Tesseract基本使用
版本:
Tesseract OCR v5.0.0-alpha
Git Hub 地址:
https://github.com/tesseract-ocr/
语言包:
https://github.com/tesseract-ocr/tessdata
文档:
https://github.com/tesseract-ocr/docs
https://stackoverflow.com/questions/44619077/pytesseract-ocr-multiple-config-options
Page segmentation modes:
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.
11 Sparse text. Find as much text as possible in no particular order.
12 Sparse text with OSD.
13 Raw line. Treat the image as a single text line,
bypassing hacks that are Tesseract-specific.
基本命令演示:
tesseract filename output -l lang --psm 1
Tesseract OCR训练 Tesseract项目中的训练介绍
https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract-4.00
使用jTessBoxEditor来训练自己的数据
https://www.jianshu.com/p/31afd7fc5813
https://www.cnblogs.com/cnlian/p/5765871.html
https://www.cnblogs.com/xpwi/p/9604567.html
采用这个工具遇到的问题(未解决)
案例相关
https://github.com/tesseract-ocr/tesseract/issues/1452
http://tpgit.github.io/UnOfficialLeptDocs/leptonica/index.html
改进质量
https://github.com/tesseract-ocr/tesseract/wiki/ImproveQuality
TensorFlow训练
EasyPR是一个开源的中文车牌识别系统
https://github.com/liuruoze/EasyPR
https://www.cnblogs.com/subconscious/p/3979988.html
其他公司的产品测试:
http://khmerocr.open.org.kh/api/ocr_image_to_text by providing input based-64 image.
编程语言
编程语: python
Tesseract库: pytesseract
图像处理库: OpenCV