Program to extract text from untranslated/Japanese Light Novel images using Tesseract and OpenCV.
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.
Watch this video: https://www.youtube.com/watch?v=9O7bycz-1k0