scaner 6 months ago
parent e3f7d5b275
commit 983a22b2f3

@ -0,0 +1,8 @@
# 默认忽略的文件
/shelf/
/workspace.xml
# 基于编辑器的 HTTP 客户端请求
/httpRequests/
# Datasource local storage ignored files
/dataSources/
/dataSources.local.xml

@ -0,0 +1,11 @@
<?xml version="1.0" encoding="UTF-8"?>
<module type="PYTHON_MODULE" version="4">
<component name="NewModuleRootManager">
<content url="file://$MODULE_DIR$" />
<orderEntry type="jdk" jdkName="Python 3.7 (Scaner)" jdkType="Python SDK" />
<orderEntry type="sourceFolder" forTests="false" />
</component>
<component name="TestRunnerService">
<option name="PROJECT_TEST_RUNNER" value="Unittests" />
</component>
</module>

@ -0,0 +1,7 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="Black">
<option name="sdkName" value="Python 3.7 (python_project)" />
</component>
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.7 (Scaner)" project-jdk-type="Python SDK" />
</project>

@ -0,0 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectModuleManager">
<modules>
<module fileurl="file://$PROJECT_DIR$/.idea/document-scanner.iml" filepath="$PROJECT_DIR$/.idea/document-scanner.iml" />
</modules>
</component>
</project>

Binary file not shown.

After

Width:  |  Height:  |  Size: 43 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 43 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 74 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 99 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 43 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 43 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 74 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 43 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 2.0 MiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 2.0 MiB

@ -0,0 +1,150 @@
from tkinter import *
import tkinter as tk
import tkinter.messagebox as messagebox
import subprocess
from tkinter import filedialog
import pymysql
from flask import Flask, render_template, request, redirect, url_for
conn = pymysql.connect(host='localhost',
user='root',
password='123456',
database='scaner',
port=3306,
charset='utf8')
# 使用 cursor() 方法创建一个游标对象 cursor
cursor = conn.cursor()
print("数据库连接成功!")
# 查询用户信息
def userinfo_query(username, password):
cursor.execute("select * from `user`")
data = cursor.fetchall()
username_list_length = len(data)
for i in range(username_list_length):
username.append(data[i][0])
password.append(data[i][1])
def user_register():
deng = Tk()
deng.title("注册")
deng.geometry("300x200+280+580")
# 在GUI中添加新的输入字段和按钮
label_new_username = Label(deng, text="新账号:")
label_new_username.pack()
entry_new_username = Entry(deng)
entry_new_username.pack()
label_new_password = Label(deng, text="新密码:")
label_new_password.pack()
entry_new_password = Entry(deng, show="*")
entry_new_password.pack()
btn_register = Button(deng, text="注册", command=lambda: register_action(deng, entry_new_username, entry_new_password))
btn_register.pack(side='right', padx=50)
def register_action(deng, entry_new_username, entry_new_password):
cursor.execute("INSERT INTO user (`username`, `password`) VALUES (%s, %s)",
(entry_new_username.get(), entry_new_password.get()))
conn.commit()
deng.destroy()
messagebox.showinfo("注册结果", "注册成功!")
print("注册成功!")
def user_login():
global count
count = 2
username_list = []
password_list = []
userinfo_query(username_list, password_list)
username_input = entry_username.get()
password_input = entry_password.get()
if username_input not in username_list:
messagebox.showerror("登录结果", "账号错误!")
label_message.config(text="账号错误!")
else:
if password_input in password_list:
messagebox.showinfo("登录结果", "登录成功!")
print("debug1")
windows.destroy()
def choose_folde():
print("debug2")
root.destroy()
root5 = tk.Tk()
root5.title('选择图片')
root5.geometry('300x300')
filename = filedialog.askopenfilename(
initialdir="/", # 设置对话框初始打开的目录
title="选择图片",
filetypes=(("图片文件", "*.jpg;*.png;*.gif"), ("所有文件", "*.*")) # 指定文件类型过滤器
)
if filename: # 如果用户选择了文件
# 使用subprocess运行另一个Python脚本并将图片路径作为参数传递
root5.destroy()
subprocess.run(["python", "scan.py", "-i", filename])
exit()
# root.mainloop()
# def callback():
# rootback = tk.Tk()
# rootback.title('用户界面')
# rootback.geometry('300x300')
# tk.Label(rootback, text='请选择你的功能').pack()
# tk.Button(rootback, text="选择需要扫描的图片", command=choose_folde).pack()
# rootback.mainloop()
# windows.destroy()
root = tk.Tk()
root.title('用户界面')
root.geometry('300x300')
tk.Label(root, text='请选择你的功能').pack()
tk.Button(root, text="选择需要扫描的图片", command=choose_folde).pack()
# tk.mainloop()
print("debug3")
else:
label_message.config(text="密码错误!还可以尝试{}".format(3-count))
count += 1
if count == 3:
messagebox.showerror("登录结果", "登录失败!")
label_message.config(text="登录失败!")
btn_login.config(state='disabled')
windows = Tk()
windows.title("登录")
windows.geometry("300x200")
# windows.configure(bg='#3ffff3')
label_username = Label(windows, text="账号:")
label_username.pack()
entry_username = Entry(windows)
entry_username.pack()
label_password = Label(windows, text="密码:")
label_password.pack()
entry_password = Entry(windows, show="*")
entry_password.pack()
btn_login = Button(windows, text="登录", command=user_login)
print("debug0")
btn_login.pack(side='left', padx=50)
entry_password.pack()
btn_login = Button(windows, text='注册', command=user_register)
btn_login.pack(side='right', padx=50)
label_message = Label(windows, text="")
label_message.pack()
windows.mainloop()

