PROJECT TITLE :

Content-Aware Video2Comics With Manga-Style Layout

ABSTRACT:

We introduce during this paper a replacement approach that conveniently converts conversational videos into comics with manga-vogue layout. With our approach, the manga-style layout of a comic book page is achieved during a content-driven manner, and the most elements, as well as panels and word balloons, that represent a visually pleasing comic page are intelligently organized . Our approach extracts key frames on speakers by employing a speaker detection technique such that word balloons will be placed near the corresponding speakers. We tend to qualitatively measure the knowledge contained in an exceedingly comic page. With the initial layout automatically determined, the final comic page is obtained by maximizing such a measure and optimizing the parameters referring to the optimal display of comics. An efficient Markov chain Monte Carlo sampling algorithm is designed for the optimization. Our user study demonstrates that users a lot of prefer our manga-style comics to purely Western style comics. Extensive experiments and comparisons against previous work also verify the effectiveness of our approach.