Fer2013 数据集人脸表情识别 详细代码
本文将从数据集、模型训练、模型实践应用（AI模型落地场景实际应用）几个部分完整讲解基于Fer2013 数据集的人脸表情识别项目，最终项目实现效果：
通过人体姿态（百度AI姿态识别接口）和表情识别模型综合评估学生听课效果
其中涉及理论部分请详见基于卷积网络的人脸表情识别及其应用（毕业论文）
github 链接 https://github.com/cucohhh/Expression-recognition/
github 项目地址
文章目录
一、卷积网络模型搭建训练代码
数据集载入
fer2013 数据集下载链接Fer2013数据集
数据集已经将训练集和测试集划分好，训练集两万多张图片，测试集三千张图片
excel格式 非常方便读取（使用pandas 库）
import pandas as pd
import numpy as np
##path 为数据集路径
def dataRead(path, x_data, y_data, data_size_begin, data_size_end):
# 加载训练集
train_data = pd.read_csv(path)
num_of_instances = len(train_data)
min_data = train_data.iloc[data_size_begin:data_size_end]
pixels = min_data['pixels']
emotions = min_data['emotion']
print("数据集加载完成，数据集大小")
print(len(pixels))
# 表情类别数
num_classes = 7
# x_train, y_train = [], []
# x_test, y_test = [], []
import os
import keras
for emotion, img in zip(emotions, pixels):
try:
emotion = keras.utils.to_categorical(emotion, num_classes) # 独热向量编码
val = img.split(" ")
pixels = np.array(val, 'float32')
x_data.append(pixels)
y_data.append(emotion)
except:
print("111")
print("表情 分类完成 finish")
print(len(x_data))
x_data = np.array(x_data)
y_data = np.array(y_data)
x_data = x_data.reshape(-1, 48, 48, 1)
print("数据集 格式转换完成")
print(len(x_data))
res = [];
res.append(x_data)
res.append(y_data)
return res;
模型训练、评估
模型的训练环境 ：keras库 + TensorFlow1.1.5 版本
由于TensorFlow 版本的更新 keras库的导入也许需要部分调整，请自行修改
import numpy as np
import pandas as pd
from keras.layers import LeakyReLU
from keras import regularizers
from data_Reader import dataRead
# 加载训练集
path_train = "C:\\Users\\Administrator\\PycharmProjects\\pythonProject\\fer2013原-csv\\train.csv"
train_data_x =[];
train_data_y =[];
train_size_begin = 0;
train_size_end = 30000;
train = dataRead(path_train,train_data_x,train_data_y,train_size_begin,train_size_end)
# 加载测试集
path_test = "C:\\Users\\Administrator\\PycharmProjects\\pythonProject\\fer2013原-csv\\test.csv"
test_data_x=[]
test_data_y=[]
test_size_begin = 0;
test_size_end = 10000;
test = dataRead(path_test,test_data_x,test_data_y,test_size_begin,test_size_end)
from keras.models import Sequential
from keras.layers import Conv2D, MaxPool2D, AveragePooling2D, Activation, Dropout, Flatten, Dense, BatchNormalization
from keras.optimizers import Adam
from keras.preprocessing.image import ImageDataGenerator
batch_size = 256;
epochs = 40;
model = Sequential()
# 第一层卷积层
model.add(Conv2D(input_shape=(48, 48, 1), filters=32, kernel_size=3,strides=1 ,padding='same'))
#kernel_regularizer=regularizers.l2(0.01)))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Conv2D(filters=32, kernel_size=3,strides=1, ))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPool2D(pool_size=2, strides=2))
model.add(Dropout(0.5))
# 第二层卷积层
model.add(Conv2D(filters=64, kernel_size=3,strides=1 , ))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Conv2D(filters=64, kernel_size=3, strides=1 ,))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPool2D(pool_size=2, strides=2))
model.add(Dropout(0.5))
# 第三层卷积层
model.add(Conv2D(filters=128, kernel_size=3,strides=1 , padding='same', ))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Conv2D(filters=128, kernel_size=3,strides=1 , padding='same',))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(AveragePooling2D(pool_size=2, strides=2)) ## 进入全连接层时采用 平均池化层
model.add(Dropout(0.5))
# 全连接层
model.add(Flatten())
model.add(Dense(1024, activation='relu', ))
model.add(Dropout(0.2))
model.add(Dense(1024, activation='relu', ))
model.add(Dropout(0.2))
model.add(Dense(512, activation='relu' ,))
model.add(Dropout(0.2))
#softmax层
model.add(Dense(7, activation='softmax'))
# 进行训练
model.compile(loss='categorical_crossentropy', optimizer=Adam(), metrics=['accuracy'])
history = model.fit(train[0], train[1], batch_size=batch_size, epochs=epochs, validation_data=(test[0],test[1]),shuffle='true')
train_score = model.evaluate(train[0], train[1], verbose=0)
print('Train loss:', train_score[0])
print('Train accuracy:', 100 * train_score[1])
model.save('my_base_model_relu2_Dropout_Normalization.h5')
from paint_Process import paint_process
name = "my_base_model_relu2_Dropout_Normalization"
paint_process(history, name);
如何载入训练一半的模型继续训练，
每次都从新训练代码很麻烦，也很浪费时间，所以在此提供一个继续训练的代码
