目录
0. 前提
不是所有人都有GPU，因此这篇文章探索的是笔记本CPU就可以inference的程序；而且鉴于很多人对C++不是很熟悉(比如我)，所以这里均为python入门！
你可以拿这个练手，即时效果很好。
1. 人脸的python库包or开源项目
[1] dlib 可以采用GPU，但是默认关闭，博主暂时没有免费的显卡用
[2] face_recognition 此项目基于dlib实现，但是dlib自己也可实现；API文档
[3] libfacedetection 可以基于opencv-python-DNN实现，Link
TODO
2. windows上安装教程
在linux上均容易安装，但是windows下不易。
环境： windows、python3.8
pip install dlib-19.19.0-cp38-cp38-win_amd64.whl
pip install face_recognition
pip install opencv-python
dlib百度云链接 提取码：1sk6
3. 样例代码
import cv2
import numpy as np
import torch
import time
'''
目标检测(AI)-yolov5
'''
# model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)
# # img = r"E:\Python_Code\test\test.jpg"
# # results = model(img)
# # print(results.pandas().xyxy[0]["class"])
# # results.show()
# cap = cv2.VideoCapture(700)
# num = 0
# while True:
# if num % 2 != 0:
# continue
# ret, img = cap.read()
# if ret:
# results = model(img)
# results_pandas = results.pandas().xyxy[0] # 只有1张图像
# # 筛选数据，逻辑判断
# results_person = results_pandas[results_pandas["class"]==0]
# results_person_ = results_person.to_numpy()
# # 遍历画框
# rows = results_person_.shape[0]
# for i in range(rows):
# x1 = int(results_person_[i][0])
# y1 = int(results_person_[i][1])
# x2 = int(results_person_[i][2])
# y2 = int(results_person_[i][3])
# cv2.rectangle(img, (x1,y1), (x2,y2), (0,0,255), 2)
# cv2.imshow("img", img)
# if cv2.waitKey(1) & 0xFF == ord('q'):
# break
'''
人脸检测(opencv-python)
'''
# face_cascade = cv2.CascadeClassifier("D:\Anaconda3\Lib\site-packages\cv2\data\haarcascade_frontalface_default.xml")
# eye_cascade = cv2.CascadeClassifier("D:\Anaconda3\Lib\site-packages\cv2\data\haarcascade_eye.xml")
# cap = cv2.VideoCapture(700)// 笔记本的可能为0 或 700
# while True:
# ret, img = cap.read()
# if ret:
# gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# faces = face_cascade.detectMultiScale(gray,1.1,5)
# if len(faces)>0:
# for faceRect in faces:
# x, y, w, h = faceRect
# cv2.rectangle(img, (x,y), (x+w,y+h), (255,0,0), 2)
# roi_gray = gray[y:y+h//2, x:x+w]
# roi_color = img[y:y+h//2, x:x+w]
# eyes = eye_cascade.detectMultiScale(roi_gray, 1.1, 1, cv2.CASCADE_SCALE_IMAGE, (2,2))
# for (ex,ey,ew,eh) in eyes:
# cv2.rectangle(roi_color, (ex,ey), (ex+ew,ey+eh), (0,255,0), 2)
# cv2.imshow("img",img)
# if cv2.waitKey(1) & 0xFF == ord('q'):
# break
'''
dlib人脸检测
'''
# import dlib
# detector = dlib.get_frontal_face_detector()
# cap = cv2.VideoCapture(700)
# while True:
# ret, img = cap.read()
# if ret:
# dets = detector(img, 1)
# for i, d in enumerate(dets):
# cv2.rectangle(img, (d.left()-10,d.top()-10), (d.right()+10,d.bottom()+10), (0,0,255), 4)
# print(img)
# cv2.imshow("img",img)
# if cv2.waitKey(1) & 0xFF == ord('q'):
# break
# import sys
# import dlib
# from skimage import io
# detector = dlib.get_frontal_face_detector()
# window = dlib.image_window()
# img = cv2.imread(r"D:\20191215155844414.png")
# dets = detector(img, 1)
# print("Number of faces detected: {}".format(len(dets)))
# for i, d in enumerate(dets):
# print("Detection {}: Left: {} Top: {} Right: {} Bottom: {}".format(i, d.left(), d.top(), d.right(), d.bottom()))
# window.clear_overlay()
# window.set_image(img)
# window.add_overlay(dets)
# dlib.hit_enter_to_continue()
'''
基于dlib的 face_recognition 人脸检测识别
'''
import face_recognition
import cv2
import numpy as np
# This is a demo of running face recognition on live video from your webcam. It's a little more complicated than the
# other example, but it includes some basic performance tweaks to make things run a lot faster:
# 1. Process each video frame at 1/4 resolution (though still display it at full resolution)
# 2. Only detect faces in every other frame of video.
# PLEASE NOTE: This example requires OpenCV (the `cv2` library) to be installed only to read from your webcam.
# OpenCV is *not* required to use the face_recognition library. It's only required if you want to run this
# specific demo. If you have trouble installing it, try any of the other demos that don't require it instead.
# Get a reference to webcam #0 (the default one)
video_capture = cv2.VideoCapture(700)
# Load a sample picture and learn how to recognize it.
obama_image = face_recognition.load_image_file("leilei.jpg")
obama_face_encoding = face_recognition.face_encodings(obama_image)[0]
# Load a second sample picture and learn how to recognize it.
biden_image = face_recognition.load_image_file("leilei1.jpg")
biden_face_encoding = face_recognition.face_encodings(biden_image)[0]
# Create arrays of known face encodings and their names
known_face_encodings = [
obama_face_encoding,
biden_face_encoding
]
known_face_names = [
"LeiLei",
"LeiLei1"
]
# Initialize some variables
face_locations = []
face_encodings = []
face_names = []
process_this_frame = True
downsample_ratio = 0.5
upsample_ratio = 1/downsample_ratio
while True:
# Grab a single frame of video
ret, frame = video_capture.read()
# Resize frame of video to 1/4 size for faster face recognition processing
small_frame = cv2.resize(frame, (0, 0), fx=downsample_ratio, fy=downsample_ratio)
# Convert the image from BGR color (which OpenCV uses) to RGB color (which face_recognition uses)
rgb_small_frame = small_frame[:, :, ::-1]
# Only process every other frame of video to save time
if process_this_frame:
# Find all the faces and face encodings in the current frame of video
face_locations = face_recognition.face_locations(rgb_small_frame) # model="cnn" 默认hog更快
face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations)
face_names = []
for face_encoding in face_encodings:
# See if the face is a match for the known face(s)
matches = face_recognition.compare_faces(known_face_encodings, face_encoding)
name = "Unknown"
# # If a match was found in known_face_encodings, just use the first one.
# if True in matches:
# first_match_index = matches.index(True)
# name = known_face_names[first_match_index]
# Or instead, use the known face with the smallest distance to the new face
face_distances = face_recognition.face_distance(known_face_encodings, face_encoding)
best_match_index = np.argmin(face_distances)
if matches[best_match_index]:
name = known_face_names[best_match_index]
face_names.append(name)
process_this_frame = not process_this_frame
# Display the results
for (top, right, bottom, left), name in zip(face_locations, face_names):
# Scale back up face locations since the frame we detected in was scaled to 1/4 size
top *= upsample_ratio
right *= upsample_ratio
bottom *= upsample_ratio
left *= upsample_ratio
top = int(top)
right = int(right)
bottom = int(bottom)
left = int(left)
# Draw a box around the face
cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)
# Draw a label with a name below the face
cv2.rectangle(frame, (left, bottom - 35), (right, bottom), (0, 0, 255), cv2.FILLED)
font = cv2.FONT_HERSHEY_DUPLEX
cv2.putText(frame, name, (left + 6, bottom - 6), font, 1.0, (255, 255, 255), 1)
# Display the resulting image
cv2.imshow('Video', frame)
# Hit 'q' on the keyboard to quit!
if cv2.waitKey(1) & 0xFF == ord('q'):
break
# Release handle to the webcam
video_capture.release()
cv2.destroyAllWindows()