OCR Chinese - download Tesseract Chinese OCR files and try out this method

[pythonLiNM]

How can OCR recognize Chinese ，ths!!

[kensoh]

See below comment which is verified to work for TagUI engine, the engine used by RPA for Python.

1. download Tesseract Chinese OCR files and put them in the correct SikuliX directory https://github.com/kelaberetiv/TagUI/issues/1215#issuecomment-1110529037

2. use the following Python code in your Python script to switch to Chinese OCR

import rpa as r
r.init(visual_automation = True)

r.vision('import org.sikuli.script.TextRecognizer as TR')
r.vision('Settings.OcrReadText = True')
r.vision('Settings.OcrLanguage = "chi_sim"')
r.vision('TR.reset()')

Let me know how it goes! I don't have a Windows laptop to test above method.