Journal of Multimedia Information System

Korea Multimedia Society (한국멀티미디어학회)
권호 표지
DOI QR코드

DOI QR Code

A Simple Eye Gaze Correction Scheme Using 3D Affine Transformation and Image In-painting Technique

  • Received : 2018.03.09
  • Accepted : 2018.04.26
  • Published : 2018.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Owing to high speed internet technologies, video conferencing systems are exploited in our home as well as work places using a laptop or a webcam. Although eye contact in the video conferencing system is significant, most systems do not support good eye contact due to improper locations of cameras. Several ideas have been proposed to solve the eye contact problem; however, some of them require complicated hardware configurations and expensive customized hardwares. In this paper, we propose a simple eye gaze correction method using the three-dimensional (3D) affine transformation. We also apply an image in-painting method to fill empty holes that are caused by round-off errors from the coordinate transformation. From experiments, we obtained visually improved results.

Keywords

References

  1. C. Fehn, "Depth-image-based rendering (DIBR), compression and transmission for a new approach on 3DTV," Proceedings of the SPIE, Conference on Stereoscopic Displays and Virtual Reality Systems XI, vol. 5291, pp.93-104, May 2004.
  2. S.B. Lee and Y.S. Ho, "Generation of eye contact image using depth camera for realistic telepresence," Proceedings of Asia-Pacific Signal and Information Processing Association (APSIPA), OS.30-SPS.4.1, pp. 1-4, Nov.
  3. Y.S. Ho and W.S Jang, "Gaze correction using 3D video processing for videoconferencing," IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP), 3DV-O.3, pp. 496- 499, July 2015.
  4. K.H. Tan, I.N. Robinson, B. Culbertson, and J. Apostolopoulos, "ConnectBoard: Enabling genuine eye contact and accurate gaze in remote collaboration," IEEE Transactions on Multimedia, Vol. 13, No. 3, pp. 466-473, March 2011. https://doi.org/10.1109/TMM.2011.2130516
  5. J. Sun, N.N. Zheng, and H.Y. Shum, "Stereo matching using belief propagation," IEEE Transactions on pattern analysis and machine intelligence, Vol. 25, No. 7, pp. 787-800, June 2003. https://doi.org/10.1109/TPAMI.2003.1206509
  6. C. Kuster, T. Popa, J.C. Bazin, C. Gotsman, and M. Gross, "Gaze correction for home video conferencing," ACM Transaction on Graphics, Vol. 31, No. 6, pp. 1-6, Nov. 2012.
  7. K. Wu, E. Otoo, and K. Suzuki, "Two strategies to speed up connected component labeling algorithms," Technical Report LBNL-59102, Nov. 2005.
  8. A. Telea, "An image inpainting technique based on the fast marching method," Journal of Graphics Tools, Vol. 9, No.1, pp. 25-36, Jan. 2004.