Skip to content

Latest commit

 

History

History
22 lines (15 loc) · 785 Bytes

README.md

File metadata and controls

22 lines (15 loc) · 785 Bytes

ocr_recognition

use java opencv tesseract ocr image words detects and recognition,use python generate jTessBoxEditor train box file

Let's see the word detect and recognition results:


recognition result:


recognition result

The draw_text_image.py is used to generate yours own box train file.

see my bolg my bolg for more detail