handwritten text recognition using Google.Cloud.Vision.V1 API. Why languages not detect 100% ?

[bhagya]

handwritten text detection using google.cloud,.vision.v1 . I was create a project and it will detect English, Hindi ,Marathi languages 100 % accuracy but in case detection with Malayalam, Kannada it was detect 70 percent accuracy. I want to detect all Indian languages with 100% accuracy. Please give me solution . C# language used for project. .NET Frameworks 

[Andre_Fiesco · Accepted solution]

According to this documentation,both Malayalam and Kannada are supported. But they are not supported by handwriting scripts, only the following languages are supported or are in experimental phase:

Handwriting scripts

The following scripts are supported for handwriting recognition. Check the language tables above for languages that use each script.

Script Tag	Name	Support Level
Beng	Bengali	Experimental
Cyrl	Cyrillic	Experimental
Deva	Devanagari	Experimental
Grek	Greek	Experimental
Hani	Chinese	Experimental
Jpan	Japanese	Supported
Kore	Korean	Supported
Latn	Latin	Supported
vi	Vietnamese	Experimental

Since the language is not supported by handwriting scripts, its accuracy might differ from the languages supported.    

If this is impacting your application or your business, you can file a feature request using the following link. File the feature request, and they will assist you with the feature you are trying to implement.