a3023fd Feb 22, 2017
@davisking @ageitgey
executable file 124 lines (109 sloc) 5.27 KB
# 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.
# 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 install
# or
# python 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 and boost-python installed. On Ubuntu, this can be done easily by
# running the command:
# sudo apt-get install libboost-python-dev cmake
# Also note that this example requires scikit-image which can be installed
# via the command:
# pip install scikit-image
# Or downloaded from
import sys
import os
import dlib
import glob
from skimage import io
if len(sys.argv) != 4:
"Call this program like this:\n"
" ./ shape_predictor_68_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"
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)
# 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.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.
# 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. He we just print
# the vector to the screen.
face_descriptor = facerec.compute_face_descriptor(img, shape)
# 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%.