Merge branch 'visionworkz-master'

python_examples/face_clustering.py

@@ -0,0 +1,126 @@
+#!/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 for clustering using chinese_whispers.
+#   This is useful when you have a collection of photographs which you know are linked to
+#   a particular person, but the person may be photographed with multiple other people.
+#   In this example, we assume the largest cluster will contain photos of the common person in the
+#   collection of photographs. Then, we save extracted images of the face in the largest cluster in
+#   a 150x150 px format which is suitable for jittering and loading to perform metric learning (as shown
+#   in the dnn_metric_learning_on_images_ex.cpp example.
+#   https://github.com/davisking/dlib/blob/master/examples/dnn_metric_learning_on_images_ex.cpp
+#
+# 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 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 http://scikit-image.org/download.html. 
+
+import sys
+import os
+import dlib
+import glob
+from skimage import io
+
+if len(sys.argv) != 5:
+    print(
+        "Call this program like this:\n"
+        "   ./face_clustering.py shape_predictor_5_face_landmarks.dat dlib_face_recognition_resnet_model_v1.dat ../examples/faces output_folder\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]
+output_folder_path = sys.argv[4]
+
+# 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)
+
+descriptors = []
+images = []
+
+# Now find all the faces and compute 128D face descriptors for each face.
+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):
+        # Get the landmarks/parts for the face in box d.
+        shape = sp(img, d)
+
+        # Compute the 128D vector that describes the face in img identified by
+        # shape.  
+        face_descriptor = facerec.compute_face_descriptor(img, shape)
+        descriptors.append(face_descriptor)
+        images.append((img, shape))
+
+# Now let's cluster the faces.  
+labels = dlib.chinese_whispers_clustering(descriptors, 0.5)
+num_classes = len(set(labels))
+print("Number of clusters: {}".format(num_classes))
+
+# Find biggest class
+biggest_class = None
+biggest_class_length = 0
+for i in range(0, num_classes):
+    class_length = len([label for label in labels if label == i])
+    if class_length > biggest_class_length:
+        biggest_class_length = class_length
+        biggest_class = i
+
+print("Biggest cluster id number: {}".format(biggest_class))
+print("Number of faces in biggest cluster: {}".format(biggest_class_length))
+
+# Find the indices for the biggest class
+indices = []
+for i, label in enumerate(labels):
+    if label == biggest_class:
+        indices.append(i)
+
+print("Indices of images in the biggest cluster: {}".format(str(indices)))
+
+# Ensure output directory exists
+if not os.path.isdir(output_folder_path):
+    os.makedirs(output_folder_path)
+
+# Save the extracted faces
+print("Saving faces in largest cluster to output folder...")
+for i, index in enumerate(indices):
+    img, shape = images[index]
+    file_path = os.path.join(output_folder_path, "face_" + str(i))
+    dlib.save_face_chip(img, shape, file_path)
+    
+    
+
+

tools/python/src/face_recognition.cpp

@@ -9,6 +9,8 @@
 #include <dlib/dnn.h>
 #include <dlib/image_transforms.h>
 #include "indexing.h"
+#include <dlib/image_io.h>
+#include <dlib/clustering.h>
 
 
 using namespace dlib;
@@ -140,6 +142,78 @@ private:
     anet_type net;
 };
 
+// ----------------------------------------------------------------------------------------
+
+boost::python::list chinese_whispers_clustering(boost::python::list descriptors, float threshold)
+{
+    boost::python::list clusters;
+
+    size_t num_descriptors = len(descriptors);
+
+    // This next bit of code creates a graph of connected objects and then uses the Chinese
+    // whispers graph clustering algorithm to identify how many objects there are and which
+    // objects belong to which cluster.
+    std::vector<sample_pair> edges;
+    std::vector<unsigned long> labels;
+    for (size_t i = 0; i < num_descriptors; ++i)
+    {
+        for (size_t j = i+1; j < num_descriptors; ++j)
+        {
+            matrix<double,0,1>& first_descriptor = boost::python::extract<matrix<double,0,1>&>(descriptors[i]);
+            matrix<double,0,1>& second_descriptor = boost::python::extract<matrix<double,0,1>&>(descriptors[j]);
+
+            if (length(first_descriptor-second_descriptor) < threshold)
+                edges.push_back(sample_pair(i,j));
+        }
+    }
+    const auto num_clusters = chinese_whispers(edges, labels);
+    for (size_t i = 0; i < labels.size(); ++i)
+    {
+        clusters.append(labels[i]);
+    }
+    return clusters;
+}
+
+void save_face_chips (
+    object img,
+    const std::vector<full_object_detection>& faces,
+    const std::string& chip_filename
+)
+{
+    int num_faces = faces.size();
+    std::vector<chip_details> dets;
+    for (auto& f : faces)
+        dets.push_back(get_face_chip_details(f, 150, 0.25));
+    dlib::array<matrix<rgb_pixel>> face_chips;
+    extract_image_chips(numpy_rgb_image(img), dets, face_chips);
+    int i=0;
+    for (auto& chip : face_chips) 
+    {
+        i++;
+        if(num_faces > 1) 
+        {
+            const std::string& file_name = chip_filename + "_" + std::to_string(i) + ".jpg";
+            save_jpeg(chip, file_name);
+        }
+        else
+        {
+            const std::string& file_name = chip_filename + ".jpg";
+            save_jpeg(chip, file_name);
+        }
+    }
+}
+
+void save_face_chip (
+    object img,
+    const full_object_detection& face,
+    const std::string& chip_filename
+)
+{
+    std::vector<full_object_detection> faces(1, face);
+    save_face_chips(img, faces, chip_filename);
+    return;
+}
+
 
 // ----------------------------------------------------------------------------------------
 
@@ -158,6 +232,16 @@ void bind_face_recognition()
             );
     }
 
+    def("save_face_chip", &save_face_chip, (arg("img"),arg("face"),arg("chip_filename")),
+        "Takes an image and a full_object_detection that references a face in that image and saves the face with the specified file name prefix.  The face will be rotated upright and scaled to 150x150 pixels."
+        );
+    def("save_face_chips", &save_face_chips, (arg("img"),arg("faces"),arg("chip_filename")),
+        "Takes an image and a full_object_detections object that reference faces in that image and saves the faces with the specified file name prefix.  The faces will be rotated upright and scaled to 150x150 pixels."
+        );
+    def("chinese_whispers_clustering", &chinese_whispers_clustering, (arg("descriptors"), arg("threshold")),
+        "Takes a list of descriptors and returns a list that contains a label for each descriptor. Clustering is done using dlib::chinese_whispers."
+        );
+
     {
     typedef std::vector<full_object_detection> type;
     class_<type>("full_object_detections", "An array of full_object_detection objects.")