from keras import regularizers
from data_Reader_T import dataRead_T
from data_Reader import dataRead
# 加载训练集
path_train = "C:\\Users\\Administrator\\PycharmProjects\\pythonProject\\fer2013原-csv\\train.csv"
train_data_x =[];
train_data_y =[];
train_size_begin = 0;
train_size_end = 30000;
train = dataRead(path_train,train_data_x,train_data_y,train_size_begin,train_size_end)
# 加载测试集
path_test = "C:\\Users\\Administrator\\PycharmProjects\\pythonProject\\fer2013原-csv\\test.csv"
test_data_x=[]
test_data_y=[]
test_size_begin = 0;
test_size_end = 10000;
test = dataRead(path_test,test_data_x,test_data_y,test_size_begin,test_size_end)
from keras.models import Sequential
from keras.layers import Conv2D, MaxPool2D, Activation, Dropout, Flatten, Dense, BatchNormalization
from keras.optimizers import Adam
from keras.preprocessing.image import ImageDataGenerator
batch_size = 256;
epochs = 30;
from keras.models import load_model
model = load_model('C:\\Users\\Administrator\\PycharmProjects\\pythonProject\\trian_or_Test\\my_base_model_relu2_Dropout_Normalization.h5')
# 进行训练
model.compile(loss='categorical_crossentropy', optimizer=Adam(), metrics=['accuracy'])
history = model.fit(train[0], train[1], batch_size=batch_size, epochs=epochs, validation_data=(test[0],test[1]),shuffle='true')
train_score = model.evaluate(train[0], train[1], verbose=0)
print('Train loss:', train_score[0])
print('Train accuracy:', 100 * train_score[1])
model.save('my_base_model_relu2_L2_2twice.h5')
from paint_Process import paint_process
name = "my_base_model_relu2_L2_2twice"
paint_process(history, name);
训练过程参数绘制
import matplotlib.pyplot as plt
def paint_process(history,name):
epoch = len(history.history['loss']) #迭代的次数
plt.plot(range(epoch), history.history['loss'], label='loss')
plt.plot(range(epoch), history.history['accuracy'], label='train_acc')
plt.plot(range(epoch), history.history['val_accuracy'], label='val_acc')
plt.plot(range(epoch), history.history['val_loss'], label='val_loss')
plt.legend()
path = "C:\\Users\\Administrator\\PycharmProjects\\pythonProject\\trian_image\\"
plt.savefig(path+name);
plt.show()
人脸表情识别功能落地实践
这里用到了OpenCV库来获取笔记本摄像头，得到实时的视频图像数据，
使用的是OpenCV 4.2版本以及它的扩展库，
实现过程：
- 获取到视频数据
- 导入卷积网络模型对图像数据实时分析
- 绘制分析的结果到图像中
最终效果：
这里展示的是单个图片的识别效果（由于懒惰，不知道怎么添加gif），代码可以完成实时视频数据的分析（实际循环识别判断多帧图片）
import cv2
import numpy as np
import os
from tensorflow import keras
def resize_image(image):
if len(image) != 0:
image = cv2.resize(image, (48, 48))
#print(image.shape)
# ima=change_image_channels(image)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
#print(gray.shape)
x = np.array(gray).reshape(48, 48, 1)
x = np.expand_dims(x, axis=0)
return x
def displayText(img, result):
text1 = "W:" + str(result[0][0])
cv2.putText(img, text1, (40, 50), cv2.FONT_HERSHEY_COMPLEX, 1.0, (10, 10, 210), 2)
text2 = "W:" + str(result[0][1])
cv2.putText(img, text2, (40, 80), cv2.FONT_HERSHEY_PLAIN, 2.0, (0, 0, 255), 2)
text3 = "W:" + str(result[0][2])
cv2.putText(img, text3, (40, 110), cv2.FONT_HERSHEY_PLAIN, 2.0, (0, 0, 255), 2)
text4 = "W:" + str(result[0][3])
cv2.putText(img, text4, (40, 140), cv2.FONT_HERSHEY_PLAIN, 2.0, (0, 0, 255), 2)
text5 = "W:" + str(result[0][4])
cv2.putText(img, text5, (40, 170), cv2.FONT_HERSHEY_PLAIN, 2.0, (0, 0, 255), 2)
text6 = "W:" + str(result[0][5])
cv2.putText(img, text6, (40, 200), cv2.FONT_HERSHEY_PLAIN, 2.0, (0, 0, 255), 2)
text7 = "W:" + str(result[0][6])
cv2.putText(img, text7, (40, 230), cv2.FONT_HERSHEY_PLAIN, 2.0, (0, 0, 255), 2)
def displayEmotion(img, result,x,y,w,h):
a = max(result)
l = a.tolist()
c = l.index(max(l))
if c == 0:
text = "anger:" #+ str(result[0][0])
if c == 1:
text = "disgust:" #+ str(result[0][1])
if c == 2:
text = "fear:" #+ str(result[0][2])
if c == 3:
text = "happy:" #+ str(result[0][3])
if c == 4:
text = "sad:" #+ str(result[0][4])
if c == 5:
text = "surprised:" #+ str(result[0][5])
if c == 6:
text = "normal:" #+ str(result[0][6])
cv2.rectangle(img, (x-5, y), (x+w+5, y-20), (228, 181, 240), thickness=-1)
cv2.putText(img, text, (x+20, y), cv2.FONT_HERSHEY_PLAIN, 2.0, (0, 0, 0), 2)
def findMax(result):
a = max(result)
l = a.tolist()
c = l.index(max(l))
if c == 0:
return "anger"
if c == 1:
return "disgust"
