Translator Disclaimer
10 February 2009 Optimal input sizes for neural network de-interlacing
Author Affiliations +
Proceedings Volume 7245, Image Processing: Algorithms and Systems VII; 72451A (2009) https://doi.org/10.1117/12.810569
Event: IS&T/SPIE Electronic Imaging, 2009, San Jose, California, United States
Abstract
Neural network de-interlacing has shown promising results among various de-interlacing methods. In this paper, we investigate the effects of input size for neural networks for various video formats when the neural networks are used for de-interlacing. In particular, we investigate optimal input sizes for CIF, VGA and HD video formats.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hyunsoo Choi, Guiwon Seo, and Chulhee Lee "Optimal input sizes for neural network de-interlacing", Proc. SPIE 7245, Image Processing: Algorithms and Systems VII, 72451A (10 February 2009); https://doi.org/10.1117/12.810569
PROCEEDINGS
8 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Deinterlacing with reduced flickering
Proceedings of SPIE (September 02 2009)
State of the art for large area high resolution gray...
Proceedings of SPIE (August 27 1993)
Deinterlacing in spatial and temporal domain
Proceedings of SPIE (February 02 2006)
Efficient implementation of neural network deinterlacing
Proceedings of SPIE (February 10 2009)
Subjective video quality comparison of HDTV monitors
Proceedings of SPIE (January 19 2009)

Back to Top