Python人脸表情识别QT窗体
.Python人脸表情识别QT窗体
如需安装运行环境或远程调试，可加扣905733049, 或扣2945218359由专业技术人员远程协助！
运行结下：
主要代码：
# coding:utf-8
import sys
#从转换的.py文件内调用类
import cv2
import numpy as np
import sys
import tensorflow as tf
from untitled import Ui_Dialog
from PyQt5 import QtWidgets
from PyQt5 import QtWidgets, QtCore, QtGui
from PyQt5.QtCore import *
class myWin(QtWidgets.QWidget, Ui_Dialog):
def __init__(self):
super(myWin, self).__init__()
self.setupUi(self)
def openFileButton(self):
imgName, imgType = QFileDialog.getOpenFileName(self,"打开文件","./","files(*.*)")
img = cv2.imread(imgName)
cv2.imwrite("temp/original.jpg", img)
height, width, pixels = img.shape
print("width,height",width,height)
print("self.label.width()",self.label.width())
print("self.label.height()",self.label.height())
frame = cv2.resize(img, (int(rwidth), int(rheight)))
print("rwidth-elif,rheight-elfi", rwidth, rheight)
img2 = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB) # opencv读取的bgr格式图片转换成rgb格式
_image = QtGui.QImage(img2[:], img2.shape[1], img2.shape[0], img2.shape[1] * 3, QtGui.QImage.Format_RGB888)
jpg_out = QtGui.QPixmap(_image).scaled(rwidth, rheight) #设置图片大小
self.label.setPixmap(jpg_out) #设置图片显示
def saveFileButton(self):
img = cv2.imread("temp/original.jpg")
file_path = QFileDialog.getSaveFileName(self, "save file", "./save/test","jpg files (*.jpg);;all files(*.*)")
print(file_path[0])
cv2.imwrite(file_path[0], img)
cv2.waitKey(0)
cv2.destroyAllWindows()
def recogPerson(self):
import os
import cv2
img = cv2.imread("temp/original.jpg")
cv2.imwrite("save/recognPerson2.jpg", img)
face_detect = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
eye_detect = cv2.CascadeClassifier('haarcascade_eye.xml')
# 灰度处理
gray = cv2.cvtColor(img, code=cv2.COLOR_BGR2GRAY)
# 检查人脸 按照1.1倍放到 周围最小像素为5
face_zone = face_detect.detectMultiScale(gray,1.3,5)
# print ('识别人脸的信息：\n',face_zone)
l = len(face_zone)
ints = 0
# 绘制矩形和圆形检测人脸
for x, y, w, h in face_zone:
ints += 1
# 绘制矩形人脸区域
if w < 1000:
cv2.rectangle(img, pt1=(x, y), pt2=(x + w, y + h), color=[0, 0, 255], thickness=2)
# 绘制圆形人脸区域 radius表示半径
cv2.circle(img, center=(x + w // 2, y + h // 2), radius=w // 2, color=[0, 255, 0], thickness=2)
roi_face = gray[y:y + h, x:x + w] # 灰度图
roi_color = img[y:y + h, x:x + w] # 彩色图
eyes = eye_detect.detectMultiScale(roi_face)
for (ex, ey, ew, eh) in eyes:
cv2.rectangle(roi_color, (ex, ey), (ex + ew, ey + eh), (0, 255, 0), 2)
cv2.imwrite("save/recognPerson.jpg", img)
#cv2.waitKey(0)
#显示人数到窗体
self.textEdit.setPlainText(str(ints))
#self.textEdit.setPlainText('Hello PyQt5!\n单击按钮')
frame = cv2.resize(img, (int(rwidth), int(rheight)))
img2 = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB) # opencv读取的bgr格式图片转换成rgb格式
_image = QtGui.QImage(img2[:], img2.shape[1], img2.shape[0], img2.shape[1] * 3, QtGui.QImage.Format_RGB888)
jpg_out = QtGui.QPixmap(_image).scaled(rwidth, rheight) #设置图片大小
self.label_2.setPixmap(QPixmap(""))
self.label_2.setPixmap(jpg_out) #设置图片显示
#emotion recog
CASC_PATH = './data/haarcascade_files/haarcascade_frontalface_default.xml'
cascade_classifier = cv2.CascadeClassifier(CASC_PATH)
EMOTIONS = ['Angry', 'Disgusted', 'Fearful', 'Happy', 'Sad', 'Surprised', 'Neutral']
def format_image(image):
if len(image.shape) > 2 and image.shape[2] == 3:
image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
faces = cascade_classifier.detectMultiScale(
image,
scaleFactor=1.3,
minNeighbors=5
)
# None is no face found in image
if not len(faces) > 0:
return None, None
max_are_face = faces[0]
for face in faces:
if face[2] * face[3] > max_are_face[2] * max_are_face[3]:
max_are_face = face
# face to image
face_coor = max_are_face
image = image[face_coor[1]:(face_coor[1] + face_coor[2]), face_coor[0]:(face_coor[0] + face_coor[3])]
# Resize image to network size
try:
image = cv2.resize(image, (48, 48), interpolation=cv2.INTER_CUBIC)
except Exception:
print("[+} Problem during resize")
return None, None
return image, face_coor
def face_dect(image):
"""
Detecting faces in image
:param image:
:return: the coordinate of max face
"""
if len(image.shape) > 2 and image.shape[2] == 3:
image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
faces = cascade_classifier.detectMultiScale(
image,
scaleFactor=1.3,
minNeighbors=5
)
if not len(faces) > 0:
return None
max_face = faces[0]
for face in faces:
if face[2] * face[3] > max_face[2] * max_face[3]:
max_face = face
face_image = image[max_face[1]:(max_face[1] + max_face[2]), max_face[0]:(max_face[0] + max_face[3])]
try:
image = cv2.resize(face_image, (48, 48), interpolation=cv2.INTER_CUBIC) / 255.
