赞
踩
python 人脸识别,感觉有点棒棒滴~走,同志们让我们一起出发,咱们的目标是:星辰和大海
目录
首先我先介绍下我的环境 我是win10系统,Python 使用的是Anconda默认的python3.6.3版本!在这里一定要注意,我们使用的python3.6版本,原先的3.5版本由于各种坑,往死的填也填不完,所以我们就简单略过,用跟家快捷的方法,得到我们想要的结果(在这里我不得不夸下我自己,真是鬼才,嘎嘎嘎~)
准备环境之安装依赖
1. 配置安装好:dlib,这个模式轮子网站好像没有了,可以使用源码安装,或者自行百度亲~
2. 然后利用 pip install face_recongnition
轮子安装网站:点这里
当然在我们python3.6版本,不用考虑安装好自己的cmake环境和boost环境
然后直接利用pip install face_recongnition 就好!
然后直接打开我们的cmd进入python 交互界面输入
import face_recognition
如果没有报错就说明这个第三方软件包正常!
为了调用我们的程序我们需要在我们的 python里面安装opencv-python一遍我们调用我们的摄像头! 方便我们进行人工摄像头识别。
接下来让我们走进python face人脸识别,让我们尽情造作吧,看下下面的代码。(咳咳~如有侵权,请本人联系我,我马上改,嘿嘿~)
- 导入pil模块 ,可用命令安装 apt-get install python-Imaging
- from PIL import Image, ImageDraw
-
- # 导入face_recogntion模块,可用命令安装 pip install face_recognition
- import face_recognition
-
- # 将jpg文件加载到numpy 数组中
- image = face_recognition.load_image_file("abm.png")
- #查找图像中所有面部的所有面部特征
- face_landmarks_list = face_recognition.face_landmarks(image)
- print("I found {} face(s) in this photograph.".format(len(face_landmarks_list)))
- for face_landmarks in face_landmarks_list:
- #打印此图像中每个面部特征的位置
- facial_features = [
- 'chin',
- 'left_eyebrow',
- 'right_eyebrow',
- 'nose_bridge',
- 'nose_tip',
- 'left_eye',
- 'right_eye',
- 'top_lip',
- 'bottom_lip'
- ]
- for facial_feature in facial_features:
- print("The {} in this face has the following points: {}".format(facial_feature, face_landmarks[facial_feature]))
- #让我们在图像中描绘出每个人脸特征!
- pil_image = Image.fromarray(image)
- d = ImageDraw.Draw(pil_image)
- for facial_feature in facial_features:
- d.line(face_landmarks[facial_feature], width=5)
- pil_image.show()
- 运行结果如下:
运行结果如下:
正常识别,脸部轮廓
我们会识别图片的特征轮廓,也就是通过这个方法来识别面部特征
好的,距离我的目标又近了一步,下面乡亲们请看下方图片的各位美女,嘿嘿~,我想要通过代码去识别宝贝们儿的脸部,并很残忍的切割下来(放大看~)
代码实现:
- from PIL import Image
- import face_recognition
- #这是一个jpg的图片!
- image = face_recognition.load_image_file('jh.jpg')
-
- face_locations = face_recognition.face_locations(image)
-
- print('I found {} faces in this photograph'.format(len(face_locations)))
-
- for face_location in face_locations:
- 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.save(str(top)+'.jpg')
运行结果如下:
不的不说美女就是赏心悦目,不需要发型衬托五官,很棒~
下面我们通过输入一个图片分析它的特征来更好的识别人脸,对比接下来我注入进去的图片中的人脸看看是不是同一个人。
相当于咱们打卡系统:首先录入指纹(美女图片相当于录入的指纹),然后每天个人打卡对比已经录入的指纹(老马就相当于个人),通过奥巴马的脸部来对比美女们的面部
传递: 人脸图像(想传谁都行)
对比的:
- import face_recognition
- #加入奥巴马图片
- abm_image = face_recognition.load_image_file('abm.png')
- #这个是全体图片
- unknown_image = face_recognition.load_image_file('jh.jpg')
- #对图片的数据进行分析
- abm_face_encoding = face_recognition.face_encodings(abm_image)[0]
-
- print('chen_face_encoding:{}'.format(abm_face_encoding))
-
- unknown_face_encoding = face_recognition.face_encodings(unknown_image)[0]
-
- print('unknow_face_encoding:{}'.format(unknown_face_encoding))
-
- known_faces = [
-
- abm_face_encoding
- ]
-
- result = face_recognition.compare_faces(known_faces,unknown_face_encoding)
-
- print('result is {}'.format(result))
-
- print('这个面孔是奥巴马吗{}'.format(result[0]))
-
- print('这个未知的面孔是我们的新面孔吗{}'.format(not True in result ))
运行结果如下:
实战:利用咱们的摄像头来实现人工人脸检测!
