# This example program shows how to find frontal human faces in an image. In
# particular, it shows how you can take a list of images from the command
# line and display each on the screen with red boxes overlaid on each human
# face.
#
# The examples/faces folder contains some jpg images of people. You can run
# this program on them and see the detections by executing the
# following command:
# ./face_detector.py ../examples/faces/*.jpg
#
# This face detector is made using the now classic Histogram of Oriented
# Gradients (HOG) feature combined with a linear classifier, an image
# pyramid, and sliding window detection scheme. This type of object detector
# is fairly general and capable of detecting many types of semi-rigid objects
# in addition to human faces. Therefore, if you are interested in making
# your own object detectors then read the train_object_detector.py example
# program.
import sys
import dlib
detector = dlib.get_frontal_face_detector()
win = dlib.image_window()
for f in sys.argv[1:]:
print("Processing file: {}".format(f))
img = dlib.load_rgb_image(f)
# 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)))
for i, d in enumerate(dets):
print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
i, d.left(), d.top(), d.right(), d.bottom()))
win.clear_overlay()
win.set_image(img)
win.add_overlay(dets)
dlib.hit_enter_to_continue()
# Finally, if you really want to you can ask the detector to tell you the score
# for each detection. The score is bigger for more confident detections.
# The third argument to run is an optional adjustment to the detection threshold,
# where a negative value will return more detections and a positive value fewer.
# Also, the idx tells you which of the face sub-detectors matched. This can be
# used to broadly identify faces in different orientations.
if (len(sys.argv[1:]) > 0):
img = dlib.load_rgb_image(sys.argv[1])
dets, scores, idx = detector.run(img, 1, -1)
for i, d in enumerate(dets):
print("Detection {}, score: {}, face_type:{}".format(
d, scores[i], idx[i]))
# This example program shows how you can use dlib to make a HOG based object
# detector for things like faces, pedestrians, and any other semi-rigid
# object. In particular, we go though the steps to train the kind of sliding
# window object detector first published by Dalal and Triggs in 2005 in the
# paper Histograms of Oriented Gradients for Human Detection.
import os
import sys
import glob
import dlib
# In this example we are going to train a face detector based on the small
# faces dataset in the examples/faces directory. This means you need to supply
# the path to this faces folder as a command line argument so we will know
# where it is.
if len(sys.argv) != 2:
print(
"Give the path to the examples/faces directory as the argument to this "
"program. For example, if you are in the python_examples folder then "
"execute this program by running:\n"
" ./train_object_detector.py ../examples/faces")
exit()
faces_folder = sys.argv[1]
# Now let's do the training. The train_simple_object_detector() function has a
# bunch of options, all of which come with reasonable default values. The next
# few lines goes over some of these options.
options = dlib.simple_object_detector_training_options()
# Since faces are left/right symmetric we can tell the trainer to train a
# symmetric detector. This helps it get the most value out of the training
# data.
options.add_left_right_image_flips = True
# The trainer is a kind of support vector machine and therefore has the usual
# SVM C parameter. In general, a bigger C encourages it to fit the training
# data better but might lead to overfitting. You must find the best C value
# empirically by checking how well the trained detector works on a test set of
# images you haven't trained on. Don't just leave the value set at 5. Try a
# few different C values and see what works best for your data.
options.C = 5
# Tell the code how many CPU cores your computer has for the fastest training.
options.num_threads = 4
options.be_verbose = True
training_xml_path = os.path.join(faces_folder, "training.xml")
testing_xml_path = os.path.join(faces_folder, "testing.xml")
