涉及深度度量学习的面部识别包含一个triplet训练步骤。triplet包含三种不同的脸,其中两张是一个人。神经网络为人脸图像生成128维向量。如果是同一个人的脸,我们就调整神经网络权重,让矢量距离更接近。
$ workon # optional
$ pip install dlib
$ workon# optional
$ git clone https://github.com/davisking/dlib.git
$ cd dlib
$ mkdir build
$ cd build
$ cmake .. -DUSE_AVX_INSTRUCTIONS=1
$ cmake --build .
$ cd ..
$ python setup.py install --yes USE_AVX_INSTRUCTIONS
$ workon# optional
$ git clone https://github.com/davisking/dlib.git
$ cd dlib
$ mkdir build
$ cd build
$ cmake .. -DDLIB_USE_CUDA=1 -DUSE_AVX_INSTRUCTIONS=1
$ cmake --build .
$ cd ..
$ python setup.py install --yes USE_AVX_INSTRUCTIONS --yes DLIB_USE_CUDA
$ workon# optional
$ pip install face_recognition
$ workon# optional
$ pip install imutils
$ tree --filelimit 10 --dirsfirst
.
├── dataset
│ ├── alan_grant [22 entries]
│ ├── claire_dearing [53 entries]
│ ├── ellie_sattler [31 entries]
│ ├── ian_malcolm [41 entries]
│ ├── john_hammond [36 entries]
│ └── owen_grady [35 entries]
├── examples
│ ├── example_01.png
│ ├── example_02.png
│ └── example_03.png
├── output
│ └── lunch_scene_output.avi
├── videos
│ └── lunch_scene.mp4
├── search_bing_api.py
├── encode_faces.py
├── recognize_faces_image.py
├── recognize_faces_video.py
├── recognize_faces_video_file.py
└── encodings.pickle
10 directories, 11 files
# import the necessary packages
from imutils import paths
import face_recognition
import argparse
import pickle
import cv2
import os
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--dataset", required=True,
help="path to input directory of faces + images")
ap.add_argument("-e", "--encodings", required=True,
help="path to serialized db of facial encodings")
ap.add_argument("-d", "--detection-method", type=str, default="cnn",
help="face detection model to use: either `hog` or `cnn`")
args = vars(ap.parse_args())
# grab the paths to the input images in our dataset
print("[INFO] quantifying faces...")
imagePaths = list(paths.list_images(args["dataset"]))
# initialize the list of known encodings and known names
knownEncodings = []
knownNames = []
# loop over the image paths
for (i, imagePath) in enumerate(imagePaths):
# extract the person name from the image path
print("[INFO] processing image {}/{}".format(i + 1,
len(imagePaths)))
name = imagePath.split(os.path.sep)[-2]
# load the input image and convert it from BGR (OpenCV ordering)
# to dlib ordering (RGB)
image = cv2.imread(imagePath)
rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
# detect the (x, y)-coordinates of the bounding boxes
# corresponding to each face in the input image
boxes = face_recognition.face_locations(rgb,
model=args["detection_method"])
# compute the facial embedding for the face
encodings = face_recognition.face_encodings(rgb, boxes)
# loop over the encodings
for encoding in encodings:
# add each encoding + name to our set of known names and
# encodings
knownEncodings.append(encoding)
knownNames.append(name)
# dump the facial encodings + names to disk
print("[INFO] serializing encodings...")
data = {"encodings": knownEncodings, "names": knownNames}
f = open(args["encodings"], "wb")
f.write(pickle.dumps(data))
f.close()
$ python encode_faces.py --dataset dataset --encodings encodings.pickle
[INFO] quantifying faces...
[INFO] processing image 1/218
[INFO] processing image 2/218
[INFO] processing image 3/218
...
[INFO] processing image 216/218
[INFO] processing image 217/218
[INFO] processing image 218/218
[INFO] serializing encodings...
$ ls -lh encodings*
-rw-r--r--@ 1 adrian staff 234K May 29 13:03 encodings.pickle
# import the necessary packages
import face_recognition
import argparse
import pickle
import cv2
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-e", "--encodings", required=True,
help="path to serialized db of facial encodings")
ap.add_argument("-i", "--image", required=True,
help="path to input image")
ap.add_argument("-d", "--detection-method", type=str, default="cnn",
help="face detection model to use: either `hog` or `cnn`")
args = vars(ap.parse_args())
# load the known faces and embeddings
print("[INFO] loading encodings...")
data = pickle.loads(open(args["encodings"], "rb").read())
# load the input image and convert it from BGR to RGB
image = cv2.imread(args["image"])
rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
# detect the (x, y)-coordinates of the bounding boxes corresponding
# to each face in the input image, then compute the facial embeddings
# for each face
print("[INFO] recognizing faces...")