@ -0,0 +1,86 @@
we owe owe owe oke ome owk sh ok who o c %K
WHOLE
FOODS
M __A R__K _E T}
WHOLE FOODS MARKET - WESTPORT,.CT 06880
399 POST RD WEST - (203) 227-6858
364 BACON LS
365 BACON LS
3565 BACON LS
365 BACUN iS
BRO TH CHIC
FLOUR ALMUNL
CHKN BRST BNLSS SK
HEAVY CREAM
BALSMC REDUCT
BEEF - GRND - 85/15
JUICE COF CASHEW L
DOCS PINT ORGAx IC
HNY ALMOND Bul TiR
% % ## TAX . 00 BAL
NP
NP
NP
NP
NP
NP
NP
NP
NP
NP
NP
NP
NP
4
4
4
4
11.
~ n o
14.
«
101
99
. 99
. 99
29
19
99
. 80
3.39
. 49
04
. 99
49
. 99
. 33
m mom nom m ot ton n oto onmoy

Binary file not shown.

After

Width:  |  Height:  |  Size: 340 KiB

@ -0,0 +1,182 @@
# 导入工具包
import numpy as np
import argparse
import cv2
import pytesseract
import os
from PIL import Image
# def process_image(image_path):
# try:
# # 使用Pillow库打开并显示图片
# with Image.open(image_path) as img:
# img.show()
# # 在这里添加更多处理图片的代码...
# except IOError:
# print(f"无法打开图片: {image_path}")
def main():
parser = argparse.ArgumentParser(description="处理图片的脚本")
parser.add_argument("-i", "--image", required=True, help="指定要处理的图片的路径")
args = parser.parse_args()
# process_image(args.image)
print("main")
def order_points(pts):
# 一共4个坐标点
rect = np.zeros((4, 2), dtype = "float32")
# 按顺序找到对应坐标0123分别是 左上,右上,右下,左下
# 计算左上,右下
s = pts.sum(axis = 1)
rect[0] = pts[np.argmin(s)]
rect[2] = pts[np.argmax(s)]
# 计算右上和左下
diff = np.diff(pts, axis = 1)
rect[1] = pts[np.argmin(diff)]
rect[3] = pts[np.argmax(diff)]
return rect
def four_point_transform(image, pts):
# 获取输入坐标点
rect = order_points(pts)
(tl, tr, br, bl) = rect
# 计算输入的w和h值
widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
maxWidth = max(int(widthA), int(widthB))
heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
maxHeight = max(int(heightA), int(heightB))
# 变换后对应坐标位置
dst = np.array([
[0, 0],
[maxWidth - 1, 0],
[maxWidth - 1, maxHeight - 1],
[0, maxHeight - 1]], dtype = "float32")
# 计算变换矩阵
M = cv2.getPerspectiveTransform(rect, dst)
warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))
# 返回变换后结果
return warped
def resize(image, width=None, height=None, inter=cv2.INTER_AREA):
dim = None
(h, w) = image.shape[:2]
if width is None and height is None:
return image
if width is None:
r = height / float(h)
dim = (int(w * r), height)
else:
r = width / float(w)
dim = (width, int(h * r))
resized = cv2.resize(image, dim, interpolation=inter)
return resized
# 设置参数
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required = True,
help = "Path to the image to be scanned")
args = vars(ap.parse_args())
print("arg")
print(__name__)
if __name__ == "__main__":
main()
# 读取输入
image = cv2.imread(args["image"])
#坐标也会相同变化
ratio = image.shape[0] / 500.0
orig = image.copy()
image = resize(orig, height = 500)
# 预处理
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) # 色彩空间转换
gray = cv2.GaussianBlur(gray, (5, 5), 0) # 高斯模糊
edged = cv2.Canny(gray, 75, 200)
# 展示预处理结果
print("STEP 1: 边缘检测")
cv2.imshow("Image", image)
cv2.imshow("Edged", edged)
cv2.waitKey(0)
cv2.destroyAllWindows()
# 轮廓检测
cnts = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)[0]
cnts = sorted(cnts, key = cv2.contourArea, reverse = True)[:5] # 降序排列+切片
# 遍历轮廓
for c in cnts:
# 计算轮廓近似
peri = cv2.arcLength(c, True)
# C表示输入的点集数组
# epsilon表示从原始轮廓到近似轮廓的最大距离它是一个准确度参数
# True表示封闭的
approx = cv2.approxPolyDP(c, 0.10 * peri, True) # 近似
# 4个点的时候就拿出来
if len(approx) == 4:
screenCnt = approx
break
# 展示结果
print("STEP 2: 获取轮廓")
cv2.drawContours(image, [screenCnt], -1, (0, 255, 0), 2)
cv2.imshow("Outline", image)
cv2.waitKey(0)
cv2.destroyAllWindows()
# 透视变换
warped = four_point_transform(orig, screenCnt.reshape(4, 2) * ratio)
# 二值处理
warped = cv2.cvtColor(warped, cv2.COLOR_BGR2GRAY)
ref = cv2.threshold(warped, 100, 255, cv2.THRESH_BINARY)[1]
cv2.imwrite('scan.jpg', ref)
# 展示结果
print("STEP 3: 变换")
cv2.imshow("Original", resize(orig, height = 650))
cv2.imshow("Scanned", resize(ref, height = 650))
cv2.waitKey(0)
cv2.destroyAllWindows()
# OCR扫描
preprocess = "blur"
if preprocess == "thresh":
gray = cv2.threshold(ref, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
if preprocess == "blur":
gray = cv2.medianBlur(ref, 3)
cv2.imshow("Detect", gray)
filename = "{}.png".format(os.getpid())
cv2.imwrite(filename, gray)
text = pytesseract.image_to_string(Image.open(filename)) # 调用Tesseract OCR引擎对保存的图像进行文本识别
os.remove(filename)
encodings = ['utf-8', 'latin1', 'iso-8859-1', 'cp1252', 'gbk', 'big5']
for encoding in encodings:
try:
with open("out.txt", 'w', encoding=encoding, errors="replace") as file:
file.write(text)
break
except UnicodeDecodeError:
continue
file.close()
print("text is written to out.txt")
# Wait for pressing any key
cv2.waitKey(0)
cv2.destroyAllWindows()