if c == 2:
return "fear"
if c == 3:
return "happy"
if c == 4:
return "sad"
if c == 5:
return "surprised"
if c == 6:
return "normal"
# from keras.preprocessing import image
from matplotlib.pyplot import imshow
face_cascade = cv2.CascadeClassifier(r'C:\ProgramData\Anaconda3\envs\tfenv\Lib\site-packages\cv2\data\haarcascade_frontalface_alt.xml')
# face_cascade.load("D:\Build\OpenCV\opencv-4.1.2\modules\core\src\persistence_xml\haarcascade_frontalface_alt.xml")
# eye_cascade = cv2.CascadeClassifier("D:\face_recognized\haarcascade_eye.xml")
model2 = keras.models.load_model("../Model/my_VGG_11_model_10000_256_100.h5")
cap = cv2.VideoCapture(-1)
result=""
def facial_expression_check(cap):
ret, img = cap.read()
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.1, 5)
result=[]
#cv2.imshow("img", img)
if len(faces) > 0:
for faceRect in faces:
x, y, w, h = faceRect
image = img[y - 10: y + h + 10, x - 10: x + w + 10]
image = resize_image(image)
result = model2.predict(image)
# print(result)
# print(model2.predict(image))
cv2.rectangle(img, (x-5, y-5), (x + w+5, y + h+5), (228, 181, 240), 2)
displayEmotion(img, result, x, y, w, h)
roi_gray = gray[y:y + h // 2, x:x + w]
roi_color = img[y:y + h // 2, x:x + w]
# eyes = eye_cascade.detectMultiScale(roi_gray,1.1,1,cv2.CASCADE_SCALE_IMAGE,(2,2))
# for (ex,ey,ew,eh) in eyes:
# cv2.rectangle(roi_color,(ex,ey),(ex+ew,ey+eh),(0,255,0),2)
cv2.namedWindow("facial_expression",0)
cv2.resizeWindow("facial_expression", 300, 200);
cv2.imshow("facial_expression", img)
x='Noface'
if len(result)!=0:
x = findMax(result)
return x
def main():
while True:
facial_expression_check(cap)
if cv2.waitKey(10) & 0xFF == ord('q'):
break
二、PostureCheck(百度AI接口)
百度AI接口调用过程
-
在百度智慧AI平台注册账号
-
选择人体姿态识别功能、创建应用、下载官方提供的API库
-
记录你的
APP_ID = ’ ’
API_KEY = ‘’
SECRET_KEY = ’ ’ -
代码调用（此处同样使用opencv获取图像数据）
-
绘制识别到的重要人体姿态关节点
-
此处可以查询官网详细了解更多的接口使用方式
此处主要对环保双臂和高低肩（对学生状态影响较大的动作、具体详见博文基于卷积网络的人脸表情识别）进行了识别，读者可以根据自己实际需要自行修改其他动作
from aip import AipBodyAnalysis
from Test import draw_line
from datetime import datetime
import math
import cv2
import time
from tensorflow import keras
from face_check import facial_expression_check
from DocumentGeneration import generateDocument
from SMTP_send import SMTPSend
face_cascade = cv2.CascadeClassifier(
r'C:\ProgramData\Anaconda3\envs\tfenv\Lib\site-packages\cv2\data\haarcascade_frontalface_alt.xml')
model2 = keras.models.load_model("C:\\Users\\Administrator\\PycharmProjects\\pythonProject\\trian_or_Test\\my_base_model6.h5")
expression = {'anger': 0, 'disgust': 0, 'fear': 0, 'happy': 0, 'sad': 0, 'surprised': 0, 'normal': 0, 'Noface': 0}
posture = {'cross_arms': 0, 'shoulder_drop': 0}
# total = 0 #总共表情和姿态的检测次数
# 将opencv读取图片转换成字符串
def ChangeToString(image):
# image_str = cv2.imencode('.jpg',image)[1].tostring();
print("图片转字节中...")
a = datetime.now();
image_str = cv2.imencode('.jpg', image)[1].tobytes();
b = datetime.now();
changeTime = (b - a).seconds;
print(changeTime);
return image_str;
def BodyAnalysis(img_str):
print("分析数据中...");
""" 你的 APPID AK SK """
APP_ID = '23411049'
API_KEY = 'LNCh4Tz8Yq5LaMGj2qWLFH9Q'
SECRET_KEY = 'f4FEXEHZQ2T0HVkK4GXDGPZibZHjrch5 '
client = AipBodyAnalysis(APP_ID, API_KEY, SECRET_KEY)
""" 读取图片 """
image = img_str;
""" 调用人体关键点识别 """
a = datetime.now();
result = client.bodyAnalysis(image);
b = datetime.now();
bodyAnalysisTime = (b - a).seconds;
print(bodyAnalysisTime);
return result;
# 分析是否交叉手臂 判断手腕关键点的横坐标
def cross_arms(left_wrist, right_wrist):
if left_wrist <= right_wrist:
posture['cross_arms'] = posture['cross_arms'] + 1;
return True
else:
return False
# 分析肩部高低差，左右肩部关键点纵坐标差不能大于50px
def shoulder_drop(left_shoulder, right_shoulder):
if math.fabs(left_shoulder - right_shoulder) > 20:
posture['shoulder_drop'] = posture['shoulder_drop'] + 1;
return True
else:
return False
def Body_posture_check(frame):
img_str = ChangeToString(frame);
my_result = BodyAnalysis(img_str);
person = my_result['person_info'][0]['body_parts'];
draw_line(person, frame)
cv2.namedWindow("body_posture", 0)
cv2.resizeWindow("body_posture", 300, 200)
cv2.imshow("body_posture", frame)
cross_arms_count = 0
shoulder_drop_count = 0
if cross_arms(int(person['left_wrist']['x']), int(person['right_wrist']['x'])):
