Int. J. Signal and Imaging Systems Engineering, Vol. 1, Nos. 3/4, 2008 185
Copyright © 2008 Inderscience Enterprises Ltd.
A robust framework for automated digital video
inpainting
Suneet Grover and Ankush Mittal*
Department of Electronics and Computer Engineering,
Indian Institute of Technology Roorkee,
247667 Roorkee, India
E-mail: suneet.grover@gmail.com
E-mail: ankumfec@iitr.ernet.in
*Corresponding author
Sumit Gupta
Department of Computer Science and Engineering,
MVGR College of Engineering,
Vizianagaram, 530030 AP, India
E-mail: sumit108@hotmail.com
Anil K. Sarje and Nitin Kaushik
Department of Electronics and Computer Engineering,
Indian Institute of Technology Roorkee,
247667 Roorkee, India
E-mail: sarjefec@iitr.ernet.in
E-mail: ntin.kaushik@gmail.com
Abstract: In this paper, a novel method for filling-in the missing information in images and
videos is proposed. The algorithm presented here is able to reconstruct the structure as well as the
texture. The pixel values are chosen by interpolating and searching the similar patch in a small
window in the input image, and are filled in an order depending on their confidence values.
The approach for video inpainting involves the automated tracking of the object selected for
removal, followed by filling-in the holes while enforcing the global spatio-temporal consistency.
Experiments show the effectiveness of our algorithm in tracking and removing large occluding
objects as well as thin scratches.
Keywords: Dirichlet boundary conditions; multimedia restoration; temporal coherency;
texture filling; structure preservation.
Reference to this paper should be made as follows: Grover, S., Mittal, A., Gupta, S., Sarje, A.K.
and Kaushik, N. (2008) ‘A robust framework for automated digital video inpainting’,
Int. J. Signal and Imaging Systems Engineering, Vol. 1, Nos. 3/4, pp.185–196.
Biographical notes: Suneet Grover received his BTech Degree in Computer Science
Engineering from YMCA Instt. of Engg., Faridabad (Haryana, India) in the year 2003. He did his
Master’s Degree in Information Technology at Indian Institute of Technology Roorkee, Roorkee,
India. His research interests are image processing, video tracking and A.I.
Ankush Mittal received the BTech (Computer Science and Engineering) and MS by Research
(Computer Science and Engineering) from Indian Institute of Technology, Delhi, in 1996
and 1998, respectively. He obtained his PhD in Electrical and Computer Engineering from
National University of Singapore. From March 2001 for around two years, he was a faculty
member in the Department of Computer Science, National University of Singapore. At present,
he serves as Associate Professor in IIT Roorkee, India. His research interests include machine
learning, image processing, bioinformatics and e-learning. He has published more than
150 research papers in these areas.
Sumit Gupta received the BTech (Electrical Engineering) from Indian Institute of Technology,
Delhi, in 1996. He obtained his PhD in Electrical and Computer Engineering from National
University of Singapore. He is faculty and head of the Department of Computer Science and
Engineering at MVGR College of Engineering, Vizianagaram, AP, India. His research interests
include 3-D modelling, image processing and computer vision.