foreword

Use the OpenCV library in python to implement face recognition technology, and use pycharm to implement it.

1. Code implementation

Get the face and convert it to grayscale

Create a new data folder in the same directory to store grayscale images. The haarcascade_frontalface_default.xml file is changed according to the actual method. The input id number will correspond to the names in the identification code, for example, 0, 1, 2, 3. It cannot exceed the size of the names, otherwise an error will be reported.

# -----获取人脸样本-----
import cv2

# 调用笔记本内置摄像头，参数为0，如果有其他的摄像头可以调整参数为1,2
cap = cv2.VideoCapture(0)
# 调用人脸分类器，要根据实际路径调整
face_detector = cv2.CascadeClassifier(
    'D:/software/anaconda3/envs/mediapipe/Lib/site-packages/cv2/data/haarcascade_frontalface_default.xml')  # 待更改
# 为即将录入的脸标记一个id
face_id = input('\n User data input,Look at the camera and wait ...')
# sampleNum用来计数样本数目
count = 0

while True:
    # 从摄像头读取图片
    success, img = cap.read()
    # 转为灰度图片，减少程序符合，提高识别度
    if success is True:
        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    else:
        break
    # 检测人脸，将每一帧摄像头记录的数据带入OpenCv中，让Classifier判断人脸
    # 其中gray为要检测的灰度图像，1.3为每次图像尺寸减小的比例，5为minNeighbors
    faces = face_detector.detectMultiScale(gray, 1.3, 5)

    # 框选人脸，for循环保证一个能检测的实时动态视频流
    for (x, y, w, h) in faces:
        # xy为左上角的坐标,w为宽，h为高，用rectangle为人脸标记画框
        cv2.rectangle(img, (x, y), (x + w, y + w), (255, 0, 0))
        # 成功框选则样本数增加
        count += 1
        # 保存图像，把灰度图片看成二维数组来检测人脸区域
        # (这里是建立了data的文件夹，当然也可以设置为其他路径或者调用数据库)
        cv2.imwrite("data/User."+str(face_id)+'.'+str(count)+'.jpg',gray[y:y+h,x:x+w])
        # 显示图片
        cv2.imshow('image', img)
        # 保持画面的连续。waitkey方法可以绑定按键保证画面的收放，通过q键退出摄像
    k = cv2.waitKey(1)
    if k == '27':
        break
        # 或者得到足够个样本后退出摄像，这里可以根据实际情况修改数据量
    elif count >= 15:
        break

# 关闭摄像头，释放资源
cap.release()
cv2.destroyAllWindows()

Train the model

Create a folder named trainner in the same directory to store the recognizer, and call LBPHFaceRecognizer in OpenCV to create a human recognition model.

import os
import cv2
import numpy as np
from PIL import Image

# 导入pillow库，用于处理图像
# 设置之前收集好的数据文件路径
path = 'data'

# 初始化识别的方法
recog = cv2.face.LBPHFaceRecognizer_create()

# 调用熟悉的人脸分类器
detector = cv2.CascadeClassifier(
    'D:/software/anaconda3/envs/mediapipe/Lib/site-packages/cv2/data/haarcascade_frontalface_default.xml')


# 创建一个函数，用于从数据集文件夹中获取训练图片,并获取id
# 注意图片的命名格式为User.id.sampleNum
def get_images_and_labels(path):
    image_paths = [os.path.join(path, f) for f in os.listdir(path)]
    # 新建连个list用于存放
    face_samples = []
    ids = []

    # 遍历图片路径，导入图片和id添加到list中
    for image_path in image_paths:

        # 通过图片路径将其转换为灰度图片
        img = Image.open(image_path).convert('L')

        # 将图片转化为数组
        img_np = np.array(img, 'uint8')

        if os.path.split(image_path)[-1].split(".")[-1] != 'jpg':
            continue

        # 为了获取id，将图片和路径分裂并获取
        id = int(os.path.split(image_path)[-1].split(".")[1])
        faces = detector.detectMultiScale(img_np)

        # 将获取的图片和id添加到list中
        for (x, y, w, h) in faces:
            face_samples.append(img_np[y:y + h, x:x + w])
            ids.append(id)
    return face_samples, ids


# 调用函数并将数据喂给识别器训练
print('Training...')
faces, ids = get_images_and_labels(path)
# 训练模型
recog.train(faces, np.array(ids))
# 保存模型
recog.save('trainner/trainner.yml')

Call the camera for identification

The number of face_id entered before corresponds to the name in the names below.

# -----检测、校验并输出结果-----
import cv2

# 准备好识别方法
recognizer = cv2.face.LBPHFaceRecognizer_create()

# 使用之前训练好的模型
recognizer.read('trainner/trainner.yml')

# 再次调用人脸分类器
cascade_path = "D:/software/anaconda3/envs/mediapipe/Lib/site-packages/cv2/data/haarcascade_frontalface_default.xml"
face_cascade = cv2.CascadeClassifier(cascade_path)

# 加载一个字体，用于识别后，在图片上标注出对象的名字
font = cv2.FONT_HERSHEY_SIMPLEX

idnum = 0
# 设置好与ID号码对应的用户名，如下，如0对应的就是初始

names = ['user1','user2','user3','user4','user5',]

# 调用摄像头
cam = cv2.VideoCapture(0)
minW = 0.1 * cam.get(3)
minH = 0.1 * cam.get(4)
cap.open(0)
while cap.isOpened():
    ret, img = cam.read()
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    # 识别人脸
    faces = face_cascade.detectMultiScale(
        gray,
        scaleFactor=1.2,
        minNeighbors=5,
        minSize=(int(minW), int(minH))
    )
    # 进行校验
    for (x, y, w, h) in faces:
        cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2)
        idnum, confidence = recognizer.predict(gray[y:y + h, x:x + w])

        # 计算出一个检验结果
        if confidence < 100:
            idum = names[idnum]
            confidence = "{0}%", format(round(100 - confidence))
        else:
            idum = "unknown"
            confidence = "{0}%", format(round(100 - confidence))

        # 输出检验结果以及用户名
        cv2.putText(img, str(idum), (x + 5, y - 5), font, 1, (0, 0, 255), 1)
        cv2.putText(img, str(confidence), (x + 5, y + h - 5), font, 1, (0, 0, 0), 1)

        # 展示结果
        cv2.imshow('camera', img)
    if cv2.waitKey(1) in [ord('q'), 27]:  # q或esc退出
        break

# 释放资源
cam.release()
cv2.destroyAllWindows()

Second, the error occurred

The following problem occurs because the face_id is entered incorrectly, and a number that does not exceed the size of names must be entered, such as 0, 1, 2...

IndexError: list index out of range

Summarize

This face recognition code is very short, you can try it if you are interested.

Simple face recognition based on OpenCV

face recognition