Open DimIsaev opened 3 years ago
hej,
sure, see the updated iris.py
.
Now you can call it with a -i
flag to the inputfile:
python iris.py -i /path/to/some/file/i-am-a-video-file.mp4
for static something like this
import cv2
import mediapipe as mp
import numpy as np
from PIL import Image
mp_face_mesh = mp.solutions.face_mesh
frame = cv2.imread("/path_to_image/something.png")
cv2_im_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
frame_rgb = np.asarray(Image.fromarray(cv2_im_rgb), dtype=np.uint8)
with mp_face_mesh.FaceMesh(
static_image_mode=True, min_detection_confidence=0.5, min_tracking_confidence=0.5
) as face_mesh:
results = face_mesh.process(frame_rgb)
multi_face_landmarks = results.multi_face_landmarks
if multi_face_landmarks:
pass
# now add the processing steps from iris.py
#
# ...
# ...
thanks for the simple Python implementation
plan to do video and static file processing?