an application to automatically extract text from comic books.
cbrTekStraktor is an application to automatically extract text from the text bubbles or speech balloons present in comic book reader files (CBR). Its prime goal is to perform analysis on the texts of comic books. cbrTekStraktor can however also be used for scanlation or similar purposes.
The application also enables to manually define text areas in CBR files. The application comprises a simple graphical editor for further processing the extracted text.
The text extraction is achieved by a combination of statistical and graphical processing operations. ...
Java source code for image processing books by Burger & Burge
NOTE: The source repository for this project has been moved to a NEW LOCATION:
************************************************************************************
https://github.com/imagingbook/imagingbook-public
************************************************************************************
Scribe Software is a software system for the nondestructive scanning and digitization of books with the Internet Archive's Scribe machine. The Java UI and PHP image processing pipeline produce books for www.archive.org and other digital libraries.