基于人脸识别的课堂考勤系统
课堂考勤是保证学生出勤率的重要手段之一，也是学生课程成绩重要的组成部分，课堂考勤可以很好的监督学生，从而确保了课堂的教学质量。目前主要的考勤手段仍然是教师人工点名或者随机抽查的方式，这种人工点名的方式不仅占用上课时间而且无法解决学生的早退、代签和旷课等现象，无法很好的对学生考勤做到监管．市面上也存在着各种各样的考勤机，但是由于硬件和部署的成本较高，无法很好的解决考勤问题。
为了解决上述的问题，本文采用人脸识别技术，设计实现了一个适合日常课堂考勤的自动化人脸识别考勤系统，主要研究了该系统的设计与功能的实现。阐述了人脸识别技术的基本概念、发展阶段和基本方法，分析了传统考勤方式的不足，同时也介绍了国内外相关技术的发展历史和研究成果。接着详细介绍了活体检测、人脸检测及人脸识别的主要方法。然后根据考勤系统在功能和性能上的各种需求，进行软件架构的设计。最终整体介绍系统的功能以及测试内容，并展示了相应的GUI界面。
利用python实现人脸识别技术是基于mtcnn和facenet考勤
实现了人脸大角度识别
import cv2
import os
import numpy as np
from net.mtcnn import mtcnn
import utils.utils as utils
from net.inception import InceptionResNetV1
import time
from dateutil.parser import parse
font = cv2.FONT_HERSHEY_COMPLEX
def seekopp(list_2,i):
for j in range(i-1,-1,-1):
if list_2[j]==0:
continue
elif list_2[j]>0:
return 1
elif list_2[j]<0:
return 0
def local_maximum(list_1):
a=len(list_1)
if a==0:
return 'error'
if a==1:
return list_1
if a==2:
if list_1[0]>list_1[1]:
return list_1[0]
elif list_1[0]2:
list_2=[]
index_1=[]
for i in range(0,a-1):
list_2.append(list_1[i+1]-list_1[i])
b=len(list_2)
if list_2[0]<0:
index_1.append(0)
for i in range(0,b-1):
if list_2[i+1]<0:
if list_2[i]>0:
index_1.append(i+1)
elif list_2[i]==0:
if seekopp(list_2,i):
index_1.append(i+1)
else:
continue
else:
continue
list_3=[]
for i in index_1:
list_3.append(list_1[i])
return list_3
def transform(t1,t2):
timeArray1 = time.localtime(t1)
timeArray2 = time.localtime(t2)
time_1 = time.strftime("%Y-%m-%d %H:%M:%S", timeArray1)
time_2 = time.strftime("%Y-%m-%d %H:%M:%S", timeArray2)
date1 = parse(time_1)
date2 = parse(time_2)
result = int((date2 - date1).total_seconds())
return result
class face_rec():
time = 0
def __init__(self):
# 创建mtcnn对象
# 检测图片中的人脸
self.mtcnn_model = mtcnn()
# 门限函数
self.threshold = [0.5,0.8,0.9]
# 载入facenet
# 将检测到的人脸转化为128维的向量
self.facenet_model = InceptionResNetV1()
# model.summary()
model_path = './model_data/facenet_keras.h5'
self.facenet_model.load_weights(model_path)
#-----------------------------------------------#
# 对数据库中的人脸进行编码
# known_face_encodings中存储的是编码后的人脸
# known_face_names为人脸的名字
#-----------------------------------------------#
face_list = os.listdir("face_dataset")
self.known_face_encodings=[]
self.known_face_names=[]
self.time_list=[]
self_learn_time = 0
self.total_time = []
for face in face_list:
name = face.split(".")[0]
img = cv2.imread("./face_dataset/"+face)
img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
# 检测人脸
rectangles = self.mtcnn_model.detectFace(img, self.threshold)
# 转化成正方形
rectangles = utils.rect2square(np.array(rectangles))
# facenet要传入一个160x160的图片
rectangle = rectangles[0]
# 记下他们的landmark
landmark = (np.reshape(rectangle[5:15],(5,2)) - np.array([int(rectangle[0]),int(rectangle[1])]))/(rectangle[3]-rectangle[1])*160
crop_img = img[int(rectangle[1]):int(rectangle[3]), int(rectangle[0]):int(rectangle[2])]
crop_img = cv2.resize(crop_img,(160,160))
new_img,_ = utils.Alignment_1(crop_img,landmark)
new_img = np.expand_dims(new_img,0)
# 将检测到的人脸传入到facenet的模型中，实现128维特征向量的提取
face_encoding = utils.calc_128_vec(self.facenet_model,new_img)
self.known_face_encodings.append(face_encoding)
self.known_face_names.append(name)
def recognize(self,draw):
#-----------------------------------------------#
# 人脸识别
# 先定位，再进行数据库匹配
#-----------------------------------------------#
height,width,_ = np.shape(draw)
draw_rgb = cv2.cvtColor(draw,cv2.COLOR_BGR2RGB)
# 检测人脸
rectangles = self.mtcnn_model.detectFace(draw_rgb, self.threshold)
'''
if len(rectangles)==0:
font = cv2.FONT_HERSHEY_SIMPLEX
if time_flag==0:
print('首次执行！')
first_time = time.time()
