Hybrid Identification of Frame Areas in Manga Using Image Recognition and Microtask Crowdsourcing

DOI
  • MIHARA Tetsuya
    Faculty of Library, Information and Media Studies University of Tsukuba
  • ISHIKAWA Natsuki
    College of Media Arts, Science and Technology University of Tsukuba
  • TOYOTA Shohei
    Graduate School of Library, Information and Media Studies University of Tsukuba
  • NAGAMORI Mitsuharu
    Faculty of Library, Information and Media Studies University of Tsukuba
  • SUGIMOTO Shigeo
    Faculty of Library, Information and Media Studies University of Tsukuba

Bibliographic Information

Other Title
  • 画像認識とマイクロタスク型クラウドソーシングを組み合わせたマンガのコマ領域の判定

Abstract

<p>Frames are the most fundamental objects in the expression of manga. Many technologies have been developed to identify frame areas from manga graphics, however, there is no universal method that can identify frames as well as human readers can from various types of manga expressions. We propose a hybrid identification method of frames that combines image recognition with microtask crowdsourcing. This hybrid method brings together the accuracy of human readers, and the efficiency of dispersed identification tasks.</p>

Journal

Details

  • CRID
    1390564238000865024
  • NII Article ID
    130007423953
  • DOI
    10.11517/pjsai.jsai2018.0_4m105
  • Text Lang
    ja
  • Data Source
    • JaLC
    • CiNii Articles
  • Abstract License Flag
    Disallowed

Report a problem

Back to top