Dlib的人脸定位和人脸对齐

无bug代码搬运工

于 2023-05-16 18:47:15 发布

阅读量270

点赞数

CC 4.0 BY-SA版权

文章标签： opencv 计算机视觉 python

本文链接：https://blog.youkuaiyun.com/DoKiDoK/article/details/130711837

该代码示例展示了如何利用dlib库的面部检测器和形状预测器，结合OpenCV处理图像，从图片中检测并处理人脸。首先，它改变工作目录到face_recognition_models模型文件夹，然后加载必要的模型数据。接着，对输入图片进行颜色空间转换，并使用dlib的检测器找到人脸。通过形状预测器获取面部特征点，最后用OpenCV显示处理后的人脸切片。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import cv2
import dlib
import sys
import numpy as np
import os
print(os.getcwd())
os.chdir("C:\\Users\\333\\anaconda3\\Lib\\site-packages\\face_recognition_models\\models\\")
predicter_path =  'shape_predictor_68_face_landmarks.dat'
face_file_path =  'aq.jpg'
detector = dlib.get_frontal_face_detector()
sp = dlib.shape_predictor(predicter_path)
bgr_img = cv2.imread(face_file_path)
if bgr_img is None:
   print("Sorry, we could not load '{}' as an image".format(face_file_path))
   exit()
rgb_img = cv2.cvtColor(bgr_img, cv2.COLOR_BGR2RGB)
dets = detector(rgb_img, 1)
num_faces = len(dets)
if num_faces == 0:
   print("Sorry, there were no faces found in '{}'".format(face_file_path))
   exit()
faces = dlib.full_object_detections()
for det in dets:
   faces.append(sp(rgb_img, det))
images = dlib.get_face_chips(rgb_img, faces, size=320)
image_cnt = 0
for image in images:
    image_cnt += 1
    cv_rgb_image = np.array(image).astype(np.uint8)
    cv_bgr_image = cv2.cvtColor(cv_rgb_image, cv2.COLOR_RGB2BGR)
    cv2.imshow('%s'%(image_cnt), cv_bgr_image)
 
cv2.waitKey(0)
cv2.destroyAllWindows()