Google Cloud Vision API - TEXT_DETECTION

Question

When I try to recognize text in an image, for example, the Italian word "Perchè", the Vision API will return the word "Perche" (return "e", not the correct "è").

I do not want to use languageHints to try to get the best results, because I have to do OCR recognition in different languages.

What is the problem?

Answer 1

This is a known issue with the Cloud Vision API when you are not using language prompts.

You can see the actual error report here .

accepted, , , . , .