print("存在交叉双臂动作")
cross_arms_count = cross_arms_count + 1
if shoulder_drop(int(person['left_shoulder']['y']), int(person['right_shoulder']['y'])):
print("左右肩部高低差过大")
shoulder_drop_count = shoulder_drop_count + 1
# 设置摄像头捕获
cap = cv2.VideoCapture(0);
flag = True
def GetView():
print("dainji")
var = 30; # 每1000毫秒检测一次
person = None;
my_result = None;
total = 0;
while flag:
var = var + 1;
ret, frame = cap.read();
# cv2.imshow("image", frame)
# img_str = ChangeToString(frame);
# my_result = BodyAnalysis(img_str);
# person = my_result['person_info'][0]['body_parts'];
result = facial_expression_check(cap)
facial_expression_statistics(result)
total = total + 1
if (var % 30 == 0):
# img_str = ChangeToString(frame);
# my_result = BodyAnalysis(img_str);
# person = my_result['person_info'][0]['body_parts'];
# draw_line(person, frame);
# cv2.imshow("body_posture", frame)
Body_posture_check(frame)
if cv2.waitKey(10) & 0xff == ord('q'):
print(expression)
print(posture)
print(var)
#cap.release()
cv2.destroyAllWindows()
generateDocument(expression, posture, total)
time.sleep(2)
SMTPSend()
break
return
三、 模型落地实现对学生听课状态的评估
FerCheck + PostureCheck
FerCheck .py 包含人脸检测+表情识别功能
import cv2
import numpy as np
import os
from tensorflow import keras
def resize_image(image):
if len(image) != 0:
image = cv2.resize(image, (48, 48))
#print(image.shape)
# ima=change_image_channels(image)
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
#print(gray.shape)
x = np.array(gray).reshape(48, 48, 1)
x = np.expand_dims(x, axis=0)
return x
def displayText(img, result):
text1 = "W:" + str(result[0][0])
cv2.putText(img, text1, (40, 50), cv2.FONT_HERSHEY_COMPLEX, 1.0, (10, 10, 210), 2)
text2 = "W:" + str(result[0][1])
cv2.putText(img, text2, (40, 80), cv2.FONT_HERSHEY_PLAIN, 2.0, (0, 0, 255), 2)
text3 = "W:" + str(result[0][2])
cv2.putText(img, text3, (40, 110), cv2.FONT_HERSHEY_PLAIN, 2.0, (0, 0, 255), 2)
text4 = "W:" + str(result[0][3])
cv2.putText(img, text4, (40, 140), cv2.FONT_HERSHEY_PLAIN, 2.0, (0, 0, 255), 2)
text5 = "W:" + str(result[0][4])
cv2.putText(img, text5, (40, 170), cv2.FONT_HERSHEY_PLAIN, 2.0, (0, 0, 255), 2)
text6 = "W:" + str(result[0][5])
cv2.putText(img, text6, (40, 200), cv2.FONT_HERSHEY_PLAIN, 2.0, (0, 0, 255), 2)
text7 = "W:" + str(result[0][6])
cv2.putText(img, text7, (40, 230), cv2.FONT_HERSHEY_PLAIN, 2.0, (0, 0, 255), 2)
def displayEmotion(img, result,x,y,w,h):
a = max(result)
l = a.tolist()
c = l.index(max(l))
if c == 0:
text = "anger:" #+ str(result[0][0])
if c == 1:
text = "disgust:" #+ str(result[0][1])
if c == 2:
text = "fear:" #+ str(result[0][2])
if c == 3:
text = "happy:" #+ str(result[0][3])
if c == 4:
text = "sad:" #+ str(result[0][4])
if c == 5:
text = "surprised:" #+ str(result[0][5])
if c == 6:
text = "normal:" #+ str(result[0][6])
cv2.rectangle(img, (x-5, y), (x+w+5, y-20), (228, 181, 240), thickness=-1)
cv2.putText(img, text, (x+20, y), cv2.FONT_HERSHEY_PLAIN, 2.0, (0, 0, 0), 2)
def findMax(result):
a = max(result)
l = a.tolist()
c = l.index(max(l))
if c == 0:
return "anger"
if c == 1:
return "disgust"
if c == 2:
return "fear"
if c == 3:
return "happy"
if c == 4:
return "sad"
if c == 5:
return "surprised"
if c == 6:
return "normal"
# from keras.preprocessing import image
from matplotlib.pyplot import imshow
face_cascade = cv2.CascadeClassifier(r'C:\ProgramData\Anaconda3\envs\tfenv\Lib\site-packages\cv2\data\haarcascade_frontalface_alt.xml')
# face_cascade.load("D:\Build\OpenCV\opencv-4.1.2\modules\core\src\persistence_xml\haarcascade_frontalface_alt.xml")
# eye_cascade = cv2.CascadeClassifier("D:\face_recognized\haarcascade_eye.xml")
model2 = keras.models.load_model("../Model/my_VGG_11_model_10000_256_100.h5")
cap = cv2.VideoCapture(-1)
result=""
def facial_expression_check(cap):
ret, img = cap.read()
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.1, 5)
result=[]
#cv2.imshow("img", img)
if len(faces) > 0:
for faceRect in faces:
x, y, w, h = faceRect
image = img[y - 10: y + h + 10, x - 10: x + w + 10]
image = resize_image(image)
result = model2.predict(image)
# print(result)
# print(model2.predict(image))
cv2.rectangle(img, (x-5, y-5), (x + w+5, y + h+5), (228, 181, 240), 2)
