summaryrefslogtreecommitdiffstats
path: root/ml/dlib/python_examples/face_recognition.py
blob: da2bdbc55b080eda7e1bae7f4da9c97abc889f65 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
#!/usr/bin/python
# The contents of this file are in the public domain. See LICENSE_FOR_EXAMPLE_PROGRAMS.txt
#
#   This example shows how to use dlib's face recognition tool.  This tool maps
#   an image of a human face to a 128 dimensional vector space where images of
#   the same person are near to each other and images from different people are
#   far apart.  Therefore, you can perform face recognition by mapping faces to
#   the 128D space and then checking if their Euclidean distance is small
#   enough. 
#
#   When using a distance threshold of 0.6, the dlib model obtains an accuracy
#   of 99.38% on the standard LFW face recognition benchmark, which is
#   comparable to other state-of-the-art methods for face recognition as of
#   February 2017. This accuracy means that, when presented with a pair of face
#   images, the tool will correctly identify if the pair belongs to the same
#   person or is from different people 99.38% of the time.
#
#   Finally, for an in-depth discussion of how dlib's tool works you should
#   refer to the C++ example program dnn_face_recognition_ex.cpp and the
#   attendant documentation referenced therein.
#
#
#
#
# COMPILING/INSTALLING THE DLIB PYTHON INTERFACE
#   You can install dlib using the command:
#       pip install dlib
#
#   Alternatively, if you want to compile dlib yourself then go into the dlib
#   root folder and run:
#       python setup.py install
#   or
#       python setup.py install --yes USE_AVX_INSTRUCTIONS
#   if you have a CPU that supports AVX instructions, since this makes some
#   things run faster.  This code will also use CUDA if you have CUDA and cuDNN
#   installed.
#
#   Compiling dlib should work on any operating system so long as you have
#   CMake installed.  On Ubuntu, this can be done easily by running the
#   command:
#       sudo apt-get install cmake
#
#   Also note that this example requires scikit-image which can be installed
#   via the command:
#       pip install scikit-image
#   Or downloaded from http://scikit-image.org/download.html. 

import sys
import os
import dlib
import glob
from skimage import io

if len(sys.argv) != 4:
    print(
        "Call this program like this:\n"
        "   ./face_recognition.py shape_predictor_5_face_landmarks.dat dlib_face_recognition_resnet_model_v1.dat ../examples/faces\n"
        "You can download a trained facial shape predictor and recognition model from:\n"
        "    http://dlib.net/files/shape_predictor_5_face_landmarks.dat.bz2\n"
        "    http://dlib.net/files/dlib_face_recognition_resnet_model_v1.dat.bz2")
    exit()

predictor_path = sys.argv[1]
face_rec_model_path = sys.argv[2]
faces_folder_path = sys.argv[3]

# Load all the models we need: a detector to find the faces, a shape predictor
# to find face landmarks so we can precisely localize the face, and finally the
# face recognition model.
detector = dlib.get_frontal_face_detector()
sp = dlib.shape_predictor(predictor_path)
facerec = dlib.face_recognition_model_v1(face_rec_model_path)

win = dlib.image_window()

# Now process all the images
for f in glob.glob(os.path.join(faces_folder_path, "*.jpg")):
    print("Processing file: {}".format(f))
    img = io.imread(f)

    win.clear_overlay()
    win.set_image(img)

    # Ask the detector to find the bounding boxes of each face. The 1 in the
    # second argument indicates that we should upsample the image 1 time. This
    # will make everything bigger and allow us to detect more faces.
    dets = detector(img, 1)
    print("Number of faces detected: {}".format(len(dets)))

    # Now process each face we found.
    for k, d in enumerate(dets):
        print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
            k, d.left(), d.top(), d.right(), d.bottom()))
        # Get the landmarks/parts for the face in box d.
        shape = sp(img, d)
        # Draw the face landmarks on the screen so we can see what face is currently being processed.
        win.clear_overlay()
        win.add_overlay(d)
        win.add_overlay(shape)

        # Compute the 128D vector that describes the face in img identified by
        # shape.  In general, if two face descriptor vectors have a Euclidean
        # distance between them less than 0.6 then they are from the same
        # person, otherwise they are from different people. Here we just print
        # the vector to the screen.
        face_descriptor = facerec.compute_face_descriptor(img, shape)
        print(face_descriptor)
        # It should also be noted that you can also call this function like this:
        #  face_descriptor = facerec.compute_face_descriptor(img, shape, 100)
        # The version of the call without the 100 gets 99.13% accuracy on LFW
        # while the version with 100 gets 99.38%.  However, the 100 makes the
        # call 100x slower to execute, so choose whatever version you like.  To
        # explain a little, the 3rd argument tells the code how many times to
        # jitter/resample the image.  When you set it to 100 it executes the
        # face descriptor extraction 100 times on slightly modified versions of
        # the face and returns the average result.  You could also pick a more
        # middle value, such as 10, which is only 10x slower but still gets an
        # LFW accuracy of 99.3%.


        dlib.hit_enter_to_continue()