Classification of Real 3D and Fake 3D Video

Abstract

The tremendous growth in communication and media technology and the wide availability of cheaper end using devices have made 3D video communication very popular due to its immersive experience. It has been observed that a 3D video can be produced either by direct accusation using a 3D camera (say real 3D video) or by rendering from a set of 2D images (say fake 3D video). There are several occasions where it is required to distinguish between such real and fake 3D video sequences. In this paper, an algorithm is proposed which can distinguish the real 3D video from the fake one. A set of distinguishing features has been identified which are primarily based on the vertical parallax and sharpness peculiarities of object edges due to 3D acquisition process and rendering. Finally, two different supervised learning classifiers (Support Vector Machines and Linear discriminant analysis), are being trained using these features to detect the fake 3D video sequences. A comprehensive set of experiments has been carried out to justify the applicability of the proposed detection scheme over the recent existing scheme.

Keywords:

• Depth-image-based rendering (DIBR)
• Fake 3D video
• LDA
• Parallax
• Real 3D video
• SIFT
• SVM
• 3DTV

Notes

1 link:“http://www.tanimoto.nuee.nagoya-u.ac.jp/fukushima/mpegftv/”, “http://www.merl.com/pub/tian/NICT-3D/” and “http://www.merl.com/pub/avetro/mvc-testseq/orig-yuv/”

2 as the details presented in “http://realorfake3d.com/ ”

Additional information

Notes on contributors

Shuvendu Rana

Shuvendu Rana received his PhD degree in 2017 and MTech degree in 2013 in computer Science and engineering from Department of Computer Science and Engineering, Indian Institute of Technology Guwahati. He has received his BTech degree in 2009 in computer science and engineering from West Bengal University of Technology. He is currently working as a research associate in Department of Electronic & Electrical Engineering, University of Strathclyde, Glasgow. He is a recipient of TCS scholarship and DST ITS travel grant in his PhD tenure at IIT Guwahati. His research interests include 3D image & video analysis, image & video watermarking, medical imaging, structure from motion, information hiding and multimedia security.

Sibaji Gaj

Sibaji Gaj received his BTech degree in electronics and instrumentation engineering from Heritage Institute of Technology, Kolkata, West Bengal and Dual Degree (MTech+PhD) degrees in computer science and engineering from Indian Institute of Technology Guwahati, in 2017. He is currently working as a data scientist in Kovid Research Lab. His research interests include compressed domain image video processing, deep learning, information hiding, and multimedia security. Email: [email protected]

Arijit Sur

Arijit Sur received his PhD degree in computer science and engineering from Department of Computer Science and Engineering, Indian Institute of Technology Kharagpur. He has received his MSc in computer and information science and MTech in computer science and engineering both from Department of Computer Science and Engineering, University of Calcutta. He is currently working as an assistant professor at Department of Computer Science and Engineering, Indian Institute of Technology Guwahati. He is a recipient of Infosys Scholarship during his PhD tenure at IIT Kharagpur. He got Microsoft Outstanding Young Faculty Program Award at Dept of CSE, IIT Guwahati. His current research interest is multimedia security such as image and video watermarking, steganography & steganalysis and reversible data hiding. Email: [email protected]

Prabin Kumar Bora

Prabin Kumar Bora (M'97) received the BEng degree in electrical engineering from Assam Engineering College, Guwahati, India, in 1984 and the MEng and PhD degrees in electrical engineering from the Indian Institute of Science, Bangalore, in 1990 and 1993, respectively. Currently, he is a professor in the Department of Electronics and Communication Engineering, Indian Institute of Technology, Guwahati. Previously, he was a faculty member with Assam Engineering College, Guwahati; Jorhat Engineering College, Jorhat, India; and Guwahati University, Guwahati. His research interests include video coding, image and video watermarking, perceptual video hashing, and computer vision. Email: [email protected]