非常奇怪的输出,用于我的文本提取程序

时间:2018-07-28 01:31:40

标签: python python-3.x image python-imaging-library python-tesseract

这是我的程序,从图像程序中提取文本:

import pytesseract
from PIL import Image
import os
from os.path import join
import sys
con_1 = True
store_1 = []
store_2 = []
store_3 = []
con_1 = True
print("Welcome to my Text Extraction from Image Program. Here you can extract text from any image.")
while con_1:
    image_name = input("Enter your image's name:")
    for root, dirs, files in os.walk("/home/"):
        if image_name in files:
           found = join(root, image_name)
           store_1.append(found)
    if len(store_1) == 0:
       ask_1 = str(input("Your image was not found. Do you want to try again(Y/n)?:"))
       if ask_1 == "Y" or ask_1 == "y":
          con_1 = True
       elif ask_1 == "N" or ask_1 == "n":
          con_1 = False
       else:
          print("Your input is out of bounds. Please try again.")
    else:
        print("Your image was successfully found.")
        image_open = Image.open(found)
        image_text = pytesseract.image_to_string(image_open)
        print(image_text)
        break

这是我正在测试的图像: enter image description here

这是我见过的最奇怪的输出:

‘Understanding how computer memory
ia tire terrae tec
programming lan

这是我正在测试的另一张图片:enter image description here

另一个非常奇怪的输出:

Sesh chee nia ec Hiok pc



RU hun oe
mete een
machines work while still being easy to learn.

我从未见过我的程序给我如此偏离目标和奇怪的输出。我完全不知道这是怎么回事。我非常想知道如何修复它以及为什么我的程序出现故障。

0 个答案:

没有答案