Question

18.2. Tesseract

Tesseract：开源的OCR识别引擎，初期Tesseract引擎由HP实验室研发，后来贡献给了开源软件业，后由Google进行改进、修改bug、优化，重新发布。

18.2.1. 安装 Tesseract

neo@MacBook-Pro-Neo ~/workspace/python/ocr % brew install tesseract
neo@MacBook-Pro-Neo ~/workspace/python/ocr % brew install tesseract-lang
neo@MacBook-Pro-Neo ~/workspace/python/ocr % pip3 install pytesseract

18.2.2. 演示 Tesseract

#!/usr/bin/python3
# -*- coding:utf-8 -*-

from PIL import Image
import pytesseract

# 英文识别
english = pytesseract.image_to_string(Image.open("english.png"))
print(english)

print('-' * 50)

# 简体中文识别
chinese = pytesseract.image_to_string(Image.open("chinese.png"), lang='chi_sim')
print(chinese)	

18.2.3.