displayEmotion(img, result, x, y, w, h)
roi_gray = gray[y:y + h // 2, x:x + w]
roi_color = img[y:y + h // 2, x:x + w]
# eyes = eye_cascade.detectMultiScale(roi_gray,1.1,1,cv2.CASCADE_SCALE_IMAGE,(2,2))
# for (ex,ey,ew,eh) in eyes:
# cv2.rectangle(roi_color,(ex,ey),(ex+ew,ey+eh),(0,255,0),2)
cv2.namedWindow("facial_expression",0)
cv2.resizeWindow("facial_expression", 300, 200);
cv2.imshow("facial_expression", img)
x='Noface'
if len(result)!=0:
x = findMax(result)
return x
def main():
while True:
facial_expression_check(cap)
if cv2.waitKey(10) & 0xFF == ord('q'):
break
PostureCheck.py 姿态检测（调用了ferCheck中部分函数）
rom aip import AipBodyAnalysis
from Test import draw_line
from datetime import datetime
import math
import cv2
import time
from tensorflow import keras
from face_check import facial_expression_check
from DocumentGeneration import generateDocument
from SMTP_send import SMTPSend
face_cascade = cv2.CascadeClassifier(
r'C:\ProgramData\Anaconda3\envs\tfenv\Lib\site-packages\cv2\data\haarcascade_frontalface_alt.xml')
# face_cascade.load("D:\Build\OpenCV\opencv-4.1.2\modules\core\src\persistence_xml\haarcascade_frontalface_alt.xml")
# eye_cascade = cv2.CascadeClassifier("D:\face_recognized\haarcascade_eye.xml")
model2 = keras.models.load_model("C:\\Users\\Administrator\\PycharmProjects\\pythonProject\\trian_or_Test\\my_base_model6.h5")
expression = {'anger': 0, 'disgust': 0, 'fear': 0, 'happy': 0, 'sad': 0, 'surprised': 0, 'normal': 0, 'Noface': 0}
posture = {'cross_arms': 0, 'shoulder_drop': 0}
# total = 0 #总共表情和姿态的检测次数
# 将opencv读取图片转换成字符串
def ChangeToString(image):
# image_str = cv2.imencode('.jpg',image)[1].tostring();
print("图片转字节中...")
a = datetime.now();
image_str = cv2.imencode('.jpg', image)[1].tobytes();
b = datetime.now();
changeTime = (b - a).seconds;
print(changeTime);
return image_str;
def BodyAnalysis(img_str):
print("分析数据中...");
""" 你的 APPID AK SK """
APP_ID = '23411049'
API_KEY = 'LNCh4Tz8Yq5LaMGj2qWLFH9Q'
SECRET_KEY = 'f4FEXEHZQ2T0HVkK4GXDGPZibZHjrch5 '
client = AipBodyAnalysis(APP_ID, API_KEY, SECRET_KEY)
""" 读取图片 """
image = img_str;
""" 调用人体关键点识别 """
a = datetime.now();
result = client.bodyAnalysis(image);
b = datetime.now();
bodyAnalysisTime = (b - a).seconds;
print(bodyAnalysisTime);
return result;
# 分析是否交叉手臂 判断手腕关键点的横坐标
def cross_arms(left_wrist, right_wrist):
if left_wrist <= right_wrist:
posture['cross_arms'] = posture['cross_arms'] + 1;
return True
else:
return False
# 分析肩部高低差，左右肩部关键点纵坐标差不能大于50px
def shoulder_drop(left_shoulder, right_shoulder):
if math.fabs(left_shoulder - right_shoulder) > 20:
posture['shoulder_drop'] = posture['shoulder_drop'] + 1;
return True
else:
return False
def Body_posture_check(frame):
img_str = ChangeToString(frame);
my_result = BodyAnalysis(img_str);
person = my_result['person_info'][0]['body_parts'];
draw_line(person, frame)
cv2.namedWindow("body_posture", 0)
cv2.resizeWindow("body_posture", 300, 200)
cv2.imshow("body_posture", frame)
cross_arms_count = 0
shoulder_drop_count = 0
if cross_arms(int(person['left_wrist']['x']), int(person['right_wrist']['x'])):
print("存在交叉双臂动作")
cross_arms_count = cross_arms_count + 1
if shoulder_drop(int(person['left_shoulder']['y']), int(person['right_shoulder']['y'])):
print("左右肩部高低差过大")
shoulder_drop_count = shoulder_drop_count + 1
def facial_expression_statistics(result):
expression[result] = expression[result] + 1
# 设置摄像头捕获
cap = cv2.VideoCapture(0);
flag = True
def GetView():
print("dainji")
var = 30; # 每1000毫秒检测一次
person = None;
my_result = None;
total = 0;
while flag:
var = var + 1;
ret, frame = cap.read();
# cv2.imshow("image", frame)
# img_str = ChangeToString(frame);
# my_result = BodyAnalysis(img_str);
# person = my_result['person_info'][0]['body_parts'];
result = facial_expression_check(cap)
facial_expression_statistics(result)
total = total + 1
if (var % 30 == 0):
# img_str = ChangeToString(frame);
# my_result = BodyAnalysis(img_str);
# person = my_result['person_info'][0]['body_parts'];
# draw_line(person, frame);
# cv2.imshow("body_posture", frame)
Body_posture_check(frame)
if cv2.waitKey(10) & 0xff == ord('q'):
print(expression)
print(posture)
print(var)
#cap.release()
cv2.destroyAllWindows()
generateDocument(expression, posture, total)
