Abstract
Under a video communication environment with single camera, the key problem to interfere user’s natural feeling of conversation is its physical limitation to establish proper eye contact. This problem is caused by difficulty in aligning viewing directions of camera and user. We present a new approach to solve this problem using image-based warping technique. The main idea for our gaze correction is to generate an image captured by a virtual camera placed on the point which the user stares at. Our proposed method has two key components. The first one is to estimate the correction angle from the input images without supervision. The second one is the warping process to gaze-correct the input image. We show experimental results of gaze correction for situations which can occur in typical real communication environment.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
I. Lee and B. Jeon: Three-dimensional Mesh Warping for Natural Eye-to-Eye Contact in Internet Video Communication. Proc. of Visual Communication and Image Processing(VCIP 00), vol.4067, pp. 308–315, 2000.
I. Lee and B. Jeon: Gaze-Correction using Simplified 3D Mesh Warping. Proc. of Visual Communication and Image Processing(VCIP 01), vol.4310, pp. 595–602, 2001.
C. Tomasi and T. kanade: Shape and Motion from Image Stream under orthography: A Factorization Method. Int. Journal of Computer Vision, 9(2):137–154, Nov., 1992.
C. Bregler, A. Hertzmann, and H. Biermann: Recovering Non-Rigid 3D Shape from Image Streams. Proc. of Computer Vision and Pattern Recognition 2000(CVPR2000), vol. 2, pp. 690–696, 2000.
B. K. Horn: Robot Vision. The MIT Press, Cambridge, 1986.
A. M. Tekalp: Digital Video Processing. Prentice Hall, 1995.
W. Press, S. Teukolsky, W. Vetterling, and B. Flannery: Numerical Recipes in C. Cambridge University Press, pp. 59–70, 1996.
V. Blanz and T. Vetter: A Morphable Model for the Synthesis of 3D Faces. Proc. of SIG-GRAPH’99, pp. 187–194, 1999.
G. Wolberg: Digital Image Warping. IEEE Computer Society Press, 1990.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lee, I., Jeon, B. (2001). Enhanced Video Communication Using Gaze Correction with Simplified 3D Warping and Single Camera. In: Tucci, M. (eds) Multimedia Databases and Image Communication. MDIC 2001. Lecture Notes in Computer Science, vol 2184. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44819-5_18
Download citation
DOI: https://doi.org/10.1007/3-540-44819-5_18
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42587-8
Online ISBN: 978-3-540-44819-8
eBook Packages: Springer Book Archive