python 識別圖片中的漢字

 

我們就識別上面的漢字。

 

安裝軟件tesseract和python庫

https://www.cnblogs.com/sea-stream/p/10961580.html

 

然后新建一個文件夾test,把上面那張圖片放在文件夾里面，再新建一個test文件

寫入如下內容

#coding=utf-8
from PIL import Image
import pytesseract
#上面都是導包，只需要下面這一行就能實現圖片文字識別
text=pytesseract.image_to_string(Image.open('xxx.png'),lang='chi_sim')
print(text)

目錄如下：

運行可能會出現錯誤：

C:\Users\k\Desktop\test>python test.py
Traceback (most recent call last):
  File "test.py", line 5, in <module>
    text=pytesseract.image_to_string(Image.open('xxx.png'),lang='chi_sim')
  File "C:\Users\k\Anaconda3\lib\site-packages\pytesseract\pytesseract.py", line 309, in image_to_string
    }[output_type]()
  File "C:\Users\k\Anaconda3\lib\site-packages\pytesseract\pytesseract.py", line 308, in <lambda>
    Output.STRING: lambda: run_and_get_output(*args),
  File "C:\Users\k\Anaconda3\lib\site-packages\pytesseract\pytesseract.py", line 218, in run_and_get_output
    run_tesseract(**kwargs)
  File "C:\Users\k\Anaconda3\lib\site-packages\pytesseract\pytesseract.py", line 194, in run_tesseract
    raise TesseractError(status_code, get_errors(error_string))
pytesseract.pytesseract.TesseractError: (1, 'Error opening data file C:\\Program Files (x86)\\Tesseract-OCR/tessdata/chi_sim.traineddata Please make sure the TESSDATA_PREFIX environment variable is set to the parent directory of your "tessdata" directory. Failed loading language \'chi_sim\' Tesseract couldn\'t load any languages! Could not initialize tesseract.')

因為tesseract-ocr默認不支持中文識別。 將下載到的文件：chi_sim.traineddata 放到Tesseract-OCR安裝目錄 D:\Program Files (x86)\Tesseract-OCR\tessdata 下

鏈接：https://pan.baidu.com/s/1c-fveIYnm1sQHxX9WRpUZw
提取碼：9ovq

再次運行

python test.py

 

下面是輸出結果

C:\Users\k\Desktop\test>python test.py
風急天高猿嘯衷′ 渚麥冒麥少丑弓飛口。
u邊洛木蕭蕭下′ 不〖長江滾滾來。
萬 悲禾火常作畜′ 年多病獨登台。
艱難苦恨縈霜 渣倒新停澍酉木不=

 

 

參考：

https://www.cnblogs.com/lizhe860/p/8969171.html

https://blog.csdn.net/showgea/article/details/82656515