Frame Border Detection for Digitized Historical Footage

Frame Border Detection for Digitized Historical Footage

Automatic video analysis of digitized historical analog films is influenced by video quality, composition and scan artifacts called overscanning. This paper provides a first pipeline to crop the mainframe window by detecting Sprocket-Holes and interpreting the geometric hole layout to distinguish between two different film reel types (16mm and 9.5mm). Therefore, an heuristic approach based on histogram features is explored. Finally, our results demonstrate a first baseline for future research.

Article Download
Daniel Helm, Bernhard Pointner, Martin Kampel, Frame Border Detection for Digitized Historical Footage, in: Proceedings of the Joint Austrian Computer Vision and Robotics Workshop (August 2020), 114-115.
Article cover
978-3-85125-752-6