shinonome-bunko / 東雲文庫

やがて夜は明ける．

In my mind...🤔

graph TD
    A["Images of Books (ex. 国立国会図書館デジタルコレクション)"] -->|OCR| B
    B["Text File (MD? XML?; UTF-8? Shift-JIS?)"] -->|"Parser? (Should I do this?)"| C
    B --> |"Iterate + Modify by Human (Editor in Browser or Git; cf. Wiki, Qiita, Zenn)"| B
    C["Aozora Bunko File Format?"] -->| | D
    D["Publish to Aozora Bunko?"]

Loading

1. Use Existing Aozora Bunko Files as Training Data
   • We can find original texts since Aozora Bunko shows the original version of the texts ("底本").
   • Supervised learning with these data

This Project consists of...

1. Text Recognition
   • OCR with Python
   • Aim to generate texts accurately and quickly also in Japanese vertical texts
2. Viewer/Editor
   • Simple and Fast Viewer and Editor working on Browser
   • Anyone can modify the generated texts either in the Built-in Editor or GitHub (Can we compare the original pictures and the generated texts?)
   • Can this editor be built with Python as well?
3. Text Matching Game
   • Matching Game for Japanese Texts
   • Aim to improve the accuracy of OCR (also for fun, of course!)
   • This game can be a learning material for Japanese learners (like the original concept of Duolingo)
   • cf. Google Captcha

Related Projects

• aozorahack
  • Web Page
  • ideathon: There are many ideas similar to this project!
  • kosakuin: Aozora Bunko Editor (MIT License)
  • aozora-cli: Aozora Bunko CLI (MIT License)
  • aozora-parser.js
  • aozoraflow
• kyukyunyorituryo/AozoraEditor: 青空文庫エディタ
• kyukyunyorituryo/html2aozora
• gearsns/AozoraJavaScriptParser