An ontology-based framework for the automated analysis and interpretation of comic books' images

Since the beginning of the twenty-first century, the cultural industry has been through a massive and historical mutation induced by the rise of digital technologies. The comic books industry keeps looking for the right solution and has not yet produced anything as convincing as the music or movie have. A lot of energy has been spent to transfer printed material to digital supports so far. The specificities of those supports are not always exploited at the best of their capabilities, while they could potentially be used to create new reading conventions. In spite of the needs induced by the large amount of data created since the beginning of the comics history, content indexing has been left behind. It is indeed quite a challenge to index such a composition of textual and visual information. While a growing number of researchers are working on comic books’ image analysis from a low-level point of view, only a few are tackling the issue of representing the content at a high semantic level. We propose in this article a framework to handle the content of a comic book, to support the automatic extraction of its visual components and to formalize the semantic of the domain’s codes. We tested our framework over two applications: 1) the unsupervised content discovery of comic books’ images, 2) its capabilities to handle complex layouts and to produce a respectful browsing experience to the digital comics reader.