DH Seminar Lecture - Comics analysis and Indexing
Born in the 19th century, "comics" (Bande Dessinée in French) is a visual medium used to express ideas via images, often combined with text and graphics.
"Comics" is often considered as the 9th art, the sequential art, disseminated through the progress of the printing press throughout the world in newspapers, books and magazines. Nowadays, the development of the new technologies and the World Wide Web is giving birth to a new form of paperless comics that takes advantage of the virtual world freedom.
However, traditional comics still represent an important cultural heritage in many countries. They have not yet received the same level of attention as music, cinema or
literature about their adaptation to the digital format. Using information technologies with "classic" comics would facilitate the exploration of digital libraries, faster theirs translations,
allow augmented reading (improvement of content during reading, on demand and personalized), speech playback for the visually impaired, etc.
Cultural heritage preservation organizations such as the CIBDI in Angoulême (French acronym for International City of Comic books and Images),
the Kyoto International Manga Museum and the digitalcomicmuseum.com website in USA have already digitized hundreds of comic albums that some are now in the public domain.
Despite the expending market place of digital comics, few researches have been carried out to take advantage of the added value provided by these new media.
The difficulty of analyzing the "Bandes Dessinées", comics and mangas comes from the large diversity of contents.
Indeed, each author has his own style both in terms of drawing and representation of texts. Developing methods for extracting and indexing comics content is a significant challenge.
In this talk, I will present the different strategies used to extract the elements of comic strips such as panels, speech balloons, text, characters and links that may exist between these elements.