In this paper, we propose a content-based manga retrieval framework. For this reason, applying content-based multimedia retrieval techniques to manga search would have the potential to make the manga-search experience more intuitive, efficient, and enjoyable. They are not suitable for large-scale search and searches cannot take the images (contents) of manga into consideration. ![]() However, current e-manga archives offer very limited search support, i.e., keyword-based search by title or author. Experimental results showed that the proposed framework is efficient and scalable (70 ms from 21,142 pages using a single computer with 204 MB RAM). To the best of our knowledge, Manga109 is currently the biggest dataset of manga images available for research. For evaluation, we built a novel dataset of manga images, Manga109, which consists of 109 comic books of 21,142 pages drawn by professional manga artists. Based on the interface, two interactive reranking schemes are presented: relevance feedback and query retouch. For querying, the system provides a sketch-based interface. The proposed system consists of efficient margin labeling, edge orientation histogram feature description with screen tone removal, and approximate nearest-neighbor search using product quantization. To make the manga search experience more intuitive, efficient, and enjoyable, we propose a manga-specific image retrieval system. ![]() Manga (Japanese comics) are popular worldwide.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |