网络编程
位置:首页>> 网络编程>> Python编程>> python实现图片,视频人脸识别(dlib版)

python实现图片,视频人脸识别(dlib版)

作者:https://github.com/LeonPython/faceai/blob/master/doc/videoOpenCV.md  发布时间:2023-03-28 14:35:19 

标签:python,人脸,识别

图片人脸检测


#coding=utf-8

import cv2
import dlib

path = "img/meinv.png"
img = cv2.imread(path)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

#人脸分类器
detector = dlib.get_frontal_face_detector()
# 获取人脸检测器
predictor = dlib.shape_predictor(
 "C:\\Python36\\Lib\\site-packages\\dlib-data\\shape_predictor_68_face_landmarks.dat"
)

dets = detector(gray, 1)
for face in dets:
 shape = predictor(img, face) # 寻找人脸的68个标定点
 # 遍历所有点,打印出其坐标,并圈出来
 for pt in shape.parts():
   pt_pos = (pt.x, pt.y)
   cv2.circle(img, pt_pos, 2, (0, 255, 0), 1)
 cv2.imshow("image", img)

cv2.waitKey(0)
cv2.destroyAllWindows()

视频人脸检测


# coding=utf-8
import cv2
import dlib

detector = dlib.get_frontal_face_detector() #使用默认的人类识别器模型

def discern(img):
 gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
 dets = detector(gray, 1)
 for face in dets:
   left = face.left()
   top = face.top()
   right = face.right()
   bottom = face.bottom()
   cv2.rectangle(img, (left, top), (right, bottom), (0, 255, 0), 2)
   cv2.imshow("image", img)

cap = cv2.VideoCapture(0)
while (1):
 ret, img = cap.read()
 discern(img)
 if cv2.waitKey(1) & 0xFF == ord('q'):
   break

cap.release()
cv2.destroyAllWindows()

那么,OpenCV和Dlib的视频识别对比,有两个地方是不同的:

1.Dlib模型识别的准确率和效果要好于OpenCV;

2.Dlib识别的性能要比OpenCV差,使用视频测试的时候Dlib有明显的卡顿,但是OpenCV就好很多,基本看不出来;

来源:https://github.com/LeonPython/faceai/blob/master/doc/videoOpenCV.md

0
投稿

猜你喜欢

手机版 网络编程 asp之家 www.aspxhome.com