[人工智能]第二节 python人脸识别 从OpenCV、Dlib到Face-Recognition（使用jupyter）

1.OpenCV人脸识别

首先安装opencv，达到定位多个人脸的目的。

在安装过程中遇到的问题是，电脑里已经装好了opencv，但在jupyter里引用会出现这样的报错。

ERROR: Could not find a version that satisfies the requirement opencv (from versions: none)
ERROR: No matching distribution found for opencv

ModuleNotFoundError                       Traceback (most recent call last)
<ipython-input-3-252459bf3e0b> in <module>
----> 1 import cv2

ModuleNotFoundError: No module named 'cv2'

?

?错误原因是：系统python环境与jupyter中环境不一样

解决办法是用这行代码查一下jupyter中python的环境版本

import sys
print(sys.version)
pip install ipykernel

我的得出版本为3.8

?按照这一版本安装opencv的包，就可以在jupyter环境中成功引用cv2

安装好之后使用的代码为

import cv2
import os
import matplotlib.pyplot as plt

os.chdir("C:\\Users\\86159\\Desktop\\python")

def detect(filename):
?face_cascade = cv2.CascadeClassifier("E:\\Anaconda\\Lib\\site-packages\\cv2\\data\\haarcascade_frontalface_default.xml")
?img = cv2.imread(filename)
?gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
?faces = face_cascade.detectMultiScale(gray, 1.3, 5)


?for (x,y, w, h) in faces:
? ? ? ? img = cv2.rectangle(img,(x, y), (x + w, y + h), (255, 0, 0), 2)
?plt.imshow(img)
?plt.axis("off") ?#去掉坐标轴
?plt.show()
? ? ? ??
detect("one.jpg")

注意：文件的命名尽量用英文，数字和汉字容易报出奇怪的错误。

?

2.Dlib? face-recognition人脸识别

先安装dlib

pip install cmake
pip install boost

再按照刚才查的jupyter内python版本，下载相应版本dlib安装包，用这行代码在jupyter安装

pip install D:\下载\dlib-19.19.0-cp38-cp38-win_amd64.whl

再安装face recognition

pip install face_recognition

使用代码如下：

import face_recognition
import cv2
import matplotlib.pyplot as plt

image = face_recognition.load_image_file(r"C:\Users\86159\Desktop\python\1.jpg")
face_locations=face_recognition.face_locations(image)

face_num2=len(face_locations)
print(face_num2)       # The number of faces
org = cv2.imread(r"C:\Users\86159\Desktop\python\1.jpg")

for i in range(0,face_num2):
    top = face_locations[i][0]
    right = face_locations[i][1]
    bottom = face_locations[i][2]
    left = face_locations[i][3]

    start = (left, top)
    end = (right, bottom)

    color = (0,255,255)
    thickness = 2
    img=cv2.rectangle(org, start, end, color, thickness)
    plt.imshow(img)
    plt.axis('off')  #去掉坐标轴
plt.show()

?

?

?