Cartoon animation summarization using multi-scaled keyframes

Abstract

This research proposes a novel method to generate keyframes from cartoon animation with the aim to improve the details and completeness of contents represented by keyframes. Consider that general techniques on video summarization usually discard some important contents due to its restriction on aspect ratio; this research thus proposes a new method using panorama technology to add more details to be included in each keyframe. The concept is to mark the time code based on shot boundary and optical flow direction. The period of time between every two consecutive marked time codes is used to form a shot sequence which is actually a sequence of frames. The global and local optical flows are also used to determine how to select the frames and when to stitch the frames together according to the rules. Each of these generated keyframes is treated as a comic panel and they are organized to be represented in comic book style. The proposed algorithm aims to fit several comic panels into a comic page while also optimizing its spaces using various types of arrangements. The results of this proposed method are the pages consist of comic panels that aesthetically represent the cartoon animation in a similar way to their respective comic adaptations.