magiv2 / README.md
ragavsachdeva's picture
Create README.md
bd1dc48 verified
|
raw
history blame
4.61 kB
metadata
language:
  - en
tags:
  - Manga
  - Object Detection
  - OCR
  - Clustering
  - Diarisation
Tails Tell Tales
Chapter-Wide Manga Transcriptions With Character Names
Ragav Sachdeva, Gyungin Shin and Andrew Zisserman
University of Oxford
Static BadgeDynamic JSON Badge

image/png

Usage

from PIL import Image
import numpy as np
from transformers import AutoModel
import torch

model = AutoModel.from_pretrained("ragavsachdeva/magiv2", trust_remote_code=True).cuda().eval()


def read_image(path_to_image):
    with open(path_to_image, "rb") as file:
        image = Image.open(file).convert("L").convert("RGB")
        image = np.array(image)
    return image

chapter_pages = ["page1.png", "page2.png", "page3.png" ...]
character_bank = {
    "images": ["char1.png", "char2.png", "char3.png", "char4.png" ...],
    "names": ["Luffy", "Sanji", "Zoro", "Ussop" ...]
}

chapter_pages = [read_image(x) for x in chapter_pages]
character_bank["images"] = [read_image(x) for x in character_bank["images"]]

with torch.no_grad():
    per_page_results = model.do_chapter_wide_prediction(chapter_pages, character_bank, use_tqdm=True, do_ocr=True)

transcript = []
for i, (image, page_result) in enumerate(zip(chapter_pages, per_page_results)):
    model.visualise_single_image_prediction(image, page_result, f"page_{i}.png")
    speaker_name = {
        text_idx: page_result["character_names"][char_idx] for text_idx, char_idx in page_result["text_character_associations"]
    }
    for j in range(len(page_result["ocr"])):
        if not page_result["is_essential_text"][j]:
            continue
        name = speaker_name.get(j, "unsure") 
        transcript.append(f"<{name}>: {page_result['ocr'][j]}")
with open(f"transcript.txt", "w") as fh:
    for line in transcript:
        fh.write(line + "\n")

License and Citation

The provided model and datasets are available for unrestricted use in personal, research, non-commercial, and not-for-profit endeavors. For any other usage scenarios, kindly contact me via email, providing a detailed description of your requirements, to establish a tailored licensing arrangement. My contact information can be found on my website: ragavsachdeva [dot] github [dot] io

@misc{magiv2,
      title={Tails Tell Tales: Chapter-Wide Manga Transcriptions with Character Names}, 
      author={Ragav Sachdeva and Gyungin Shin and Andrew Zisserman},
      year={2024},
      eprint={2408.00298},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2408.00298}, 
}