time.sleep(2)
SMTPSend()
break
return
def stopLearning():
print("dainji stop Learning")
flag = False;
cap.release()
cv2.destroyAllWindows()
time.sleep(10)
SMTPSend()
def mytest():
img = cv2.imread('C:\\Users\\Administrator\\Pictures\\Camera Roll\\test3.jpeg');
# draw_line(result,img);
str = ChangeToString(img);
result = BodyAnalysis(str);
result1 = result['person_info'][0]['body_parts'];
draw_line(result1, img);
cv2.imshow('result', img);
cv2.waitKey(0);
print(result['person_info'][0]['body_parts']['nose']['x']);
学习状态分析报告生成功能
根据分析结果生成word版分析报告
from docx import Document
import docx
# 输入数据
expression = {'anger': 0, 'disgust': 0, 'fear': 0, 'happy': 10, 'sad': 0, 'surprised': 0, 'normal': 0,'Noface':0}
posture = {'cross_arms': 0, 'shoulder_drop': 0}
def getMaxExpression(expression):
maxnum = 0;
maxkey = ''
for keys, value in expression.items():
if value > maxnum:
maxnum = value
maxkey = keys
return maxkey
def generateDocument(expression, posture, total):
document = Document()
# 添加异常姿态表格
document.add_heading('学习状态评估', level=2)
document.add_heading('非放松自然状态动作统计', level=2)
posture_table = document.add_table(rows=2, cols=2)
row = posture_table.rows[0]
row.cells[0].text = '环抱双臂动作'
row.cells[1].text = str(posture['cross_arms'])
row = posture_table.rows[1]
row.cells[0].text = '肩部高低不一致'
row.cells[1].text = str(posture['shoulder_drop'])
# 添加表情统计表格
document.add_heading('面部表情状态数据统计', level=2)
table = document.add_table(rows=7, cols=2)
row = table.rows[0]
row.cells[0].text = 'anger'
row.cells[1].text = str(expression['anger'])
row = table.rows[1]
row.cells[0].text = 'disgust'
row.cells[1].text = str(expression['disgust'])
row = table.rows[2]
row.cells[0].text = 'fear';
row.cells[1].text = str(expression['fear'])
row = table.rows[3]
row.cells[0].text = 'happy'
row.cells[1].text = str(expression['happy'])
row = table.rows[4]
row.cells[0].text = 'sad'
row.cells[1].text = str(expression['sad'])
row = table.rows[5]
row.cells[0].text = 'surprised'
row.cells[1].text = str(expression['surprised'])
row = table.rows[6]
row.cells[0].text = 'normal'
row.cells[1].text = str(expression['normal'])
document.add_heading('学习状态评估结果', level=2)
# 总结出现次数最多的表情 对各个表情种类的出现进行分析
maxExpression = getMaxExpression(expression);
# 总结 normal 和happy 出现占比
study_state_text = ''
normal_happy = (expression['normal'] + expression['happy']) / total*100
Noface = (expression['Noface']) / total*100
# 总结异常姿势出现 进行相应的提醒
# posture_text =''
cross_arms_text = ''
shoulder_drop_text = ''
Noface_text=''
if posture['cross_arms'] > 0:
cross_arms_text = '出现双臂环绕动作，易导致出现紧张不适心理状态，影响听课状态，建议放松双臂，保持放松坐姿'
normal_happy-10
if posture['shoulder_drop'] > 0:
shoulder_drop_text = '两侧肩部高度差过大，建议保持肩膀放松且平衡'
normal_happy-10
if normal_happy >= 80:
study_state_text = '非常良好'
if normal_happy > 70 and normal_happy <=80:
study_state_text = '良好'
if normal_happy > 50 and normal_happy <70:
study_state_text = '一般'
if normal_happy <= 50:
study_state_text = '较差'
if Noface >=30:
study_state_text='较差'
Noface_text='出现没有识别到面部的情况，有可能存在逃课行为'
paragraph1 = document.add_paragraph("学生学习状态评价："+study_state_text)
paragraph2 = document.add_paragraph("出现最多的表情为：" + maxExpression+"占整个学习阶段的："+str(normal_happy)+"%")
paragraph3 = document.add_paragraph(cross_arms_text)
paragraph3 = document.add_paragraph(shoulder_drop_text)
paragraph4 = document.add_paragraph(Noface_text)
document.save('a.docx')
print(total)
#generateDocument(expression, posture, 100)
邮件转发功能实现
实现将分析报告转发至指定邮箱
import smtplib
from email.mime.multipart import MIMEMultipart
from email.mime.text import MIMEText
def SMTPSend():
# 设置smtplib所需的参数
# 下面的发件人，收件人是用于邮件传输的。
smtpserver = 'smtp.qq.com'
username = 'xxxx@qq.com'
password = 'xxxxxx'
sender = 'xxxxxx@qq.com'
# receiver='XXX@126.com'
# 收件人为多个收件人
receiver = ['xxxxxx@qq.com']
subject = '学习状态报告'
# 通过Header对象编码的文本，包含utf-8编码信息和Base64编码信息。以下中文名测试ok
# subject = '中文标题'
# subject=Header(subject, 'utf-8').encode()
# 构造邮件对象MIMEMultipart对象
# 下面的主题，发件人，收件人，日期是显示在邮件页面上的。
msg = MIMEMultipart('mixed')
msg['Subject'] = subject
msg['From'] = 'xxxx@qq.com <xxxx@qq.com>'
# msg['To'] = 'XXX@126.com'
# 收件人为多个收件人,通过join将列表转换为以;为间隔的字符串
msg['To'] = ";".join(receiver)
# msg['Date']='2012-3-16'
txt = MIMEText("学习状态评估报告已添加至附件请查收!!!")
