How to read the full contents of a manga page?

[ShadowAimai]

The library does indeed work, but only for small sections of a manga page. But is there a way to process an entire page without having to do it manually? It was not clear to me how to do it when reading the documentation.

[HighLiuk]

@ShadowAimai as I explained in #26:

if you look at Mokuro, looks like it combines Comic Text Detector which is great to detect Japanese text and group them to bubbles, then for each bubble you use MangaOcr and voilà (at least in theory)

[HighLiuk]

@ShadowAimai this should be fine using Mokuro:

python3 -m pip install mokuro

from mokuro.manga_page_ocr import MangaPageOcr
from mokuro.utils import dump_json

if __name__ == '__main__':
    mpocr = MangaPageOcr()
    result = mpocr('path/to/image.jpg')
    dump_json(result, 'path/to/result.json')