（2）在“画板”模块处可以进行鼠标绘制，绘制时接近画板中央会效果更好

（4）点击按钮“画板擦除”即可清空“画板”模块。

2．图片识别

四、代码及架构

1.配置环境

keras 2.4.3     PyQt5 5.15.4

numpy 1.19.5   TensorFlow 2.5.0

opencv-python 4.5.2.52

pyscreenshot 3.0   joblib 1.0.1

sklearn 0.0

2、代码结构

1、main

调用界面

2、Tan

界面逻辑和交互

3、Run

图片预处理、预测及生成结果图片

4、predict

读入图片归一化、根据参数选择预测模型预测函数

5、train

CNN训练并保存模型

6、tarin_new

sklearn库函数模型训练、比较和保存

3、全部代码

1、main

import sys
from PyQt5.QtWidgets import QApplication
from Tan import Tanif __name__ == "__main__":app = QApplication(sys.argv)mymnist = Tan()  # 调用Tan中GUImymnist.show()app.exec_()

2、Tan

# --coding:utf-8--
from PyQt5.QtWidgets import (QWidget, QPushButton, QLabel, QComboBox, QFileDialog)
from PyQt5.QtGui import (QPainter, QPen, QFont)
from PyQt5.QtCore import Qt
from PyQt5 import QtGui
from PyQt5.Qt import QIcon
from PyQt5.QtCore import *
from PyQt5.QtGui import *
from PyQt5.QtWidgets import *
from PyQt5.Qt import QDir, QIcon
from PyQt5.QtGui import QPixmap
import sys
from PIL import Image
import  osimport pyscreenshot as ImageGrab
import Run
import cv2
import numpydef is_chinese(string):"""检查整个字符串是否包含中文:param string: 需要检查的字符串:return: bool"""for ch in string:if u'\u4e00' <= ch <= u'\u9fff':return Truereturn Falseclass MyLabel(QLabel):pos_xy=[]def paintEvent(self, event):painter = QPainter()painter.begin(self)#pen = QPen(Qt.black, int(self.huabi.currentText()), Qt.SolidLine)  # 画笔尺寸 颜色painter.setPen(QPen(Qt.black, 2, Qt.SolidLine))if len(self.pos_xy) > 1:point_start = self.pos_xy[0]for pos_tmp in self.pos_xy:point_end = pos_tmpif point_end == (-1, -1):point_start = (-1, -1)continueif point_start == (-1, -1):point_start = point_endcontinuepainter.drawLine(point_start[0], point_start[1], point_end[0], point_end[1])point_start = point_endpainter.end()# 记录鼠标点下的点，添加到pos_xy列表def mouseMoveEvent(self, event):pos_tmp = (event.pos().x(), event.pos().y())self.pos_xy.append(pos_tmp)self.update()# 鼠标释放，在pos_xy中添加断点def mouseReleaseEvent(self, event):pos_test = (-1, -1)self.pos_xy.append(pos_test)#绘制事件def btn_clear_on_clicked(self):self.pos_xy = []self.setText('')self.update()# 界面
class Tan(QWidget):def __init__(self):super(Tan, self).__init__()self.resize(654, 768)  # 外围边框大小self.move(550, 95)    # 设置位置self.setWindowTitle('手写数字识别')  # 标题self.setMouseTracking(False)  # False代表不按下鼠标则不追踪鼠标事件self.pos_xy = []  # 保存鼠标移动过的点# 添加控件#窗口图标self.setWindowIcon(QIcon('bluesky.jpg'))#窗口背景self.echoLabel = QLabel(self)self.echoLabel.setGeometry(160, 0, 903, 768)self.pixmap = QPixmap("bluesky.jpg")  # 按指定路径找到图片self.echoLabel.setPixmap(self.pixmap)  # 在label上显示图片self.echoLabel.setScaledContents(True)  # 让图片自适应label大小# logoself.logoLabel = QLabel(self)self.logoLabel.setGeometry(-80, -50, 319, 220)self.pixmap1 = QPixmap("logo.png")  # 按指定路径找到图片self.logoLabel.setPixmap(self.pixmap1)  # 在label上显示图片self.logoLabel.setScaledContents(True)  # 让图片自适应label大小# 画板文字self.label_draw_name = QLabel(('''<font color=#87F1E6 face='黑体' size=5>画板：<font>'''), self)self.label_draw_name.setGeometry(180, 15, 70, 30)# 画板区域self.label_draw = MyLabel('', self)self.label_draw.setGeometry(180, 45, 450, 300)self.label_draw.setStyleSheet("QLabel{border:1px solid white;background-color: #FFFFFF}")self.label_draw.setAlignment(Qt.AlignCenter)# 图片结果文字self.label_result_name = QLabel('''<font color=#87F1E6 face='黑体' size=5>结果：<font>''', self)self.label_result_name.setGeometry(180, 410, 70, 30)self.label_result_name.setAlignment(Qt.AlignCenter)# 图片结果区域self.label_result1 = QLabel(' ', self)self.label_result1.setGeometry(180, 440, 450, 300)self.label_result1.setStyleSheet("QLabel{border:1px solid white;background-color: #FFFFFF}")self.label_result1.setAlignment(Qt.AlignCenter)# 识别按钮，跳转到 reco 方法self.btn_recognize = QPushButton('画板识别', self)self.btn_recognize.setGeometry(6, 210, 60, 50)self.btn_recognize.setStyleSheet('''background-color: #87CEFA ;height:30px;border-style: outset;border-width: 2px;border-radius: 20px;border-color: beige;font: bold 12 px;min-width: 9em;padding: 5px;''')self.btn_recognize.clicked.connect(self.reco)# 选择上传图片self.btn_clear = QPushButton("图片识别", self)self.btn_clear.setGeometry(6, 510, 60, 50)self.btn_clear.clicked.connect(self.open_file)self.btn_clear.setStyleSheet('''background-color: #87CEFA ;height:30px;border-style: outset;border-width: 2px;border-radius: 20px;border-color: beige;font: bold 12 px;min-width: 9em;padding: 5px;''')# 清空所写数字self.btn_clear = QPushButton("擦除画板", self)self.btn_clear.setGeometry(6, 360, 60, 50)self.btn_clear.clicked.connect(self.label_draw.btn_clear_on_clicked)self.btn_clear.setStyleSheet('''background-color: #87CEFA ;height:30px;border-style: outset;border-width: 2px;border-radius: 20px;border-color: beige;font: bold 12 px;min-width: 9em;padding: 5px;''')# 识别模式self.moshi = QComboBox(self)self.moshi.addItems(['CNN', "RandomForest", "KNeighbors", "DecisionTree"])self.moshi.setGeometry(30, 650, 100, 30)self.moshi.setStyleSheet('''background-color: #87CEFA ;''')# 识别函数def reco(self):bbox = (self.x()+183, self.y()+83, 1180, 470)  # 设置截屏位置im = ImageGrab.grab(bbox)    # 截屏im.save("now.png")img = cv2.imread("now.png")if self.moshi.currentText() == "CNN":Run.Run(img, 1)  # 调用Run中'CNN'方法对所截图img进行处理if self.moshi.currentText() == "RandomForest":Run.Run(img, 2)  # 调用Run中'RandomForest'方法对所截图img进行处理if self.moshi.currentText() == "KNeighbors":Run.Run(img, 3)  # 调用Run中'KNeighbors'方法对所截图img进行处理if self.moshi.currentText() == "DecisionTree":Run.Run(img, 4)  # 调用Run中'DecisionTree'方法对所截图img进行处理self.label_result1.setPixmap(QtGui.QPixmap('img.png').scaled(self.label_result1.width(), self.label_result1.height()))  # 在label_result1中显示图片self.update()def open_file(self):imgName, imgType = QFileDialog.getOpenFileName(self, "选择一张图片", "", "*.jpg;;*.png;;All Files(*)")if imgName == "":returnif is_chinese(imgName):s = imgName.split('/')[-1]else:s = imgNameimg = cv2.imread(s)if self.moshi .currentText() == "CNN":Run.Run(img, 1)  # 调用Run中'CNN'方法对所截图img进行处理if self.moshi .currentText() == "RandomForest":Run.Run(img, 2)  # 调用Run中'RandomForest'方法对所截图img进行处理if self.moshi .currentText() == "KNeighbors":Run.Run(img, 3)  # 调用Run中'KNeighbors'方法对所截图img进行处理if self.moshi .currentText() == "DecisionTree":Run.Run(img, 4)  # 调用Run中'DecisionTree'方法对所截图img进行处理self.label_result1.setPixmap(QtGui.QPixmap('img.png').scaled(self.label_result1.width(), self.label_result1.height()))  # 在label_result1中显示图片self.update()