msg.attach(txt)
# 构造附件
sendfile = open(r'C:\Users\Administrator\PycharmProjects\pythonProject\aip-python-sdk-4.15.1\a.docx', 'rb').read()
text_att = MIMEText(sendfile, 'base64', 'utf-8')
text_att["Content-Type"] = 'application/octet-stream'
# 以下附件可以重命名成aaa.txt
# text_att["Content-Disposition"] = 'attachment; filename="aaa.txt"'
# 另一种实现方式
text_att.add_header('Content-Disposition', 'attachment', filename='学习状态评估报告.docx')
msg.attach(text_att)
# 发送邮件
smtp = smtplib.SMTP()
smtp.connect('smtp.qq.com')
# 我们用set_debuglevel(1)就可以打印出和SMTP服务器交互的所有信息。
# smtp.set_debuglevel(1)
smtp.login(username, password)
smtp.sendmail(sender, receiver, msg.as_string())
smtp.quit()
UI交互代码
此处由于只实现了一个简单的“单机版”的学习状态评估功能，所以只简单的引入TK库进行界面的编写，注册和登录没有写入数据库，只是进行简单的序列化操作保存在文件中。
界面图片
时隔久远代码 代码可能有些问题，请大家多多包含！！建议大家根据需要自行编写
import pickle
import tkinter as tk
import tkinter.messagebox
from PIL import Image, ImageTk
from Expression_posture import GetView
from Expression_posture import stopLearning
from DocumentGeneration import generateDocument
usr_name=''
usr_pwd=''
usr_info=''
import cv2
from Expression_posture import cap
flag = False
def usr_login_win():
try:
with open('usr_info.pickle', 'rb') as usr_file:
usrs_info = pickle.load(usr_file)
except:
with open('usr_info.pickle', 'wb') as usr_file:
usrs_info = {'admin': 'admin'}
pickle.dump(usrs_info, usr_file)
def loginCheck( ):
usr_name = var_usr_name.get()
usr_pwd = var_usr_pwd.get()
if usr_name in usrs_info:
if usr_pwd == usrs_info[usr_name]:
tk.messagebox.showinfo(title='Welcome', message='欢迎' + usr_name+'登录！')
btn2 = tk.Button(win, width=265, image=startLearning_photo, compound=tk.CENTER, bg='#FFFFFF',
relief='flat', command=GetView)
btn2.place(x=210, y=330)
stopLabel = tk.Label(win, text='注:开始学习后输入q字母退出学习', font=('Bold', 13), fg='#5B0261',
bg='#FFFFFF')
stopLabel.place(x=210,y=380)
# stop_learning = tk.Button(win, width=265, image=startLearning_photo, compound=tk.CENTER, bg='#FFFFFF',
# relief='flat', command=stopLearning)
# stop_learning.place(x=210,y=300)
btn3.place_forget()
btn4.place_forget()
window_login.destroy()
else:
tk.messagebox.showerror(message='ERROR!')
# 用户名密码不能为空
elif usr_name == '' or usr_pwd == '':
tk.messagebox.showerror(message='用户名不能为空！')
window_login = tk.Toplevel(win)
window_login.title('login')
window_login.geometry('400x300')
background = tk.Label(window_login, image=login_bg_photo, compound=tk.CENTER, relief='flat')
background.pack()
tk.Label(window_login, text='账户：',font=("Bold",11),fg='#707070',bg='#FFFFFF').place(x=100, y=100)
tk.Label(window_login, text='密码：',font=("Bold",11),fg='#707070',bg='#FFFFFF').place(x=100, y=140)
var_usr_name = tk.StringVar()
var_usr_pwd = tk.StringVar()
enter_usr_name = tk.Entry(window_login, textvariable=var_usr_name,font=('Arail',15),width=20,relief='groove',bd=2)
enter_usr_name.place(x=160, y=100)
enter_usr_pwd = tk.Entry(window_login, textvariable=var_usr_pwd, show='*',font=('Arail',15),width=20,relief='groove',bd=2)
enter_usr_pwd.place(x=160, y=140)
btn_login = tk.Button(window_login, image=login_photo, compound=tk.CENTER, bg='#FFFFFF', relief='flat',
command=lambda: [loginCheck()])
#btn_login = tk.Button(window_login, text="login", width=10, height=2, command=loginCheck)
btn_login.place(x=100, y=200)
def usr_sign_window():
def signtowcg():
NewName = new_name.get()
NewPwd = new_pwd.get()
ConfirPwd = pwd_comfirm.get()
receiveEmail = receive_email.get()
try:
with open('usr_info.pickle', 'rb') as usr_file:
exist_usr_info = pickle.load(usr_file)
except FileNotFoundError:
exist_usr_info = {}
if NewName in exist_usr_info:
tk.messagebox.showerror(message='用户名存在！')
elif NewName == '' and NewPwd == '':
tk.messagebox.showerror(message='用户名和密码不能为空！')
elif NewPwd != ConfirPwd:
tk.messagebox.showerror(message='密码前后不一致！')
else:
exist_usr_info[NewName] = NewPwd
with open('usr_info.pickle', 'wb') as usr_file:
pickle.dump(exist_usr_info, usr_file)
tk.messagebox.showinfo(message='注册成功！')
window_sign_up.destroy()
#注册界面自定义函数
def close_regWin():
window_sign_up.destroy()
# 新建注册窗口
window_sign_up = tk.Toplevel(win)
