOSED

This probably means OpenCV wasn't able to grab an image from your webcam. Can you try rebooting your computer and running it again?

from face_recognition.

Hi,
Rebooted my Raspberry Pi. I am still get the same error.

from face_recognition.

Oh, this is a raspberry pi. You put macOS in the issue description.

The RPi camera doesn't work with OpenCV like that. There's a separate code example for raspberry pis that uses the picamera module.

from face_recognition.

Is there any separate code module that can do live video processing on Raspberry Pi similar to this? https://github.com/ageitgey/face_recognition/blob/master/examples/facerec_from_webcam_faster.py

from face_recognition.

The examples do almost the same thing. The only difference is the opencv example shows the video in a window while it processes it.

If you want to use the OpenCV example on an RPi, you could modify the OpenCV example to replace the part that captures the image:

# Get a reference to webcam #0 (the default one)
video_capture = cv2.VideoCapture(0)

# .. etc ..

while True:
    # Grab a single frame of video
    ret, frame = video_capture.read()

    # Resize frame of video to 1/4 size for faster face recognition processing
    small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25)

with the equivalent code using picamera:

camera = picamera.PiCamera()
camera.resolution = (320, 240)
small_frame = np.empty((240, 320, 3), dtype=np.uint8)

# ... etc ...

while True:
    print("Capturing image.")
    # Grab a single frame of video from the RPi camera as a numpy array
    camera.capture(small_frame, format="bgr")
    camera.close()

And something like that should work.

from face_recognition.

@ageitgey Thanks for your help. Will definitely try this out.

from face_recognition.

Cool! 👍

from face_recognition.