现在我们使用调用摄像头方法,来实现脸部对比,前提你要把先录入几张照片,方便摄像头捕捉的脸部进行对比
- # -*- coding: utf-8 -*-
-
- # @Time : 2019/1/3 11:28
-
- # @Author : for
-
- # @File : 03_摄像头识别_test.py
-
- # @Software: PyCharm
-
- # -*- coding: utf-8 -*-
-
- # 摄像头头像识别
-
- import face_recognition
-
- import cv2
- video_capture = cv2.VideoCapture(0)
- # 本地图像
- chenduling_image = face_recognition.load_image_file("abm.png")
- chenduling_face_encoding = face_recognition.face_encodings(chenduling_image)[0]
- # 本地图像二
- sunyizheng_image = face_recognition.load_image_file("pj.jpg")
- sunyizheng_face_encoding = face_recognition.face_encodings(sunyizheng_image)[0]
- # 本地图片三
- zhangzetian_image = face_recognition.load_image_file("tlp.jpg")
- zhangzetian_face_encoding = face_recognition.face_encodings(zhangzetian_image)[0]
- # Create arrays of known face encodings and their names
- # 脸部特征数据的集合
- known_face_encodings = [
- chenduling_face_encoding,
- sunyizheng_face_encoding,
- zhangzetian_face_encoding
- ]
- # 人物名称的集合
- known_face_names = [
- "aobama",
- "pujing",
- "telangpu"
- ]
- face_locations = []
- face_encodings = []
- face_names = []
- process_this_frame = True
- while True:
- # 读取摄像头画面
- ret, frame = video_capture.read()
- # 改变摄像头图像的大小,图像小,所做的计算就少
- small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25)
- # opencv的图像是BGR格式的,而我们需要是的RGB格式的,因此需要进行一个转换。
- rgb_small_frame = small_frame[:, :, ::-1]
- # Only process every other frame of video to save time
- if process_this_frame:
- # 根据encoding来判断是不是同一个人,是就输出true,不是为flase
- face_locations = face_recognition.face_locations(rgb_small_frame)
- face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations)
- face_names = []
- for face_encoding in face_encodings:
- # 默认为unknown
- matches = face_recognition.compare_faces(known_face_encodings, face_encoding)
- print(matches)
- name = "Unknown"
- if True in matches:
- first_match_index = matches.index(True)
- name = known_face_names[first_match_index]
- face_names.append(name)
- process_this_frame = not process_this_frame
- # 将捕捉到的人脸显示出来
- 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 *= 4
- right *= 4
- bottom *= 4
- left *= 4
- # 矩形框
- cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)
- #加上标签
- 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
- cv2.imshow('monitor', frame)
- # 按Q退出
- if cv2.waitKey(1) & 0xFF == ord('q'):
- break
- video_capture.release()
- cv2.destroyAllWindows()
运行结果如下:
正常识别
哎呦~出来了,大帝的名字,请大家忽略我的破手机~
在这里我们要特别提醒下,这个模块对于亚洲的人脸的识别还是不太给力,不过可以通过训练增加准确度,溜了溜了~
修仙去了,再见来不及握手~
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。