t = transform(int(first_time),int(time.time()))
cv2.putText(draw, "Focus on time:"+str(t)+" s", (250, 40), font, 0.6, (0, 255, 0), 1, cv2.LINE_AA)
time_flag==1
return
else:
print('第二次执行！')
t = transform(int(first_time),int(time.time()))
cv2.putText(draw, "Focus on time:"+str(t)+" s", (250, 40), font, 0.6, (0, 255, 0), 1, cv2.LINE_AA)
return
'''
if len(rectangles)==0:
self.time_list.append(time.time())
font = cv2.FONT_HERSHEY_SIMPLEX
t = transform(self.time_list[0],self.time_list[-1])
#print(t,type(t))
cv2.putText(draw, "Noface", (40, 40), font, 0.6, (0, 255, 0), 1, cv2.LINE_AA)
cv2.putText(draw, "Focus on time:"+str(t)+" s", (350, 40), font, 0.6, (0, 255, 0), 1, cv2.LINE_AA)
#print(self.total_time,type(self.total_time))
if len(self.total_time)==0:
self.total_time.append(t)
elif self.total_time[-1]<= t:
self.total_time.pop()
self.total_time.append(t)
elif self.total_time[-1]>= t:
self.total_time.append(t)
else:
pass
return draw,self.total_time
self.time_list.clear()
# 转化成正方形
rectangles = utils.rect2square(np.array(rectangles,dtype=np.int32))
rectangles[:,0] = np.clip(rectangles[:,0],0,width)
rectangles[:,1] = np.clip(rectangles[:,1],0,height)
rectangles[:,2] = np.clip(rectangles[:,2],0,width)
rectangles[:,3] = np.clip(rectangles[:,3],0,height)
#-----------------------------------------------#
# 对检测到的人脸进行编码
#-----------------------------------------------#
face_encodings = []
for rectangle in rectangles:
landmark = (np.reshape(rectangle[5:15],(5,2)) - np.array([int(rectangle[0]),int(rectangle[1])]))/(rectangle[3]-rectangle[1])*160
crop_img = draw_rgb[int(rectangle[1]):int(rectangle[3]), int(rectangle[0]):int(rectangle[2])]
crop_img = cv2.resize(crop_img,(160,160))
new_img,_ = utils.Alignment_1(crop_img,landmark)
new_img = np.expand_dims(new_img,0)
face_encoding = utils.calc_128_vec(self.facenet_model,new_img)
face_encodings.append(face_encoding)
face_names = []
for face_encoding in face_encodings:
# 取出一张脸并与数据库中所有的人脸进行对比，计算得分
matches = utils.compare_faces(self.known_face_encodings, face_encoding, tolerance = 0.9)
name = "Unknown"
# 找出距离最近的人脸
face_distances = utils.face_distance(self.known_face_encodings, face_encoding)
# 取出这个最近人脸的评分
best_match_index = np.argmin(face_distances)
if matches[best_match_index]:
name = self.known_face_names[best_match_index]
face_names.append(name)
rectangles = rectangles[:,0:4]
#-----------------------------------------------#
# 画框~!~
#-----------------------------------------------#
for (left, top, right, bottom), name in zip(rectangles, face_names):
cv2.rectangle(draw, (left, top), (right, bottom), (0, 0, 255), 2)
font = cv2.FONT_HERSHEY_SIMPLEX
cv2.putText(draw, name, (left , bottom - 15), font, 0.75, (255, 255, 255), 2)
if name!='Unknown':
cv2.putText(draw, 'name:'+name, (10, 20), font, 0.6, (0, 255, 0), 1, cv2.LINE_AA)
cv2.putText(draw, "state:"+"clock on", (10, 60), font, 0.6, (0, 255, 0), 1, cv2.LINE_AA)
cv2.putText(draw, "Please concentrate on your study!", (200, 40), font, 0.6, (0, 0, 255), 1, cv2.LINE_AA)
else:
cv2.putText(draw, 'name:'+name, (10, 20), font, 0.6, (0, 255, 0), 1, cv2.LINE_AA)
cv2.putText(draw, "state:"+"clock out failed", (10, 60), font, 0.6, (0, 255, 0), 1, cv2.LINE_AA)
cv2.putText(draw, "Please add face!", (300, 40), font, 0.6, (0, 0, 255), 1, cv2.LINE_AA)
return draw,self.total_time
if __name__ == "__main__":
dududu = face_rec()
video_capture = cv2.VideoCapture(0)
while True:
ret, draw = video_capture.read()
dududu.recognize(draw)
cv2.imshow('Video', draw)
if cv2.waitKey(20) & 0xFF == ord('q'):
break
video_capture.release()
cv2.destroyAllWindows()
欢迎分享，转载请注明来源：内存溢出
微信扫一扫
支付宝扫一扫
评论列表（0条）