3、Run

import cv2
import numpy as np
import matplotlib.pyplot as plt
from keras.models import load_model
from predict import *
import joblibdef Run(img,model_x):""":param img: 输入图像矩阵:excute   将标注好的图片存入根目录，命名为“img.png”"""# 载入训练好的模型if model_x == 1:model = load_model('net1')if model_x == 2:model = joblib.load("RandomForest.pkl")if model_x == 3:model = joblib.load("KNeighbors.pkl")if model_x == 4:model = joblib.load("DecisionTree.pkl")image = cv2.resize(img, (960, 640), interpolation=cv2.INTER_LINEAR)# 将这帧转换为灰度图gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)# 二值化retval, binary = cv2.threshold(gray, 90, 255, cv2.THRESH_BINARY_INV)# 放大所有轮廓contours, hierarchy = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)for i in range(len(contours)):cv2.drawContours(binary, contours, i, (255, 255, 255), 5)# 过滤噪声点contours, hierarchy = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)for i in range(len(contours)):perimeter = cv2.arcLength(contours[i], False)if perimeter < 100:# print(s)cv2.drawContours(binary, contours, i, (0, 0, 0), 15)# cv2.imshow('binary_f', binary)contours, hierarchy = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)#print(len(contours))# 遍历整个图片每个轮廓for i in range(len(contours)):M = cv2.moments(contours[i])#  找到中心点if M['m00'] != 0:cx = int(M['m10'] / M['m00'])cy = int(M['m01'] / M['m00'])x, y, w, h = cv2.boundingRect(contours[i])pad = max(w, h) + 10#  画出绿色框图cv2.rectangle(image, (cx - pad // 2, cy - pad // 2), (cx + pad // 2, cy + pad // 2), (0, 255, 0), thickness=2)#  进行预测if cy - pad // 2 >= 0 and cx - pad // 2 >= 0:number_i = (binary[cy - pad // 2:cy + pad // 2, cx - pad // 2:cx + pad // 2])number_i = cv2.resize(number_i, (28, 28))if model_x == 1:number_i = np.reshape(number_i, (-1, 28, 28, 1)).astype('float')else:number_i = number_i.reshape(1, 784).astype('float32')#将结果红色显示在框上result = number_predict(number_i, model, model_x)cv2.putText(image, str(result[0]), org=(x, y), fontFace=cv2.FONT_HERSHEY_SIMPLEX, fontScale=1.2,color=(0, 0, 255), thickness=2)cv2.imwrite('img.png', image)return 0#cv2.waitKey()#cv2.destroyAllWindows()

4、predict

def number_predict(img, model, k):# 图像处理img = img / 255.0# 预测if k == 1:result = model.predict_classes(img)else:result = model.predict(img)return result