except Exception:
print("[+} Problem during resize")
return None
return face_image
def resize_image(image, size):
try:
image = cv2.resize(image, size, interpolation=cv2.INTER_CUBIC) / 255.
except Exception:
print("+} Problem during resize")
return None
return image
def draw_emotion():
pass
import os
import sys
def demo(modelPath, showBox=False):
import cv2
face_x = tf.placeholder(tf.float32, [None, 2304])
y_conv = deepnn(face_x)
probs = tf.nn.softmax(y_conv)
print("test3")
saver = tf.train.Saver()
ckpt = tf.train.get_checkpoint_state(modelPath)
sess = tf.Session()
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
print('Restore model sucsses!!\nNOTE: Press SPACE on keyboard to capture face.')
feelings_faces = []
for index, emotion in enumerate(EMOTIONS):
feelings_faces.append(cv2.imread('./data/emojis/' + emotion + '.png', -1))
#video_captor = cv2.VideoCapture(0)
import cv2
result = sess.run(probs, feed_dict={face_x: tensor})
print("result: ", result)
# name_list = ','.join(result)
# print("name_list: ", name_list)
print("test4")
if os.path.exists("recv.txt"):
os.remove("recv.txt")
if os.path.exists("recv2.txt"):
os.remove("recv2.txt")
for index, emotion in enumerate(EMOTIONS):
file = open('recv.txt', 'a')
file.write(str(emotion)+": " + str(rate)+", ")
file.write(";")
file.close()
file5 = open("recv.txt", 'rt')
contents = file5.read()
data = contents.replace(";", ";\n")
fin = open('recv2.txt', "wt")
fin.write(data)
fin.close()
with open("recv2.txt", "r") as file2:
path = file2.read()
print("path ", path)
file2.close()
self.textEdit_2.setPlainText(path)
tf.reset_default_graph()
# emoji_face = []
# result = None
#
# while True:
# #ret, frame = video_captor.read()
# import cv2
# frame = cv2.imread("save/recognPerson.jpg")
# detected_face, face_coor = format_image(frame)
# if showBox:
# if face_coor is not None:
# [x, y, w, h] = face_coor
# cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 2)
#
# if cv2.waitKey(1) & 0xFF == ord(' '):
#
# if detected_face is not None:
# # cv2.imwrite('a.jpg', detected_face)
# tensor = image_to_tensor(detected_face)
# result = sess.run(probs, feed_dict={face_x: tensor})
# print("result: ",result)
# if result is not None:
# for index, emotion in enumerate(EMOTIONS):
# print("emotion: ", emotion)
# print("index: ", index)
# cv2.putText(frame, emotion, (10, index * 20 + 20), cv2.FONT_HERSHEY_PLAIN, 1.2, (0, 255, 0), 1)
# cv2.rectangle(frame, (130, index * 20 + 10),
# (130 + int(result[0][index] * 100), (index + 1) * 20 + 4),
# (255, 0, 0), -1)
# emoji_face = feelings_faces[np.argmax(result[0])]
# print("int(result[0][index]: ", int(result[0][index] * 100))
#
# for c in range(0, 3):
# frame[200:320, 10:130, c] = emoji_face[:, :, c] * (emoji_face[:, :, 3] / 255.0) + frame[200:320,
# 10:130, c] * (
# 1.0 - emoji_face[:, :, 3] / 255.0)
#
# cv2.imshow('face', frame)
# if cv2.waitKey(1) & 0xFF == ord('q'):
# break
if __name__ == '__main__':
modelPath = "ckpt"
demo(modelPath)
if __name__=="__main__":
app=QtWidgets.QApplication(sys.argv)
Widget=myWin()
Widget.showMaximized();
Widget.show()
sys.exit(app.exec_())运行结下：