live webcam how to save it

[r3x07]

ok can anyone here tell me how to make it save the names of the people it detects on a webcam, i mean if it sees me is there anyway to make it save it into a file?

[jobergum]

Just modify https://github.com/ageitgey/face_recognition/blob/master/examples/facerec_from_webcam_faster.py slightly to save away frames where your face was found along with other metadata you want to save away.

[r3x07]

Mind giving example?

On Fri, Feb 14, 2020, 7:09 PM Jo Kristian Bergum notifications@github.com wrote:

Just modify https://github.com/ageitgey/face_recognition/blob/master/examples/facerec_from_webcam_faster.py slightly to save away frames where your face was found along with other metadata you want to save away.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/ageitgey/face_recognition/issues/1026?email_source=notifications&email_token=AI7ME7X2IMSH4Y6ZNAS7EMTRC2QXZA5CNFSM4KGKVHEKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOELZEPJQ#issuecomment-586303398, or unsubscribe https://github.com/notifications/unsubscribe-auth/AI7ME7W3AIBRT7VZKVSYUH3RC2QXZANCNFSM4KGKVHEA .

[jobergum]

@r3x07

Slightly modified from https://github.com/ageitgey/face_recognition/blob/master/examples/facerec_from_webcam_faster.py

Where you have an image of your face stored in my-image.png, the snippet will read your camera and dump frames where a face is found which has a similar (as measured by euclidian distance) encoding representation in the 128 dimensional encoding space as compared to your stored image of you.

import face_recognition
import cv2
import numpy as np
video_capture = cv2.VideoCapture(0)

my_image = face_recognition.load_image_file('my-image.png')
my_encoding = face_recognition.face_encodings(my_image)[0]

known_face_encodings = [
    my_encoding
]
face_locations = []
face_encodings = []
process_this_frame = True
count = 0
while True:
    ret, frame = video_capture.read()
    small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25)
    rgb_small_frame = small_frame[:, :, ::-1]

    if process_this_frame:
        # Find all the faces and face encodings in the current frame of video
        face_locations = face_recognition.face_locations(rgb_small_frame)
        face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations)
        for face_encoding in face_encodings:
            face_distances = face_recognition.face_distance(known_face_encodings, face_encoding)
            distance_metric = np.min(face_distances)
            if distance_metric < 0.6:
              print("Found myself in stream with distance : %f" % distance_metric)
              cv2.imwrite("my-from-video-%d.jpg" % count, frame) 
              count += 1

    process_this_frame = not process_this_frame

video_capture.release()
cv2.destroyAllWindows()

[r3x07]

Thanks but please mind commenting codes function so I know which line saves photos

On Tue, Feb 25, 2020, 7:11 PM Jo Kristian Bergum notifications@github.com wrote:

@r3x07 https://github.com/r3x07

Slightly modified from https://github.com/ageitgey/face_recognition/blob/master/examples/facerec_from_webcam_faster.py

Where you have an image of your face stored in my-image.png, the snippet will read your camera and dump frames where a face is found which has a similar (as measured by euclidian distance) encoding representation in the 128 dimensional encoding space as compared to your stored image of you.

import face_recognition import cv2 import numpy as np video_capture = cv2.VideoCapture(0)

my_image = face_recognition.load_image_file('my-image.png') my_encoding = face_recognition.face_encodings(my_image)[0]

known_face_encodings = [ my_encoding ] face_locations = [] face_encodings = [] process_this_frame = True count = 0 while True: ret, frame = video_capture.read() small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25) rgb_small_frame = small_frame[:, :, ::-1]

if process_this_frame:
    # Find all the faces and face encodings in the current frame of video
    face_locations = face_recognition.face_locations(rgb_small_frame)
    face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations)
    for face_encoding in face_encodings:
        face_distances = face_recognition.face_distance(known_face_encodings, face_encoding)
        distance_metric = np.min(face_distances)
        if distance_metric < 0.6:
          print("Found myself in stream with distance : %f" % distance_metric)
          cv2.imwrite("my-from-video-%d.jpg" % count, frame)
          count += 1

process_this_frame = not process_this_frame

video_capture.release() cv2.destroyAllWindows()

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/ageitgey/face_recognition/issues/1026?email_source=notifications&email_token=AI7ME7STWUQLXS4LS544G23REURJJA5CNFSM4KGKVHEKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEM4DDRQ#issuecomment-590885318, or unsubscribe https://github.com/notifications/unsubscribe-auth/AI7ME7VCYPDBBHXNZ4MYKILREURJJANCNFSM4KGKVHEA .

[jobergum]

This line saves the frame from the video where your face was found:

cv2.imwrite("my-from-video-%d.jpg" % count, frame) 

[r3x07]

Thanks alot and can you tell me how to make the box bigger? Like the resolution of that shit where my webcam is displayed in

On Wed, Feb 26, 2020, 1:18 AM Jo Kristian Bergum notifications@github.com wrote:

This line saves the frame from the video where your face was found:

cv2.imwrite("my-from-video-%d.jpg" % count, frame)

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/ageitgey/face_recognition/issues/1026?email_source=notifications&email_token=AI7ME7W2XRCISU4L3FM5S5LREV4IFA5CNFSM4KGKVHEKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEM5K7XI#issuecomment-591048669, or unsubscribe https://github.com/notifications/unsubscribe-auth/AI7ME7RLSEFSJAUFNJCFDB3REV4IFANCNFSM4KGKVHEA .

[r3x07]

Please tell me how to make the window bigger like full screen

On Wed, Feb 26, 2020, 2:58 PM Turkish Fun firco40@gmail.com wrote:

Thanks alot and can you tell me how to make the box bigger? Like the resolution of that shit where my webcam is displayed in

On Wed, Feb 26, 2020, 1:18 AM Jo Kristian Bergum notifications@github.com wrote:

This line saves the frame from the video where your face was found:

cv2.imwrite("my-from-video-%d.jpg" % count, frame)

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/ageitgey/face_recognition/issues/1026?email_source=notifications&email_token=AI7ME7W2XRCISU4L3FM5S5LREV4IFA5CNFSM4KGKVHEKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEM5K7XI#issuecomment-591048669, or unsubscribe https://github.com/notifications/unsubscribe-auth/AI7ME7RLSEFSJAUFNJCFDB3REV4IFANCNFSM4KGKVHEA .