sw = window_sign_up.winfo_screenwidth() # 得到屏幕宽度
sh = window_sign_up.winfo_screenheight() # 得到屏幕高度
ww = 500
wh = 400
# 窗口宽高为100
x = (sw - ww) / 2
y = (sh - wh) / 2
window_sign_up.geometry("%dx%d+%d+%d" % (ww, wh, x, y))
#注册页面背景设置
window_sign_up.overrideredirect(False)
register_background = tk.Label(window_sign_up, image=register_bg_photo, compound=tk.CENTER, relief='flat')
register_background.pack()
#关闭窗口按钮
# reg_close = tk.Button(window_sign_up,image=close_photo, relief='flat',command=close_regWin,compound=tk.CENTER,bd=0)
# reg_close.place(x=475,y=1)
# 注册编辑框
new_name = tk.StringVar()
new_pwd = tk.StringVar()
pwd_comfirm = tk.StringVar()
receive_email = tk.StringVar()
tk.Label(window_sign_up, text='账户名：',font=('Bold',11),fg='#707070',bg='#FFFFFF').place(x=110, y=50)
enter_new_name=tk.Entry(window_sign_up, textvariable=new_name,font=('Arail',15),width=20,relief='groove',bd =2)
enter_new_name.place(x=190,y=50)
tk.Label(window_sign_up, text='密码：',font=('Bold',11),fg='#707070',bg='#FFFFFF').place(x=110, y=100)
enter_new_pwd=tk.Entry(window_sign_up, textvariable=new_pwd, show='*',font=('Arail',15),width=20,relief='groove',bd =2)
enter_new_pwd.place(x=190,y=100)
tk.Label(window_sign_up, text='确认密码：',font=('Bold',11),fg='#707070',bg='#FFFFFF').place(x=110, y=150)
enter_pwd_comfirm=tk.Entry(window_sign_up, textvariable=pwd_comfirm, show='*',font=('Arail',15),width=20,relief='groove',bd =2)
enter_pwd_comfirm.place(x=190,y=150)
tk.Label(window_sign_up,text ='注册邮箱：',font=('Bold',11),fg='#707070',bg='#FFFFFF').place(x=110,y=200)
enter_new_email = tk.Entry(window_sign_up,font=('Arail',15),width=20,relief='groove',bd =2)
enter_new_email.place(x=190,y=200)
tk.Label(window_sign_up,text='收件邮箱：',font=('Bold',11),fg='#707070',bg='#FFFFFF').place(x=110, y=250)
enter_new_email2 = tk.Entry(window_sign_up, textvariable=receive_email, font=('Arail', 15), width=20, relief='groove', bd=2)
enter_new_email2.place(x=190, y=250)
alert_lable1 = tk.Label(window_sign_up,text='注:完成学习后将向此邮箱发送学习状态评估报告',font=('Bold',8),fg='#5B0261',bg='#FFFFFF')
alert_lable1.place(x=190,y=280)
# 确认注册
bt_confirm = tk.Button(window_sign_up,image=reg_reg_photo,compound=tk.CENTER,relief='flat',bg='#FFFFFF',bd=0, command=signtowcg)
bt_confirm.place(x=270,y=310)
#自己创建的函数
def StopLearning():
print("stoplearning")
cap.release()
#主界面内容设置
win = tk.Tk()
win.configure(bg='#FFFFFF')
sw = win.winfo_screenwidth() #得到屏幕宽度
sh = win.winfo_screenheight() #得到屏幕高度
ww = 700
wh = 465
#窗口宽高为100
x = (sw-ww) / 2
y = (sh-wh) / 2
win.geometry("%dx%d+%d+%d" %(ww,wh,x,y))
win.title("Study Supervise")
def changeBtn2State():
print("change")
#btn2['state'] = tk.NORMAL
def CloseWin():
win.destroy()
#登录窗口涉及图片
login_bg_img = Image.open('UI_image/login_bg.png')
login_bg_photo = ImageTk.PhotoImage(login_bg_img)
#注册窗口涉及图片变量
register_bg_img = Image.open('UI_image/Register_bg.png')
register_bg_photo = ImageTk.PhotoImage(register_bg_img)
reg_close_img= Image.open('UI_image/close.png')
reg_close_photo= ImageTk.PhotoImage(reg_close_img)
reg_reg_img = Image.open('UI_image/register.png')
reg_reg_photo = ImageTk.PhotoImage(reg_reg_img)
# 主界面样式设置
bg_img = Image.open('UI_image/bg_img3.png')
background_img = ImageTk.PhotoImage(bg_img)
win.overrideredirect(False)
background = tk.Label(win,image=background_img,compound=tk.CENTER,relief='flat')
background.pack()
startLearning_img = Image.open('UI_image/StartLearning.png')
startLearning_photo = ImageTk.PhotoImage(startLearning_img)
login_img = Image.open('UI_image/login.png')
login_photo = ImageTk.PhotoImage(login_img)
btn3 = tk.Button(win,image=login_photo,compound=tk.CENTER,bg='#FFFFFF',relief='flat',command=lambda:[usr_login_win(),changeBtn2State()],)
btn3.place(x=165,y=330)
register_img = Image.open('UI_image/register.png')
register_photo = ImageTk.PhotoImage(register_img)
btn4 = tk.Button(win,image=register_photo,compound=tk.CENTER,bg='#FFFFFF',relief='flat',command=usr_sign_window)
btn4.place(x=400,y = 330)
win.mainloop()
扫一扫
324
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
