{
  "id": "1910.09233",
  "version": "v1",
  "published": "2019-10-21T09:37:46.000Z",
  "updated": "2019-10-21T09:37:46.000Z",
  "title": "CNN based Extraction of Panels/Characters from Bengali Comic Book Page Images",
  "authors": [
    "Arpita Dutta",
    "Samit Biswas"
  ],
  "comment": "6 pages, 3 tables and 3 figures. Accepted at GREC 2019 in conjunction with ICDAR 2019",
  "categories": [
    "cs.CV"
  ],
  "abstract": "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-10-21T09:37:46.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "bengali comic book page images",
      "extraction",
      "panels/characters",
      "bengali comic book image dataset"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 6,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}