Python实现识别图片中的所有人脸并显示出来

发表于:2020-1-02 09:21  作者:佚名   来源:Linux公社

字体: | 上一篇 | 下一篇 |我要投稿 | 推荐标签: Python

  使用Python3实现识别图片中的所有人脸并显示出来,代码如下:
   # -*- coding: utf-8 -*-
  #  识别图片中的所有人脸并显示出来
  # filename : find_faces_in_picture.py
  from PIL import Image
  import face_recognition
  # 将jpg文件加载到numpy 数组中
  image = face_recognition.load_image_file("linuxidc.com.jpg")
  # 使用默认的给予HOG模型查找图像中所有人脸
  # 这个方法已经相当准确了,但还是不如CNN模型那么准确,因为没有使用GPU加速
  # 另请参见: find_faces_in_picture_cnn.py
  face_locations = face_recognition.face_locations(image)
  # 使用CNN模型
  # face_locations = face_recognition.face_locations(image, number_of_times_to_upsample=0, model="cnn")
  # 打印:我从图片中找到了 多少 张人脸
  print("I found {} face(s) in this photograph.".format(len(face_locations)))
  # 循环找到的所有人脸
  for face_location in face_locations:
  # 打印每张脸的位置信息
  top, right, bottom, left = face_location
  print("A face is located at pixel location Top: {}, Left: {}, Bottom: {}, Right: {}".format(top, left, bottom, right))
  # 指定人脸的位置信息,然后显示人脸图片
  face_image = image[top:bottom, left:right]
  pil_image = Image.fromarray(face_image)
  pil_image.show()
  
   # 或者执行python文件
  $ python3 www.linuxidc.com.py
   从图片中识别出10张人脸,并显示出来。
   I found 10 face(s) in this photograph.
  A face is located at pixel location Top: 445, Left: 1867, Bottom: 534, Right: 1957
  A face is located at pixel location Top: 544, Left: 643, Bottom: 619, Right: 718
  A face is located at pixel location Top: 478, Left: 1647, Bottom: 553, Right: 1722
  A face is located at pixel location Top: 504, Left: 126, Bottom: 594, Right: 215
  A face is located at pixel location Top: 536, Left: 395, Bottom: 611, Right: 469
  A face is located at pixel location Top: 544, Left: 1042, Bottom: 619, Right: 1116
  A face is located at pixel location Top: 553, Left: 818, Bottom: 627, Right: 892
  A face is located at pixel location Top: 511, Left: 1431, Bottom: 586, Right: 1506
  A face is located at pixel location Top: 564, Left: 1227, Bottom: 626, Right: 1289
  A face is located at pixel location Top: 965, Left: 498, Bottom: 1017, Right: 550
  如下图:

      本文内容不用于商业目的,如涉及知识产权问题,请权利人联系博为峰小编(021-64471599-8017),我们将立即处理

【福利】填问卷送精选测试礼包+接口测试课程!为测试行业做点事!

评 论

论坛新帖

顶部 底部


建议使用IE 6.0以上浏览器,800×600以上分辨率,法律顾问:上海瀛东律师事务所 张楠律师
版权所有 上海博为峰软件技术股份有限公司 Copyright©51testing.com 2003-2020, 沪ICP备05003035号
投诉及意见反馈:webmaster@51testing.com; 业务联系:service@51testing.com 021-64471599-8017

沪公网安备 31010102002173号

51Testing官方微信

51Testing官方微博

扫一扫 测试知识全知道