快捷導(dǎo)航

Python實(shí)現(xiàn)帶GUI界面的手寫(xiě)數(shù)字識(shí)別

更新時(shí)間：2022年01月05日 15:48:34 作者：跨考上浙大

這篇文章主要介紹了如何通過(guò)Python實(shí)現(xiàn)帶GUI界面的手寫(xiě)數(shù)字識(shí)別，文中的示例代碼講解詳細(xì)，對(duì)我們學(xué)習(xí)Python有一定的幫助，感興趣的可以了解一下

1.效果圖

有點(diǎn)low，輕噴

點(diǎn)擊選擇圖片會(huì)優(yōu)先從當(dāng)前目錄查找

2.數(shù)據(jù)集

這部分我是對(duì)MNIST數(shù)據(jù)集進(jìn)行處理保存

對(duì)應(yīng)代碼：

import tensorflow as tf
import matplotlib.pyplot as plt
import cv2
from PIL import Image
import numpy as np
from scipy import misc
(x_train_all,y_train_all),(x_test,y_test) = tf.keras.datasets.mnist.load_data()
x_valid,x_train = x_train_all[:5000],x_train_all[5000:]
y_valid,y_train = y_train_all[:5000],y_train_all[5000:]
print(x_valid.shape,y_valid.shape)
print(x_train.shape,y_train.shape)
print(x_test.shape,y_test.shape)
#讀取單張圖片
def show_single_img(img_arr,len=100,path='/Users/zhangcaihui/Desktop/case/jpg/'):
    for i in range(len):#我這種寫(xiě)法會(huì)進(jìn)行覆蓋，只能保存10張照片，想保存更多的數(shù)據(jù)自己看著改
        new_im = Image.fromarray(img_arr[i])  # 調(diào)用Image庫(kù)，數(shù)組歸一化
        #new_im.show()
        #plt.imshow(img_arr)  # 顯示新圖片
        label=y_train[i]
        new_im.save(path+str(label)+'.jpg')  # 保存圖片到本地

#顯示多張圖片
def show_imgs(n_rows,n_cols,x_data,y_data):
    assert len(x_data) == len(y_data)
    assert n_rows * n_cols < len(x_data)
    plt.figure(figsize=(n_cols*1.4,n_rows*1.6))
    for row in range(n_rows):
        for col in range(n_cols):
            index = n_cols * row + col
            plt.subplot(n_rows,n_cols,index+1)
            plt.imshow(x_data[index],cmap="binary",interpolation="nearest")
            plt.axis("off")
    plt.show()
#show_imgs(2,2,x_train,y_train)
show_single_img(x_train)

3.關(guān)于模型

我保存了了之前訓(xùn)練好的模型，用來(lái)加載預(yù)測(cè)

關(guān)于tensorflow下訓(xùn)練神經(jīng)網(wǎng)絡(luò)模型：手把手教你，MNIST手寫(xiě)數(shù)字識(shí)別

訓(xùn)練好的模型model.save(path)即可

4.關(guān)于GUI設(shè)計(jì)

1）排版

#ui_openimage.py
# -*- coding: utf-8 -*-
# from PyQt5 import QtCore, QtGui, QtWidgets
# from PyQt5.QtCore import Qt
import sys,time
from PyQt5 import QtGui, QtCore, QtWidgets
from PyQt5.QtWidgets import *
from PyQt5.QtCore import *
from PyQt5.QtGui import *

class Ui_Form(object):
    def setupUi(self, Form):
        Form.setObjectName("Form")
        Form.resize(1144, 750)
        self.label_1 = QtWidgets.QLabel(Form)
        self.label_1.setGeometry(QtCore.QRect(170, 130, 351, 251))
        self.label_1.setObjectName("label_1")
        self.label_2 = QtWidgets.QLabel(Form)
        self.label_2.setGeometry(QtCore.QRect(680, 140, 351, 251))
        self.label_2.setObjectName("label_2")
        self.btn_image = QtWidgets.QPushButton(Form)
        self.btn_image.setGeometry(QtCore.QRect(270, 560, 93, 28))
        self.btn_image.setObjectName("btn_image")
        self.btn_recognition = QtWidgets.QPushButton(Form)
        self.btn_recognition.setGeometry(QtCore.QRect(680,560,93,28))
        self.btn_recognition.setObjectName("bnt_recognition")
        #顯示時(shí)間按鈕
        self.bnt_timeshow = QtWidgets.QPushButton(Form)
        self.bnt_timeshow.setGeometry(QtCore.QRect(900,0,200,50))
        self.bnt_timeshow.setObjectName("bnt_timeshow")
        self.retranslateUi(Form)
        self.btn_image.clicked.connect(self.slot_open_image)
        self.btn_recognition.clicked.connect(self.slot_output_digital)
        self.bnt_timeshow.clicked.connect(self.buttonClicked)
        self.center()
        QtCore.QMetaObject.connectSlotsByName(Form)

    def retranslateUi(self, Form): #設(shè)置文本填充label、button
        _translate = QtCore.QCoreApplication.translate
        Form.setWindowTitle(_translate("Form", "數(shù)字識(shí)別系統(tǒng)"))
        self.label_1.setText(_translate("Form", "點(diǎn)擊下方按鈕"))
        self.label_1.setStyleSheet('font:50px;')
        self.label_2.setText(_translate("Form", "0~9"))
        self.label_2.setStyleSheet('font:50px;')
        self.btn_image.setText(_translate("Form", "選擇圖片"))
        self.btn_recognition.setText(_translate("From","識(shí)別結(jié)果"))
        self.bnt_timeshow.setText(_translate("Form","當(dāng)前時(shí)間"))

