关于OpenCV for Python入门-face_recognition实现人脸识别

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

# 对指定的训练图片文件夹进行训练
def train(train_dir, model_save_path=None, n_neighbors=None, knn_algo='ball_tree', verbose=False):
    """
    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 = []

    # 循环获取训练集图片
    for class_dir in os.listdir(train_dir):
        if not os.path.isdir(os.path.join(train_dir, class_dir)):
            continue
        # 遍历当前任务的每一张图片
        # image_files_in_folder，这个地方是获取文件夹下的所有图片文件，可以修改其中的图片类型
        # 默认是jpg|jpeg|png，后来追加了bmp
        print('training picture of {}'.format(class_dir))
        for img_path in image_files_in_folder(os.path.join(train_dir, class_dir)):
            # 加载图片文件，其实是numpy数组
            image = face_recognition.load_image_file(img_path)
            # 获取人脸检测框
            face_bounding_boxes = face_recognition.face_locations(image)
            # 多个人物或者0个人物不处理
            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)

    # 设置KNN分类器的近邻数
    # 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))))
        n_neighbors = 3
        if verbose:
            print("Chose n_neighbors automatically:", n_neighbors)

    # 创建KNN分类器，并进行训练
    knn_clf = neighbors.KNeighborsClassifier(n_neighbors=n_neighbors, algorithm=knn_algo, weights='distance')
    knn_clf.fit(X, y)

    # 保存KNN训练结果
    if model_save_path is not None:
        with open(model_save_path, 'wb') as f:
            pickle.dump(knn_clf, f)

    return knn_clf

# 对指定的预测图片进行预测
def predict(X_img_path, knn_clf=None, model_path=None, distance_threshold=0.5):
    """
    Recognizes faces in given image using a trained KNN classifier
    :param X_img_path: path to image to be recognized
    :param knn_clf: (optional) a knn classifier object. if not specified, model_save_path must be specified.
    :param model_path: (optional) path to a pickled knn classifier. if not specified, model_save_path must be knn_clf.
    :param distance_threshold: (optional) distance threshold for face classification. the larger it is, the more chance
           of mis-classifying an unknown person as a known one.
    :return: a list of names and face locations for the recognized faces in the image: [(name, bounding box), ...].
        For faces of unrecognized persons, the name 'unknown' will be returned.
    """
    # 校验当前文件类型
    if not os.path.isfile(X_img_path) or os.path.splitext(X_img_path)[1][1:] not in ALLOWED_EXTENSIONS:
        raise Exception("Invalid image path: {}".format(X_img_path))

    # 校验当前模型文件和knn模型，两个不能全空
    if knn_clf is None and model_path is None:
        raise Exception("Must supply knn classifier either thourgh knn_clf or model_path")

    # 加载训练好的KNN模型
    if knn_clf is None:
        with open(model_path, 'rb') as f:
            knn_clf = pickle.load(f)

    # 加载图片，获取人脸检测框
    X_img = face_recognition.load_image_file(X_img_path)
    X_face_locations = face_recognition.face_locations(X_img)
    # print('predict {}'.format(X_img_path))
    # 如果未找到人脸，返回[]
    if len(X_face_locations) == 0:
        return []

    # 对测试图片进行编码转换，转换为numpy数组
    faces_encodings = face_recognition.face_encodings(X_img, known_face_locations=X_face_locations)

    # 通过KNN模型找到最佳匹配的人脸
    closest_distances = knn_clf.kneighbors(faces_encodings, n_neighbors=3)
    # # 返回值indices：第0列元素为参考点的索引，后面是(n_neighbors - 1)个与之最近的点的索引
    # # 返回值distances：第0列元素为与自身的距离(为0)，后面是(n_neighbors - 1)个与之最近的点与参考点的距离
    # closest_distances= [[0.34997745 0.3750366  0.37819395]]
    # closest_distances= [[ 5 12 11]]
    # for i in closest_distances:
    #     print('closest_distances=',i)
    are_matches = []
    # are_matches = [closest_distances[0][i][0] <= distance_threshold for i in range(len(X_face_locations))]
    for i in range(len(X_face_locations)):
        are_matches.append( closest_distances[0][i][0] <= distance_threshold)
        #print('predict value=', closest_distances[0][i][0])
    # print('knn_clf.predict(faces_encodings)=',knn_clf.predict(faces_encodings))
    # 预测分类
    return [(pred, loc) if rec else ("unknown", loc) for pred, loc, rec in zip(knn_clf.predict(faces_encodings), X_face_locations, are_matches)]

# 在图片上输出预测标签
def show_prediction_labels_on_image(img_path, predictions):
    """
    Shows the face recognition results visually.
    :param img_path: path to image to be recognized
    :param predictions: results of the predict function
    :return:
    """
    # 打开图片，获取句柄
    pil_image = Image.open(img_path).convert("RGB")
    draw = ImageDraw.Draw(pil_image)

    # 对预测结果进行遍历
    for name, (top, right, bottom, left) in predictions:
        # 在人脸周边画矩形框
        draw.rectangle(((left, top), (right, bottom)), outline=(0, 0, 255))

        # There's a bug in Pillow where it blows up with non-UTF-8 text
        # when using the default bitmap font
        name = name.encode("UTF-8")

        # 在人脸地图输出标签
        text_width, text_height = draw.textsize(name)
        draw.rectangle(((left, bottom - text_height - 10), (right, bottom)), fill=(0, 0, 255), outline=(0, 0, 255))
        draw.text((left + 6, bottom - text_height - 5), name, fill=(255, 255, 255, 255))

    # Remove the drawing library from memory as per the Pillow docs
    del draw

    # Display the resulting image
    pil_image.show()


if __name__ == "__main__":
    # 指定训练集路径和预测集路径
    train_dir=r'C:\Python\Pycharm\docxprocess\picture\ORL'
    test_dir=r'C:\Python\Pycharm\docxprocess\picture\predict'
    # 第一步，通过KNN分类器进行训练，并存储模型文件
    print("Training KNN classifier...")
    classifier = train(train_dir, model_save_path="trained_knn_model.clf", n_neighbors=3)
    print("Training complete!")

    # 第二步，使用训练分类器，对未知图片进行预测
    for image_file in os.listdir(test_dir):
        full_file_path = os.path.join(test_dir, image_file)
        print("Looking for faces in {}".format(image_file))

        # 使用训练模型进行预测
        predictions = predict(full_file_path, model_path="trained_knn_model.clf")

        # 输出结果
        for name, (top, right, bottom, left) in predictions:
            print("- Found {} at ({}, {})".format(name, left, top))

        # 图片上显示输出结果
        show_prediction_labels_on_image(os.path.join(test_dir, image_file), predictions)