Similar Manga Retrieval Using Visual Vocabulary Based on Regions of Interest

Manga, a kind of graphic novels expressed by sequential line drawings, is an important document image publication which is invoking more and more attentions for their copyright protection. Because of simple constructions and abstract expression styles, similar copies are always applied in plagiarisms of mangas. In addition, the enormous volume of copyrighted manga publications issues a challenge to the task of detecting suspicious images. Considering only some regions of interests (ROIs) require copyright protection, we propose a bag-of-features method using visual words based on ROIs for similar manga retrieval. In the experiments, we applied real manga publications as data and proved the effectiveness of the proposed method.