An active contour model for speech balloon detection in comics

Christophe Rigaud, Dimosthenis Karatzas, Joost Van de Weijer, Jean-Christophe Burie, Jean-Marc Ogier

Proceedings of International Conference of Document Analysis and Recognition (ICDAR), 2013

Image not found


Comic books constitute an important cultural heritage asset in many countries. Digitization combined with subsequent comic book understanding would enable a variety of new applications, including content-based retrieval and content re- targeting. Document understanding in this domain is challenging as comics are semi-structured documents, combining semantically important graphical and textual parts. Few studies have been done in this direction. In this work we detail a novel approach for closed and non-closed speech balloon localization in scanned comic book pages, an essential step towards a fully automatic comic book understanding. The approach is compared with existing methods for closed balloon localization found in the literature and results are presented.

Citation BibTeX

    title = {An active contour model for speech balloon detection in comics},
    author = {Rigaud, Christophe and Karatzas, Dimosthenis and Van de Weijer, Joost and Burie, Jean-Christophe and Ogier, Jean-Marc},
    booktitle = {Proceedings of the 12th International Conference on Document Analysis and Recognition (ICDAR)},
    pages = {1240-1244},
    year = {2013}


Download PDF version

GitHub depository