boxes = face_recognition.face_locations(rgb,
model=args["detection_method"])
encodings = face_recognition.face_encodings(rgb, boxes)
# initialize the list of names for each face detected
names = []
# loop over the facial embeddings
for encoding in encodings:
# attempt to match each face in the input image to our known
# encodings
matches = face_recognition.compare_faces(data["encodings"],
encoding)
name = "Unknown"
# check to see if we have found a match
if True in matches:
# find the indexes of all matched faces then initialize a
# dictionary to count the total number of times each face
# was matched
matchedIdxs = [i for (i, b) in enumerate(matches) if b]
counts = {}
# loop over the matched indexes and maintain a count for
# each recognized face face
for i in matchedIdxs:
name = data["names"][i]
counts[name] = counts.get(name, 0) + 1
# determine the recognized face with the largest number of
# votes (note: in the event of an unlikely tie Python will
# select first entry in the dictionary)
name = max(counts, key=counts.get)
# update the list of names
names.append(name)
(Pdb) matchedIdxs
[35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 71, 72, 73, 74, 75]
(Pdb) counts
{'ian_malcolm': 40}
(Pdb) counts
{'alan_grant': 5}
# loop over the recognized faces
for ((top, right, bottom, left), name) in zip(boxes, names):
# draw the predicted face name on the image
cv2.rectangle(image, (left, top), (right, bottom), (0, 255, 0), 2)
y = top - 15 if top - 15 > 15 else top + 15
cv2.putText(image, name, (left, y), cv2.FONT_HERSHEY_SIMPLEX,
0.75, (0, 255, 0), 2)
# show the output image
cv2.imshow("Image", image)
cv2.waitKey(0)
$ python recognize_faces_image.py --encodings encodings.pickle \
--image examples/example_01.png
[INFO] loading encodings...
[INFO] recognizing faces...
Alan Grant和Ian Malcom
$ python recognize_faces_image.py --encodings encodings.pickle \
--image examples/example_02.png
[INFO] loading encodings...
[INFO] recognizing faces...
# import the necessary packages
from imutils.video import VideoStream
import face_recognition
import argparse
import imutils
import pickle
import time
import cv2
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-e", "--encodings", required=True,
help="path to serialized db of facial encodings")
ap.add_argument("-o", "--output", type=str,
help="path to output video")
ap.add_argument("-y", "--display", type=int, default=1,
help="whether or not to display output frame to screen")
ap.add_argument("-d", "--detection-method", type=str, default="cnn",
help="face detection model to use: either `hog` or `cnn`")
args = vars(ap.parse_args())
# load the known faces and embeddings
print("[INFO] loading encodings...")
data = pickle.loads(open(args["encodings"], "rb").read())
# initialize the video stream and pointer to output video file, then
# allow the camera sensor to warm up
print("[INFO] starting video stream...")
vs = VideoStream(src=0).start()
writer = None
time.sleep(2.0)
# loop over frames from the video file stream
while True:
# grab the frame from the threaded video stream
frame = vs.read()
# convert the input frame from BGR to RGB then resize it to have
# a width of 750px (to speedup processing)
rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
rgb = imutils.resize(frame, width=750)
r = frame.shape[1] / float(rgb.shape[1])
# detect the (x, y)-coordinates of the bounding boxes
# corresponding to each face in the input frame, then compute
# the facial embeddings for each face
boxes = face_recognition.face_locations(rgb,
model=args["detection_method"])
encodings = face_recognition.face_encodings(rgb, boxes)
names = []
# loop over the facial embeddings
for encoding in encodings:
# attempt to match each face in the input image to our known
# encodings
matches = face_recognition.compare_faces(data["encodings"],
encoding)
name = "Unknown"
# check to see if we have found a match
if True in matches:
# find the indexes of all matched faces then initialize a
# dictionary to count the total number of times each face
# was matched
matchedIdxs = [i for (i, b) in enumerate(matches) if b]
counts = {}
# loop over the matched indexes and maintain a count for
# each recognized face face
for i in matchedIdxs:
name = data["names"][i]
counts[name] = counts.get(name, 0) + 1
# determine the recognized face with the largest number
# of votes (note: in the event of an unlikely tie Python
# will select first entry in the dictionary)
name = max(counts, key=counts.get)
# update the list of names
names.append(name)
# loop over the recognized faces
for ((top, right, bottom, left), name) in zip(boxes, names):
# rescale the face coordinates
top = int(top * r)
right = int(right * r)
bottom = int(bottom * r)
left = int(left * r)
# draw the predicted face name on the image
cv2.rectangle(frame, (left, top), (right, bottom),
(0, 255, 0), 2)
y = top - 15 if top - 15 > 15 else top + 15
cv2.putText(frame, name, (left, y), cv2.FONT_HERSHEY_SIMPLEX,
0.75, (0, 255, 0), 2)
# if the video writer is None *AND* we are supposed to write
# the output video to disk initialize the writer
if writer is None and args["output"] is not None:
fourcc = cv2.VideoWriter_fourcc(*"MJPG")
writer = cv2.VideoWriter(args["output"], fourcc, 20,
(frame.shape[1], frame.shape[0]), True)
# if the writer is not None, write the frame with recognized
# faces t odisk
if writer is not None:
writer.write(frame)
# check to see if we are supposed to display the output frame to
# the screen
if args["display"] > 0:
cv2.imshow("Frame", frame)
key = cv2.waitKey(1) & 0xFF
# if the `q` key was pressed, break from the loop
if key == ord("q"):
break
# do a bit of cleanup
cv2.destroyAllWindows()
vs.stop()
# check to see if the video writer point needs to be released
if writer is not None:
writer.release()
$ python recognize_faces_video.py --encodings encodings.pickle \
--output output/webcam_face_recognition_output.avi --display 1
[INFO] loading encodings...
[INFO] starting video stream...
$ python recognize_faces_video_file.py --encodings encodings.pickle \
--input videos/lunch_scene.mp4 --output output/lunch_scene_output.avi \
--display 0