A Study on Automatic Character Detection and Recognition from Comics

DOI Web Site
  • Ishii Daisuke
    Graduate School of Information and Telecommunication Studies, WASEDA University
  • Watanabe Hiroshi
    Graduate School of Information and Telecommunication Studies, WASEDA University

Bibliographic Information

Other Title
  • マンガからの自動人物検出と識別に関する一検討
  • マンガ カラ ノ ジドウ ジンブツ ケンシュツ ト シキベツ ニ カンスル イチ ケントウ

Search this article

Abstract

Recently, comics has been contents with many user not only Japan but also foreign countries. Moreover, demand for digital comic is increased by digital book equipment developing and growth of e-book market. Comics have very complex construction because a lot of elements that picture, texts, onomatopoeia, and so on are drawn on a plane. To extract elements and characters as metadata, we can increase usability of digitized comics. Comics generally have been drawn white and black, so the feature of image is different with natural　picture. Thus, to analyze comic character, we must select method that is able to treat comic image feature. In this paper, we propose specified character detection methods on a comic page by eye detection, face detection, and person recognition that utilize HOG (Histograms of　Oriented Gradient) and SVM (Support Vector Machine). Finally, we obtained 0.93 maximum precision for specified character detection by proposed method.

Journal

Related Projects

See more

Keywords

Details 詳細情報について

Report a problem

Back to top