使用Python，几行代码实现OCR图片识别，附测试图片和识别效果

Posted 2022-11-18 秋9

目录

1.具体如何做呢？

1.1安装Tesseract-OCR

1.2配置环境

1.3安装Tesseract中文包

1.4.安装pytesseract和pillow

2.代码和测试效果

2.1识别英文图片

2.2 识别中文图片

---

1.具体如何做呢？

1.1安装Tesseract-OCR

windows安装包下载地址：https://github.com/UB-Mannheim/tesseract/wiki

下载的文件名为tesseract-ocr-w64-setup-v5.2.0.20220712.exe

右击管理员运行tesseract-ocr-w64-setup-v5.2.0.20220712.exe

1.2配置环境

1.3安装Tesseract中文包

下载地址和如何安装，见另外一篇分享文章

Tesseract最新中文语言包chi_sim.traineddata(4.0.0)三种获取方式_秋9的博客-CSDN博客

1.4.安装pytesseract和pillow

pip install pytesseract 和pip install pillow

具体操作如下：

D:\\1\\ocr>pip install pytesseract
Collecting pytesseract
  Downloading pytesseract-0.3.10-py3-none-any.whl (14 kB)
Requirement already satisfied: Pillow>=8.0.0 in d:\\python\\python381\\lib\\site-packages (from pytesseract) (9.2.0)
Collecting packaging>=21.3
  Downloading packaging-21.3-py3-none-any.whl (40 kB)
     |████████████████████████████████| 40 kB 123 kB/s
Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in d:\\python\\python381\\lib\\site-packages (from packaging>=21.3->pytesseract) (2.4.7)
Installing collected packages: packaging, pytesseract
  Attempting uninstall: packaging
    Found existing installation: packaging 21.0
    Uninstalling packaging-21.0:
      Successfully uninstalled packaging-21.0
Successfully installed packaging-21.3 pytesseract-0.3.10
WARNING: You are using pip version 21.0.1; however, version 22.3 is available.
You should consider upgrading via the 'd:\\python\\python381\\python.exe -m pip install --upgrade pip' command.

D:\\1\\ocr>pip install pillow
Requirement already satisfied: pillow in d:\\python\\python381\\lib\\site-packages (9.2.0)
WARNING: You are using pip version 21.0.1; however, version 22.3 is available.
You should consider upgrading via the 'd:\\python\\python381\\python.exe -m pip install --upgrade pip' command.

D:\\1\\ocr>

2.代码和测试效果

2.1识别英文图片

代码如下：

from PIL import Image
import pytesseract
path="test2.png"
im=Image.open(path)
text=pytesseract.image_to_string(im)
print(text)

test2.png图片如下：

识别效果：

结论：只有第1个字母识别错误

2.2 识别中文图片

代码如下：

from PIL import Image
import pytesseract
path="test4.png"
im=Image.open(path)
text=pytesseract.image_to_string(im,lang='chi_sim')
print(text)

test4.png图片如下：

识别效果：

中文识别效果比较差。

欢迎小伙伴们，留言讨论