Optimal input sizes for neural network de-interlacing

Hyunsoo Choi; Guiwon Seo; Chulhee Lee

doi:10.1117/12.810569

Optimal input sizes for neural network de-interlacing

Hyunsoo Choi, Guiwon Seo, Chulhee Lee

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference 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 language	English
Title of host publication	Proceedings of SPIE-IS and T Electronic Imaging - Image Processing
Subtitle of host publication	Algorithms and Systems VII
DOIs	https://doi.org/10.1117/12.810569
Publication status	Published - 2009
Event	Image Processing: Algorithms and Systems VII - San Jose, CA, United States Duration: 2009 Jan 19 → 2009 Jan 22

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	7245
ISSN (Print)	0277-786X

Other

Other	Image Processing: Algorithms and Systems VII
Country/Territory	United States
City	San Jose, CA
Period	09/1/19 → 09/1/22

All Science Journal Classification (ASJC) codes

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

Access to Document

10.1117/12.810569

Cite this

@inproceedings{c486872f021f4dcca0dc3d3db690fae3,

title = "Optimal input sizes for neural network de-interlacing",

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.",

author = "Hyunsoo Choi and Guiwon Seo and Chulhee Lee",

year = "2009",

doi = "10.1117/12.810569",

language = "English",

isbn = "9780819474957",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

booktitle = "Proceedings of SPIE-IS and T Electronic Imaging - Image Processing",

note = "Image Processing: Algorithms and Systems VII ; Conference date: 19-01-2009 Through 22-01-2009",

}

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, Image Processing: Algorithms and Systems VII, San Jose, CA, United States, 09/1/19. https://doi.org/10.1117/12.810569

Optimal input sizes for neural network de-interlacing. / Choi, Hyunsoo; Seo, Guiwon; Lee, Chulhee.

Proceedings of SPIE-IS and T Electronic Imaging - Image Processing: Algorithms and Systems VII. 2009. 72451A (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7245).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Optimal input sizes for neural network de-interlacing

AU - Choi, Hyunsoo

AU - Seo, Guiwon

AU - Lee, Chulhee

PY - 2009

Y1 - 2009

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=66749159588&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=66749159588&partnerID=8YFLogxK

U2 - 10.1117/12.810569

DO - 10.1117/12.810569

M3 - Conference contribution

AN - SCOPUS:66749159588

SN - 9780819474957

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Proceedings of SPIE-IS and T Electronic Imaging - Image Processing

T2 - Image Processing: Algorithms and Systems VII

Y2 - 19 January 2009 through 22 January 2009

ER -

Optimal input sizes for neural network de-interlacing

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this