Japanese / English


論文の言語 英語
著者 Weihan Sun, Koichi Kise
論文名 Copyright Protection of Line Drawings:Copyrighted Part Detection Using Cascade Classifiers
論文誌名 Proceedings of the 2nd China-Japan-Korea Joint Workshop on Pattern Recognition (CJKPR2010)
ページ pp.9-10
年月 2010年11月
要約 To protect the copyright of line drawings, we proposed an image retrieval method to detect both printed and handwritten partial copies. However, the enormous volumes of line drawing publications with copyright cause the problem of scalability. Since not the whole image requires copyright protection, a practical method should detect the copyrighted parts only. In this paper, we propose applying object detection technique to detect copyrighted parts. By using cascade classifiers, we achieved the detection of comic characters’ faces, which are important copyrighted parts of line drawing publications. The experimental results show the effectiveness of this method.