Optimal input sizes for neural network de-interlacing

Hyunsoo Choi, Guiwon Seo, Chulhee Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging - Image Processing
Subtitle of host publicationAlgorithms and Systems VII
DOIs
Publication statusPublished - 2009 Jun 15
EventImage Processing: Algorithms and Systems VII - San Jose, CA, United States
Duration: 2009 Jan 192009 Jan 22

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume7245
ISSN (Print)0277-786X

Other

OtherImage Processing: Algorithms and Systems VII
CountryUnited States
CitySan Jose, CA
Period09/1/1909/1/22

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Optimal input sizes for neural network de-interlacing'. Together they form a unique fingerprint.

  • Cite this

    Choi, H., Seo, G., & Lee, C. (2009). Optimal input sizes for neural network de-interlacing. In Proceedings of SPIE-IS and T Electronic Imaging - Image Processing: Algorithms and Systems VII [72451A] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7245). https://doi.org/10.1117/12.810569