face_train1.py

"""
This is an example of using the k-nearest-neighbors (KNN) algorithm for face recognition.

When should I use this example?
This example is useful when you wish to recognize a large set of known people,
and make a prediction for an unknown person in a feasible computation time.

Algorithm Description:
The knn classifier is first trained on a set of labeled (known) faces and can then predict the person
in an unknown image by finding the k most similar faces (images with closet face-features under eucledian distance)
in its training set, and performing a majority vote (possibly weighted) on their label.

For example, if k=3, and the three closest face images to the given image in the training set are one image of Biden
and two images of Obama, The result would be 'Obama'.

* This implementation uses a weighted vote, such that the votes of closer-neighbors are weighted more heavily.

Usage:

1. Prepare a set of images of the known people you want to recognize. Organize the images in a single directory
   with a sub-directory for each known person.

2. Then, call the 'train' function with the appropriate parameters. Make sure to pass in the 'model_save_path' if you
   want to save the model to disk so you can re-use the model without having to re-train it.

3. Call 'predict' and pass in your trained model to recognize the people in an unknown image.

NOTE: This example requires scikit-learn to be installed! You can install it with pip:

$ pip3 install scikit-learn

"""

import math
from sklearn import neighbors
import os
import os.path
import pickle
from PIL import Image, ImageDraw
import face_recognition
from face_recognition.face_recognition_cli import image_files_in_folder

ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg'}


def train(train_dir, model_save_path=None, n_neighbors=11, knn_algo='ball_tree', verbose=False):
    flag=0
    """
    Trains a k-nearest neighbors classifier for face recognition.

    :param train_dir: directory that contains a sub-directory for each known person, with its name.

     (View in source code to see train_dir example tree structure)

     Structure:
        <train_dir>/
        ├── <person1>/
        │   ├── <somename1>.jpeg
        │   ├── <somename2>.jpeg
        │   ├── ...
        ├── <person2>/
        │   ├── <somename1>.jpeg
        │   └── <somename2>.jpeg
        └── ...

    :param model_save_path: (optional) path to save model on disk
    :param n_neighbors: (optional) number of neighbors to weigh in classification. Chosen automatically if not specified
    :param knn_algo: (optional) underlying data structure to support knn.default is ball_tree
    :param verbose: verbosity of training
    :return: returns knn classifier that was trained on the given data.
    """
    
    X = []
    y = []

    # Loop through each person in the training set
    for class_dir in os.listdir(train_dir):
        if not os.path.isdir(os.path.join(train_dir, class_dir)):
            continue

        # Loop through each training image for the current person
        for img_path in image_files_in_folder(os.path.join(train_dir, class_dir)):
            image = face_recognition.load_image_file(img_path)
            face_bounding_boxes = face_recognition.face_locations(image)

            if len(face_bounding_boxes) != 1:
                # If there are no people (or too many people) in a training image, skip the image.
                if verbose:
                    print("Image {} not suitable for training: {}".format(img_path, "Didn't find a face" if len(face_bounding_boxes) < 1 else "Found more than one face"))
            else:
                # Add face encoding for current image to the training set
                X.append(face_recognition.face_encodings(image, known_face_locations=face_bounding_boxes)[0])
                y.append(class_dir)

    # Determine how many neighbors to use for weighting in the KNN classifier
    if n_neighbors is None:
        n_neighbors = int(round(math.sqrt(len(X))))
        if verbose:
            print("Chose n_neighbors automatically:", n_neighbors)

    # Create and train the KNN classifier
    knn_clf = neighbors.KNeighborsClassifier(n_neighbors=n_neighbors, algorithm=knn_algo, weights='distance')
    knn_clf.fit(X, y)

    # Save the trained KNN classifier
    if model_save_path is not None:
        with open(model_save_path, 'wb') as f:
            pickle.dump(knn_clf, f)
    flag=1
    return knn_clf,flag



def training():
    # STEP 1: Train the KNN classifier and save it to disk
    flag=0
    # Once the model is trained and saved, you can skip this step next time.
    print("Training KNN classifier...")
    classifier = train("knn_examples/train", model_save_path="trained_knn_model16082020.clf", n_neighbors=11)
    print("Training complete!")
    flag=1