Skip to content

Japanese text scanning software for Light Novels using Tesseract OCR and OpenCV

License

Notifications You must be signed in to change notification settings

ahnaf-zamil/light-novel-ocr

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Light Novel OCR

Program to extract text from untranslated/Japanese Light Novel images using Tesseract and OpenCV.

Inspiration

I'm a huge Light Novel fan, and sometimes I see get untranslated novel PDFs or images which cannot be copy/pasted to translate. Google Lens also cannot translate these files for some odd reason. So I ended up making this piece of software to convert those images to text format, and then just paste that into DeepL or Google Translate to spend my entire afternoon reading.

Demonstration

Watch this video: https://www.youtube.com/watch?v=9O7bycz-1k0