5、train

import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.optimizers import RMSprop
import matplotlib.pyplot as plt
import numpy as np
from keras.utils import np_utilsbatch_size = 128
num_classes = 10
epochs = 10path = 'mnist_data/mnist.npz'
f = np.load(path)
x_train, y_train = f['x_train'], f['y_train']
x_test, y_test = f['x_test'], f['y_test']
f.close()x_train = x_train.reshape(60000, 28, 28, 1).astype('float32')
x_test = x_test.reshape(10000, 28, 28, 1).astype('float32')
x_train /= 255
x_test /= 255
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')# convert class vectors to binary class matrices
# label为0~9共10个类别，keras要求格式为binary class matricesy_train = np_utils.to_categorical(y_train, num_classes)
y_test = np_utils.to_categorical(y_test, num_classes)from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D# 卷积模型
model = Sequential()
model.add(Conv2D(filters=16,kernel_size=(5, 5),padding='same',input_shape=(28,28,1),activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(filters=36,kernel_size=(5, 5),padding='same',activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
#model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
#model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))model.summary()# 损失函数使用交叉熵
model.compile(loss='categorical_crossentropy',optimizer=RMSprop(),metrics=['accuracy'])
# 模型训练
model.fit(x_train, y_train,batch_size=batch_size,epochs=epochs,verbose=1,validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Total loss on Test Set:', score[0])
print('Accuracy of Testing Set:', score[1])# 模型保存
model.save('./net1.pkl')

6、tarin_new

import numpy as np
import pandas as pd
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.naive_bayes import MultinomialNB
from sklearn.naive_bayes import BernoulliNB
from sklearn.model_selection import StratifiedKFold
import joblibpath = 'mnist_data/mnist.npz'
f = np.load(path)
x_train, y_train = f['x_train'], f['y_train']
x_test, y_test = f['x_test'], f['y_test']
f.close()
x_train = x_train.reshape(60000, 784).astype('float32')
x_test = x_test.reshape(10000, 784).astype('float32')
x_train /= 255
x_test /= 255
clf5 = MultinomialNB()
clf5.fit(x_train, y_train)
joblib.dump(clf5, "MultinomialNB().pkl")classifierResult = clf5.predict(x_test)
mTest = len(x_test)errorCount = 0.0 ## 统计识别错误的样本个数
for i in range(mTest):if classifierResult[i] != y_test[i]:errorCount += 1.0print("\t 测试样本个数为： %d " % mTest)
print("\t 预测错误个数为： %d " % errorCount)
print("\t 预测错误率为： %2.2f%% " % (errorCount/float(mTest)*100))
print("\t 预测准确率为： %2.2f%%" % ((1-errorCount/float(mTest))*100))
'''
clf = KNeighborsClassifier(algorithm='kd_tree', n_neighbors=10)
clf.fit(x_train, y_train)
joblib.dump(clf, "KNeighbors.pkl")
clf2 = RandomForestClassifier()
clf2.fit(x_train, y_train)
joblib.dump(clf2, "RandomForest.pkl")
clf1 = DecisionTreeClassifier(criterion='entropy', random_state=0)
clf1.fit(x_train, y_train)
joblib.dump(clf1, "DecisionTree.pkl")
clf3 = GaussianNB()
clf3.fit(x_train, y_train)
joblib.dump(clf3, "GaussianNB.pkl")
clf4 = BernoulliNB()
clf4.fit(x_train, y_train)
joblib.dump(clf4, "BernoulliNB.pkl")
clf5 = MultinomialNB()
clf5.fit(x_train, y_train)
joblib.dump(clf5, "MultinomialNB().pkl")clf = joblib.load("RandomForest.pkl")
classifierResult = clf.predict(x_test)
mTest = len(x_test)errorCount = 0.0 ## 统计识别错误的样本个数
for i in range(mTest):if classifierResult[i] != y_test[i]:errorCount += 1.0print("\t 测试样本个数为： %d " % mTest)
print("\t 预测错误个数为： %d " % errorCount)
print("\t 预测错误率为： %2.2f%% " % (errorCount/float(mTest)*100))
print("\t 预测准确率为： %2.2f%%" % ((1-errorCount/float(mTest))*100))
'''