Detecting Interlaced or Progressive Source of Video

In this paper we introduce an algorithm - commonly known as a film mode detector - for separating progressive source video from interlaced source video. Due to interlacing artifacts in the presence of motion, a difference in isophote curvature can be measured and a threshold for effective classification can be set. This can be used in a video converter to ensure high quality output. We studied and compared the two approaches

[1]  Flemming Topsøe,et al.  Jensen-Shannon divergence and Hilbert space embedding , 2004, International Symposium onInformation Theory, 2004. ISIT 2004. Proceedings..

[2]  Erwin B. Bellers,et al.  De-Interlacing: A Key Technology for Scan Rate Conversion , 2000 .

[3]  Gerard de Haan,et al.  An evolutionary architecture for motion-compensated 100 Hz television , 1995, IEEE Trans. Circuits Syst. Video Technol..

[4]  R. J. Schutten,et al.  Real-time 2-3 Pull-down Elimination Applying Motion Estimation/compensation In A Programmable Device , 1998, International 1998 Conference on Consumer Electronics.

[5]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[6]  Mads Nielsen,et al.  A Total Variation Motion Adaptive Deinterlacing Scheme , 2005, Scale-Space.

[7]  J. Koenderink,et al.  Representation of local geometry in the visual system , 1987, Biological Cybernetics.

[8]  David G. Stork,et al.  Pattern classification, 2nd Edition , 2000 .

[9]  Shamik Sural,et al.  Object Level Frame Comparison for Video Shot Detection , 2005, 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1.