@ -0,0 +1,33 @@
# https://digi.bib.uni-mannheim.de/tesseract/
# 配置环境变量如E:\Program Files (x86)\Tesseract-OCR
# tesseract -v进行测试
# tesseract XXX.png 得到结果
# pip install pytesseract
# anaconda lib site-packges pytesseract pytesseract.py
# tesseract_cmd 修改为绝对路径即可
from PIL import Image
import pytesseract
import cv2
import os
preprocess = 'blur' #thresh
image = cv2.imread('scan.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
if preprocess == "thresh":
gray = cv2.threshold(gray, 0, 255,cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
if preprocess == "blur":
gray = cv2.medianBlur(gray, 3)
filename = "{}.png".format(os.getpid())
cv2.imwrite(filename, gray)
text = pytesseract.image_to_string(Image.open(filename))
print(text)
os.remove(filename)
cv2.imshow("Image", image)
cv2.imshow("Output", gray)
cv2.waitKey(0)

@ -1,5 +1,6 @@
from tkinter import *
import tkinter as tk
import tkinter.messagebox as messagebox
import subprocess
from tkinter import filedialog
import pymysql
@ -56,6 +57,7 @@ def register_action(deng, entry_new_username, entry_new_password):
(entry_new_username.get(), entry_new_password.get()))
conn.commit()
deng.destroy()
messagebox.showinfo("注册结果", "注册成功!")
print("注册成功!")
@ -71,9 +73,11 @@ def user_login():
password_input = entry_password.get()
if username_input not in username_list:
messagebox.showerror("登录结果", "账号错误!")
label_message.config(text="账号错误!")
else:
if password_input in password_list:
messagebox.showinfo("登录结果", "登录成功!")
print("debug1")
windows.destroy()
@ -114,9 +118,10 @@ def user_login():
print("debug3")
else:
label_message.config(text="密码错误!还可以尝试{}".format(count))
label_message.config(text="密码错误!还可以尝试{}".format(3-count))
count += 1
if count == 3:
messagebox.showerror("登录结果", "登录失败!")
label_message.config(text="登录失败!")
btn_login.config(state='disabled')

Loading…
Cancel
Save