BubbleCapture is a desktop application that allows users to select speech bubbles and panels in manga pages and extract the text for transcription. The app is built using Electron and Node.js, and uses a combination of image processing and natural language processing techniques to accurately identify speech bubbles and extract their content.
- Select speech bubbles and panels in manga pages with a simple click-and-drag interface
- Automatically extract text from selected speech bubbles, organized by character and dialogue
- Export transcription results to a JSON file for easy use in other applications
- Simple and intuitive user interface, designed with manga readers and transcriptionists in mind
- More soon
To get started with BubbleCapture, follow these simple steps:
- Clone the repository to your local machine
- Install the required dependencies using
npm install
- Start the app using
npm start
Once the app is running, you can open a manga page and use the click-and-drag interface to select speech bubbles and panels. The app will automatically extract the text and organize it by character and dialogue. You can then export the results to a JSON file for easy use in other applications.
BubbleCapture is released under the MIT License. See LICENSE.txt for more information.
BubbleCapture was created as a project to assist in the analysis process of manga pages in general. The app uses several third-party libraries and tools, including: