- 學位論文
漫畫影像特徵與潛藏風格模型用於漫畫風格分析
Manga-Specific Features and Latent Style Model for Manga Style Analysis
摘要
每年都會出版許多日本漫畫(Manga)，同時越來越多的漫畫也推出電子版。在本論文中，我們基於提出的漫畫影像特徵建構潛藏風格模型描述漫畫風格，可以幫助我們建立許多以風格為基礎的應用。本論文提出兩種漫畫影像特徵以描述漫畫頁，利如網點特徵描述材質及陰影，畫格特徵描述畫格配置。這些特徵都是首次被提出用來描述漫畫頁。基於隱含狄利克雷分布的技術，我們可以從漫畫影像特徵得到視覺辭彙來描述漫畫頁，進而找出漫畫頁中潛藏的風格要素。這些風格要素的分布可以用來測量漫畫文件之間的相似度，進而幫助我們發展許多基於風格的應用。 根據實驗結果，這些特別設計用來描述漫畫風格的漫畫影像特徵以及模型，有良好的實驗效果，而且能帶來許多具潛力的延伸應用。
並列摘要
Many mangas (Japanese comics) are published every year, and there are an increasing numbers of mangas published in digital version. In this thesis, a latent style model describing manga styles based on the proposed manga-specific features is constructed to facilitate novel style-based applications. Two manga-specific features, i.e., screentone features showing texture and shade, and panel features showing panel arrangement, are firstly proposed to describe manga pages. Based on the latent Dirichlet allocation technique, we discover latent style elements embedded in manga documents, which are described by visual words derived from manga-specific features. Distributions of style elements are then used to measure similarity between manga documents, and facilitate the development of various style-based applications. Experimental results show that the features and models especially designed for describing manga styles yield promising performance and could bring many potential extensions.