centos7下安裝tesseract-ocr進行驗證碼識別

摘要：

　　centos7安裝依賴庫

　　tesseract配置

　　代碼例子

centos7安裝依賴庫

• 安裝centos系統依賴

  yum install -y automake autoconf libtool gcc gcc-c++ yum install -y libpng-devel libjpeg-devel libtiff-devel

• 安裝leptonica

  wget http://www.leptonica.org/source/leptonica-1.72.tar.gz tar xvzf leptonica-1.72.tar.gz cd leptonica-1.72/ ./configure make && make install

• 安裝tesseract-ocr

  wget https://github.com/tesseract-ocr/tesseract/archive/3.04.zip unzip 3.04.zip cd tesseract-3.04/ ./configure make && make install sudo ldconfig

• 部署模型

  • 在https://github.com/tesseract-ocr/tessdata 下載對應語言的模型文件
  • 將模型文件移動到/usr/local/share/tessdata

• 安裝requirements.txt中的python依賴庫

  pip install -r requirements.txt

tesseract配置

• 在/usr/local/share/tessdata創建eng.user-patterns寫入

  \n\n\n\n\n\n

  表示識別6位字符（或數字）

• 在/usr/local/share/tessdata/configs創建myconfig寫入

  #識別白名單 tessedit_char_whitelist abcdefghijklmnopqrstuvwxyz0123546789 #用戶正則模式匹配 user_patterns_suffix user-patterns

• psm參數說明

  -psm N Set Tesseract to only run a subset of layout analysis and assume a certain form of image. The options for N are: 0 = Orientation and script detection (OSD) only. 1 = Automatic page segmentation with OSD. 2 = Automatic page segmentation, but no OSD, or OCR. 3 = Fully automatic page segmentation, but no OSD. (Default) 4 = Assume a single column of text of variable sizes. 5 = Assume a single uniform block of vertically aligned text. 6 = Assume a single uniform block of text. 7 = Treat the image as a single text line. 8 = Treat the image as a single word. 9 = Treat the image as a single word in a circle. 10 = Treat the image as a single character.

代碼例子

import pytesseract
from PIL import Image

image = Image.open('code.png')
code = pytesseract.image_to_string(image)
print code