验证dlib库：人脸关键点标定

最新推荐文章于 2025-03-03 21:25:22 发布

hfutyfl802

最新推荐文章于 2025-03-03 21:25:22 发布

阅读量570

点赞数

分类专栏： dlib库文章标签：人脸对齐

本文链接：https://blog.youkuaiyun.com/hfutyfl802/article/details/94754994

版权

上一篇已安装dlib库，接下来要验证一下调用里面的函数是否可行。
参考博文地址https://blog.youkuaiyun.com/gaoyueace/article/details/79592444
#encoding=utf-8

import cv2
import dlib

def main():
PREDICTOR_PATH = “shape_predictor_68_face_landmarks.dat”
predictor = dlib.shape_predictor(PREDICTOR_PATH)
detector = dlib.get_frontal_face_detector()
color = (0, 255, 0)
# ori_img = cv2.imread(r’F:\py_process\face_aligment\300W\01_Indoor\indoor_001.png’)
ori_img = cv2.imread(“indoor_002.png”)
gray_img = cv2.cvtColor(ori_img, cv2.COLOR_BGR2GRAY) # use the gray
# face_cascade = cv2.CascadeClassifier(r’./haarcascade_frontalface_default.xml’)
# faces = face_cascade.detectMultiScale(gray_img, scaleFactor=1.15, minNeighbors=5, minSize=(5, 5))
faces = detector(gray_img, 1)
for k, d in enumerate(faces):
cv2.rectangle(ori_img, (d.left(), d.top()), (d.right(), d.bottom()), (255, 255