Robust Alignment of Presentation Videos with Slides

Many presentations consisting of video, audio and slides are being recorded for wider dissemination purposes. Video slide alignment is necessary for efficient review and hence has attracted much attention. However, the recorded video style varies greatly because of different capturing systems, and most existing alignment approaches deal with one of the video styles. In this paper, a more general approach is proposed to make the alignment be applicable to all major video styles. We mainly combine the SIFT (scale invariant feature transform) keypoints and color features to match between video and electronic slides for alignment, and use texture features as a complement. The approach improves the alignment performance, and is able to handle many kinds of video.