Neural network deinterlacing using multiple fields and field-MSEs

Hyunsoo Choi, Chulhee Lee

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

8 Citations (Scopus)

Abstract

Generally, deinterlacing algorithms can be either classified as intra methods or inter methods. Intra methods interpolate missing lines by using surrounding pixels in the current field. Inter methods interpolate missing lines by using pixels and the motion information of multiple fields. Neural network deinterlacing that uses multiple fields has been proposed. It provides improved performance compared to existing neural network deinterlacing algorithms that use a single field. However, when adjacent fields are very different, neural network deinterlacing that uses multiple fields may not provide good performance. To address this problem, we propose using field-MSE values as additional inputs. These MSE values can provide helpful information so that the networks can consider field differences in using multiple fields. Experimental results show that the use of the proposed algorithm results in improved performance.

Original languageEnglish
Title of host publicationThe 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings
Pages869-872
Number of pages4
DOIs
Publication statusPublished - 2007 Dec 1
Event2007 International Joint Conference on Neural Networks, IJCNN 2007 - Orlando, FL, United States
Duration: 2007 Aug 122007 Aug 17

Other

Other2007 International Joint Conference on Neural Networks, IJCNN 2007
CountryUnited States
CityOrlando, FL
Period07/8/1207/8/17

Fingerprint

Neural networks
Pixels

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Choi, H., & Lee, C. (2007). Neural network deinterlacing using multiple fields and field-MSEs. In The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings (pp. 869-872). [4371072] https://doi.org/10.1109/IJCNN.2007.4371072
Choi, Hyunsoo ; Lee, Chulhee. / Neural network deinterlacing using multiple fields and field-MSEs. The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings. 2007. pp. 869-872
@inproceedings{eb2d8d115c48413492a1dd6e132e238d,
title = "Neural network deinterlacing using multiple fields and field-MSEs",
abstract = "Generally, deinterlacing algorithms can be either classified as intra methods or inter methods. Intra methods interpolate missing lines by using surrounding pixels in the current field. Inter methods interpolate missing lines by using pixels and the motion information of multiple fields. Neural network deinterlacing that uses multiple fields has been proposed. It provides improved performance compared to existing neural network deinterlacing algorithms that use a single field. However, when adjacent fields are very different, neural network deinterlacing that uses multiple fields may not provide good performance. To address this problem, we propose using field-MSE values as additional inputs. These MSE values can provide helpful information so that the networks can consider field differences in using multiple fields. Experimental results show that the use of the proposed algorithm results in improved performance.",
author = "Hyunsoo Choi and Chulhee Lee",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/IJCNN.2007.4371072",
language = "English",
isbn = "142441380X",
pages = "869--872",
booktitle = "The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings",

}

Choi, H & Lee, C 2007, Neural network deinterlacing using multiple fields and field-MSEs. in The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings., 4371072, pp. 869-872, 2007 International Joint Conference on Neural Networks, IJCNN 2007, Orlando, FL, United States, 07/8/12. https://doi.org/10.1109/IJCNN.2007.4371072

Neural network deinterlacing using multiple fields and field-MSEs. / Choi, Hyunsoo; Lee, Chulhee.

The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings. 2007. p. 869-872 4371072.

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

TY - GEN

T1 - Neural network deinterlacing using multiple fields and field-MSEs

AU - Choi, Hyunsoo

AU - Lee, Chulhee

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Generally, deinterlacing algorithms can be either classified as intra methods or inter methods. Intra methods interpolate missing lines by using surrounding pixels in the current field. Inter methods interpolate missing lines by using pixels and the motion information of multiple fields. Neural network deinterlacing that uses multiple fields has been proposed. It provides improved performance compared to existing neural network deinterlacing algorithms that use a single field. However, when adjacent fields are very different, neural network deinterlacing that uses multiple fields may not provide good performance. To address this problem, we propose using field-MSE values as additional inputs. These MSE values can provide helpful information so that the networks can consider field differences in using multiple fields. Experimental results show that the use of the proposed algorithm results in improved performance.

AB - Generally, deinterlacing algorithms can be either classified as intra methods or inter methods. Intra methods interpolate missing lines by using surrounding pixels in the current field. Inter methods interpolate missing lines by using pixels and the motion information of multiple fields. Neural network deinterlacing that uses multiple fields has been proposed. It provides improved performance compared to existing neural network deinterlacing algorithms that use a single field. However, when adjacent fields are very different, neural network deinterlacing that uses multiple fields may not provide good performance. To address this problem, we propose using field-MSE values as additional inputs. These MSE values can provide helpful information so that the networks can consider field differences in using multiple fields. Experimental results show that the use of the proposed algorithm results in improved performance.

UR - http://www.scopus.com/inward/record.url?scp=51749104432&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51749104432&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2007.4371072

DO - 10.1109/IJCNN.2007.4371072

M3 - Conference contribution

AN - SCOPUS:51749104432

SN - 142441380X

SN - 9781424413805

SP - 869

EP - 872

BT - The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings

ER -

Choi H, Lee C. Neural network deinterlacing using multiple fields and field-MSEs. In The 2007 International Joint Conference on Neural Networks, IJCNN 2007 Conference Proceedings. 2007. p. 869-872. 4371072 https://doi.org/10.1109/IJCNN.2007.4371072