    # 狀態(tài)條顯示時(shí)間模塊
    def buttonClicked(self):  # 動(dòng)態(tài)顯示時(shí)間
        timer = QTimer(self)
        timer.timeout.connect(self.showtime)
        timer.start()
    def showtime(self):
        datetime = QDateTime.currentDateTime()
        time_now = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime())
        #self.statusBar().showMessage(time_now)
        #self.bnt_timeshow.setFont(QtGui.QFont().setPointSize(100))
        self.bnt_timeshow.setText(time_now)

    def center(self):#窗口放置中央
        screen = QDesktopWidget().screenGeometry()
        size = self.geometry()
        self.move((screen.width() - size.width()) / 2,
                    (screen.height() - size.height()) / 2)


    def keyPressEvent(self, e):
        if e.key() == Qt.Key_Escape:
            self.close()

2）直接運(yùn)行這個(gè)文件（調(diào)用1）

#ui_main.py
import random

from PyQt5.QtWidgets import QFileDialog
from PyQt5.QtGui import QPixmap
from ui_openimage import Ui_Form
import sys
from PyQt5 import QtWidgets, QtGui
from PyQt5.QtWidgets import QMainWindow, QTextEdit, QAction, QApplication
import os,sys
from PyQt5.QtCore import Qt

import tensorflow
from tensorflow.keras.models import load_model
from tensorflow.keras.datasets import mnist
from tensorflow.keras import models
from tensorflow.keras import layers
from tensorflow.keras.utils import to_categorical
import tensorflow.keras.preprocessing.image as image
import matplotlib.pyplot as plt
import numpy as np
import cv2
import warnings
warnings.filterwarnings("ignore")
class window(QtWidgets.QMainWindow,Ui_Form):
    def __init__(self):
        super(window, self).__init__()
        self.cwd = os.getcwd()
        self.setupUi(self)
        self.labels = self.label_1
        self.img=None
    def slot_open_image(self):
        file, filetype = QFileDialog.getOpenFileName(self, '打開(kāi)多個(gè)圖片', self.cwd, "*.jpg, *.png, *.JPG, *.JPEG, All Files(*)")
        jpg = QtGui.QPixmap(file).scaled(self.labels.width(), self.labels.height())
        self.labels.setPixmap(jpg)
        self.img=file

    def slot_output_digital(self):
    	'''path為之前保存的模型路徑'''
        path='/Users/zhangcaihui/PycharmProjects/py38_tf/DL_book_keras/save_the_model.h5'
        model= load_model(path)
        #防止不上傳數(shù)字照片而直接點(diǎn)擊識(shí)別
        if self.img==None:
            self.label_2.setText('請(qǐng)上傳照片！')
            return
        img = image.load_img(self.img, target_size=(28, 28))
        img = img.convert('L')#轉(zhuǎn)灰度圖像
        x = image.img_to_array(img)
        #x = abs(255 - x)
        x = np.expand_dims(x, axis=0)
        print(x.shape)
        x = x / 255.0
        prediction = model.predict(x)
        print(prediction)
        output = np.argmax(prediction, axis=1)
        print("手寫(xiě)數(shù)字識(shí)別為：" + str(output[0]))
        self.label_2.setText(str(output[0]))

if __name__ == "__main__":
  app = QtWidgets.QApplication(sys.argv)
  my = window()
  my.show()
  sys.exit(app.exec_())

5.缺點(diǎn)

界面low

只能識(shí)別單個(gè)數(shù)字

其實(shí)可以將多數(shù)字圖片進(jìn)行裁剪分割，這就涉及到制作數(shù)據(jù)集了

6.遺留問(wèn)題

我自己手寫(xiě)的數(shù)據(jù)照片處理成28281送入網(wǎng)絡(luò)預(yù)測(cè)，識(shí)別結(jié)果紊亂。

反思：自己寫(xiě)的數(shù)據(jù)是RGB，且一張幾KB，圖片預(yù)處理后，按28*28讀入失真太嚴(yán)重了，誰(shuí)有好的方法可以聯(lián)系我！！！

其他的水果識(shí)別系統(tǒng)，手勢(shì)識(shí)別系統(tǒng)啊，改改直接套！

到此這篇關(guān)于Python實(shí)現(xiàn)帶GUI界面的手寫(xiě)數(shù)字識(shí)別的文章就介紹到這了,更多相關(guān)Python手寫(xiě)數(shù)字識(shí)別內(nèi)容請(qǐng)搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家！

您可能感興趣的文章: