CNN based Extraction of Panels/Characters from Bengali Comic Book Page Images
This work addresses the need for digitizing comic books for mobile reading and automation, but it is incremental as it builds on existing YOLO and CNN methods for a specific domain.
The paper tackles the problem of automatically extracting panels and characters from comic book page images, which is challenging due to diverse drawing styles, and proposes a CNN-based architecture that achieves remarkable results on datasets including a new Bengali dataset and other public datasets.
Peoples nowadays prefer to use digital gadgets like cameras or mobile phones for capturing documents. Automatic extraction of panels/characters from the images of a comic document is challenging due to the wide variety of drawing styles adopted by writers, beneficial for readers to read them on mobile devices at any time and useful for automatic digitization. Most of the methods for localization of panel/character rely on the connected component analysis or page background mask and are applicable only for a limited comic dataset. This work proposes a panel/character localization architecture based on the features of YOLO and CNN for extraction of both panels and characters from comic book images. The method achieved remarkable results on Bengali Comic Book Image dataset (BCBId) consisting of total $4130$ images, developed by us as well as on a variety of publicly available comic datasets in other languages, i.e. eBDtheque, Manga 109 and DCM dataset.