Manga OCR

Optical character recognition for Japanese text, with the main focus being Japanese manga. It uses a custom end-to-end model built with Transformers' Vision Encoder Decoder framework.

Manga OCR can be used as a general purpose printed Japanese OCR, but its main goal was to provide a high quality text recognition, robust against various scenarios specific to manga:

• both vertical and horizontal text
• text with furigana
• text overlaid on images
• wide variety of fonts and font styles
• low quality images

Unlike many OCR models, Manga OCR supports recognizing multi-line text in a single forward pass, so that text bubbles found in manga can be processed at once, without splitting them into lines.

Installation

You need Python 3.6+.

If you want to run with GPU, install PyTorch as described here, otherwise this step can be skipped.

Run:

pip install manga-ocr

Usage

Running in the background

Manga OCR can run in the background, processing new images as they appear.

You might then use a tool like ShareX to manually capture a region of the screen and let the OCR read it either from the system clipboard, or a specified directory.

For example:

• To read images from clipboard and write recognized texts to clipboard, run:

  manga_ocr
  

• To read images from ShareX's screenshot folder, run:

  manga_ocr "/path/to/sharex/screenshot/folder"
  

• To see other options, run:

  manga_ocr --help
  

If manga_ocr doesn't work, you might also try replacing it with python -m manga_ocr.

Python API

from manga_ocr import MangaOcr

mocr = MangaOcr()
text = mocr('/path/to/img')

or

import PIL.Image

from manga_ocr import MangaOcr

mocr = MangaOcr()
img = PIL.Image.open('/path/to/img')
text = mocr(img)

Usage tips

• OCR supports multi-line text, but the longer the text, the more likely some errors are to occur. If the recognition failed for some part of a longer text, you might try to run it on a smaller portion of the image.
• The model was trained specifically to handle manga well, but should do a decent job on other types of printed text, such as novels or video games. It probably won't be able to handle handwritten text though.
• The model always attempts to recognize some text on the image, even if there is none. Because it uses a transformer decoder (and therefore has some understanding of the Japanese language), it might even "dream up" some realistically looking sentences! This shouldn't be a problem for most use cases, but it might get improved in the next version.

Examples

Here are some cherry-picked examples showing the capability of the model.

image	Manga OCR result
	素直にあやまるしか
	立川で見た〝穴〟の下の巨大な眼は：
	実戦剣術も一流です
	第３０話重苦しい闇の奥で静かに呼吸づきながら
	よかったじゃないわよ！何逃げてるのよ！！早くあいつを退治してよ！
	ぎゃっ
	ピンポーーン
	ＬＩＮＫ！私達７人の力でガノンの塔の結界をやぶります
	ファイアパンチ
	少し黙っている
	わかるかな〜？
	警察にも先生にも町中の人達に！！

Acknowledgments

This project was done with the usage of Manga109-s dataset.