# This function does the actual training. It will save the final detector to
# detector.svm. The input is an XML file that lists the images in the training
# dataset and also contains the positions of the face boxes. To create your
# own XML files you can use the imglab tool which can be found in the
# tools/imglab folder. It is a simple graphical tool for labeling objects in
# images with boxes. To see how to use it read the tools/imglab/README.txt
# file. But for this example, we just use the training.xml file included with
# dlib.
dlib.train_simple_object_detector(training_xml_path, "detector.svm", options)
# Now that we have a face detector we can test it. The first statement tests
# it on the training data. It will print(the precision, recall, and then)
# average precision.
print("") # Print blank line to create gap from previous output
print("Training accuracy: {}".format(
dlib.test_simple_object_detector(training_xml_path, "detector.svm")))
# However, to get an idea if it really worked without overfitting we need to
# run it on images it wasn't trained on. The next line does this. Happily, we
# see that the object detector works perfectly on the testing images.
print("Testing accuracy: {}".format(
dlib.test_simple_object_detector(testing_xml_path, "detector.svm")))
# Now let's use the detector as you would in a normal application. First we
# will load it from disk.
detector = dlib.simple_object_detector("detector.svm")
# We can look at the HOG filter we learned. It should look like a face. Neat!
win_det = dlib.image_window()
win_det.set_image(detector)
# Now let's run the detector over the images in the faces folder and display the
# results.
print("Showing detections on the images in the faces folder...")
win = dlib.image_window()
for f in glob.glob(os.path.join(faces_folder, "*.jpg")):
print("Processing file: {}".format(f))
img = dlib.load_rgb_image(f)
dets = detector(img)
print("Number of faces detected: {}".format(len(dets)))
for k, d in enumerate(dets):
print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(
k, d.left(), d.top(), d.right(), d.bottom()))
win.clear_overlay()
win.set_image(img)
win.add_overlay(dets)
dlib.hit_enter_to_continue()
# Next, suppose you have trained multiple detectors and you want to run them
# efficiently as a group. You can do this as follows:
detector1 = dlib.fhog_object_detector("detector.svm")
# In this example we load detector.svm again since it's the only one we have on
# hand. But in general it would be a different detector.
detector2 = dlib.fhog_object_detector("detector.svm")
# make a list of all the detectors you wan to run. Here we have 2, but you
# could have any number.
detectors = [detector1, detector2]
image = dlib.load_rgb_image(faces_folder + '/2008_002506.jpg')
[boxes, confidences, detector_idxs] = dlib.fhog_object_detector.run_multiple(detectors, image, upsample_num_times=1, adjust_threshold=0.0)
for i in range(len(boxes)):
print("detector {} found box {} with confidence {}.".format(detector_idxs[i], boxes[i], confidences[i]))
# Finally, note that you don't have to use the XML based input to
# train_simple_object_detector(). If you have already loaded your training
# images and bounding boxes for the objects then you can call it as shown
# below.
# You just need to put your images into a list.
images = [dlib.load_rgb_image(faces_folder + '/2008_002506.jpg'),
dlib.load_rgb_image(faces_folder + '/2009_004587.jpg')]
# Then for each image you make a list of rectangles which give the pixel
# locations of the edges of the boxes.
boxes_img1 = ([dlib.rectangle(left=329, top=78, right=437, bottom=186),
dlib.rectangle(left=224, top=95, right=314, bottom=185),
dlib.rectangle(left=125, top=65, right=214, bottom=155)])
boxes_img2 = ([dlib.rectangle(left=154, top=46, right=228, bottom=121),
dlib.rectangle(left=266, top=280, right=328, bottom=342)])
# And then you aggregate those lists of boxes into one big list and then call
# train_simple_object_detector().
boxes = [boxes_img1, boxes_img2]
detector2 = dlib.train_simple_object_detector(images, boxes, options)
# We could save this detector to disk by uncommenting the following.
#detector2.save('detector2.svm')
# Now let's look at its HOG filter!
win_det.set_image(detector2)
dlib.hit_enter_to_continue()
# Note that you don't have to use the XML based input to
# test_simple_object_detector(). If you have already loaded your training
# images and bounding boxes for the objects then you can call it as shown
# below.
print("\nTraining accuracy: {}".format(
dlib.test_simple_object_detector(images, boxes, detector2)))
