基于face_recongnition的人脸识别

一、delib的下载安装

在windows下powershell下打开wsl

wsl

建议使用python的容器

python3 -m venv ~/venvs/dlib_env
source ~/venvs/dlib_env/bin/activate

然后安装一些依赖（我这里可能不全，有确实可以让AI帮着装）

sudo apt update && sudo apt upgrade -y

sudo apt install -y build-essential cmake python3-dev python3-pip \
libboost-all-dev libopenblas-dev liblapack-dev

然后，可以配置一下源，我这里用的是清华源，方式setuptool安装失败

mkdir -p ~/.pip
echo "[global]
index-url = https://pypi.tuna.tsinghua.edu.cn/simple
timeout = 120" > ~/.pip/pip.conf

pip install --upgrade pip setuptools wheel

sudo apt install -y libboost-all-dev

pip install dlib -i https://pypi.tuna.tsinghua.edu.cn/simple

这样就装完了，验证一下
![[Pasted image 20251010133252.png]]
成功，完成Delib的下载，接着把人脸识别的库一并下载了。

pip install face_recognition

环境就配置好了。

二、face_recongnition的使用

然后，下载face_recongnition的源码，里面有非常详细的说明和例子，教大家如何去进行人脸识别库face_recongntion的使用，其中，也不乏一些非常有趣的例子，比如识别奥巴马的脸型。

git clone https://github.com/ageitgey/face_recognition.git

这里给出几个个人比较感兴趣的例子，更多的内容参照github文档。

1、识别图像中人物的脸

先看效果：
![[Pasted image 20251014110012.png]]

代码如下：

from PIL import Image
import face_recognition


# Load the jpg file into a numpy array

image = face_recognition.load_image_file("biden.jpg")

  

# Find all the faces in the image using the default HOG-based model.

# This method is fairly accurate, but not as accurate as the CNN model and not GPU accelerated.

# See also: find_faces_in_picture_cnn.py

face_locations = face_recognition.face_locations(image)

  

print("I found {} face(s) in this photograph.".format(len(face_locations)))

  

for face_location in face_locations:

  

    # Print the location of each face in this image

    top, right, bottom, left = face_location

    print("A face is located at pixel location Top: {}, Left: {}, Bottom: {}, Right: {}".format(top, left, bottom, right))

  

    # You can access the actual face itself like this:

    face_image = image[top:bottom, left:right]

    pil_image = Image.fromarray(face_image)

    pil_image.show()

如果你有很多图片需要识别，同时又有GPU，可以查看官方的另外一个例子，来实现使用深度学习来识别拜登的脸。

2、识别单张图片中人物的关键点

效果：
![[Pasted image 20251014110815.png]]代码如下：

from PIL import Image, ImageDraw

import face_recognition

  

# Load the jpg file into a numpy array

image = face_recognition.load_image_file("two_people.jpg")

  

# Find all facial features in all the faces in the image

face_landmarks_list = face_recognition.face_landmarks(image)

  

print("I found {} face(s) in this photograph.".format(len(face_landmarks_list)))

  

# Create a PIL imagedraw object so we can draw on the picture

pil_image = Image.fromarray(image)

d = ImageDraw.Draw(pil_image)

  

for face_landmarks in face_landmarks_list:

  

    # Print the location of each facial feature in this image

    for facial_feature in face_landmarks.keys():

        print("The {} in this face has the following points: {}".format(facial_feature, face_landmarks[facial_feature]))

  

    # Let's trace out each facial feature in the image with a line!

    for facial_feature in face_landmarks.keys():

        d.line(face_landmarks[facial_feature], width=5)

  

# Show the picture

pil_image.show()

3、识别是拜登还是奥巴马

效果：
![[Pasted image 20251014112326.png]]
这个其实很简单，按照官方的说明，建立两个文件夹，第一个文件夹放置你已经知道名字的人脸图片文件夹，一个人一张图，图片的文件名即为对应的人的名字，然后第二个文件夹放置你希望识别的图片，然后运行对应的命令：

face_recognition ./pictures_of_people_i_know/ ./unknown_pictures/

即能够实现人脸的识别，输出的结果是：每一行对应着图片中的一张脸，图片名字和对应人脸识别结果用逗号分开。