Extended alphabets in TextRecognition

1. Can VNRecognizeTextRequest return / identify results with extended alphabets? Letters like Ö, Ä, Å or ü.

- I've tested by setting Finnish to recognizedLanguages, but to no effect. It has not recognized the letters correctly.


2. It identify japanese, chinese and other asian character sets?

Replies

Hi masterblaster,


For a long time I wondered why my app does not recognize German umlauts (e.g. Ü ö ä or a ß) with VNRecognizeTextRequest.


Now I found out that umlauts are only recognized if I set :

.recognitionLevel= .fast and

.usesLanguageCorrection = false

Unfortunately, the .customWords seem not to work anymore and the quality of the text recognition is not good.


At this time, the VNRecognizeTextRequest only seems to support en-US.

VNRecognizeTextRequest.supportedRecognitionLanguages() always returns 1 value of en-US.


Cheers,

Michael

In iOS 14, the language support has been improved.

The .fast pass can now recognize: ["en-US", "fr-FR", "it-IT", "de-DE", "es-ES", "pt-BR"]

The accurate pass can also read chinese. ["en-US", "fr-FR", "it-IT", "de-DE", "es-ES", "pt-BR", "zh-Hans", "zh-Hant"]