Similar Fragment Retrieval of Animations by a Bag-of-Features Approach

Serial animated cartoons, also called animations, is a kind of popular video documents that describe narratives by videos of cartoons. By using digital techniques, illegal users can divide animations into fragments and distribute them without any copyright permissions. In this paper we focus on the copyright problem of animations and try to retrieve copyright infringement fragments based on key frames. Because of the huge volumes and rapid release of animations, it is impossible to store all the episodes into the database. We propose applying bag-of-features model to retrieve similar fragments based on the visual words extracted from a limited data set. In the experiments, 12 titles of animations are employed and the similar fragments outside database are applied as queries. Our method has achieved above 98% precision at 80% recall for fragments whose durations are over 140 seconds. From the results, we show that a latest release can be retrieved based on the features of the former ones from the same title.