Video codec identification extending the idempotency property
Paolo Bestagini, Simone Milani, Marco Tagliasacchi, Stefano Tubaro · Virtual Community of Pathological Anatomy (University of Castilla La Mancha) · 2013
Video codec identification is an important task when it comes to prove the authenticity of video content. Indeed, video sequences are usually available in compressed format since the very acquisition. Therefore, being able to detect the adopted coding architecture reveals information about both the possible presence of alterations, and video origin. The paper presents two detectors that permit to identify the adopted coding architecture for a given video sequence. Both of them rely on the concept of idempotent operators, i.e., processing schemes that do not alter significantly a signal no matter how many times they are sequentially applied. The first detector extend the robustness of the idempotent detector permitting an effective detection even when additional compressions are interposed between the content creation and its analysis. The second detector extends the possibilities of the idempotent detector by permitting the identification of coding schemes that are not known by the analyst. Experimental results show that both solutions obtain a good accuracy (higher than 80 %).