Chromaticity Based Local Linear Regression for Color Distortion Estimation of Optical See-Through Displays

Kang Kyu Lee, Jae Woo Kim, Je Ho Ryu, Jong-Ok Kim

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

3 Citations (Scopus)

Abstract

Optical See-Through displays (OST Displays) require the appearance of the virtual content to closely resemble that of the real world. However, current OST displays typically show color distortion due to hardware limitations. To overcome this problem, we propose a chromaticity based local linear regression model for color distortion estimation of OST displays. From our initial experiments, it was observed that local samples with similar chromaticity can be modeled more linearly rather than simple nearest neighbors in a color space. We argue that the accuracy of local linear regression can be further improved by placing emphasis on similarity of chromaticity. Experimental results showed that the proposed chromaticity based color correction achieves higher accuracy compared to the nearest neighbor method, for any training set size or neighborhood size as well as global regression. It confirms that chromaticity based nearest neighbors can be modeled more linearly together than simple nearest neighbors in a color space.

Original languageEnglish
Title of host publicationAdjunct Proceedings of the 2016 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages151-153
Number of pages3
ISBN (Electronic)9781509037407
DOIs
Publication statusPublished - 2017 Jan 30
Event15th Adjunct IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2016 - Merida, Yucatan, Mexico
Duration: 2016 Sep 182016 Sep 23

Other

Other15th Adjunct IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2016
CountryMexico
CityMerida, Yucatan
Period16/9/1816/9/23

Fingerprint

Linear regression
Display devices
Color
Hardware
Experiments

Keywords

  • augmented reality
  • color correction
  • color distortion model
  • local linear regression
  • OST Display

ASJC Scopus subject areas

  • Computer Science Applications
  • Human-Computer Interaction
  • Media Technology
  • Computer Graphics and Computer-Aided Design

Cite this

Lee, K. K., Kim, J. W., Ryu, J. H., & Kim, J-O. (2017). Chromaticity Based Local Linear Regression for Color Distortion Estimation of Optical See-Through Displays. In Adjunct Proceedings of the 2016 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2016 (pp. 151-153). [7836485] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISMAR-Adjunct.2016.0064

Chromaticity Based Local Linear Regression for Color Distortion Estimation of Optical See-Through Displays. / Lee, Kang Kyu; Kim, Jae Woo; Ryu, Je Ho; Kim, Jong-Ok.

Adjunct Proceedings of the 2016 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 151-153 7836485.

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

Lee, KK, Kim, JW, Ryu, JH & Kim, J-O 2017, Chromaticity Based Local Linear Regression for Color Distortion Estimation of Optical See-Through Displays. in Adjunct Proceedings of the 2016 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2016., 7836485, Institute of Electrical and Electronics Engineers Inc., pp. 151-153, 15th Adjunct IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2016, Merida, Yucatan, Mexico, 16/9/18. https://doi.org/10.1109/ISMAR-Adjunct.2016.0064
Lee KK, Kim JW, Ryu JH, Kim J-O. Chromaticity Based Local Linear Regression for Color Distortion Estimation of Optical See-Through Displays. In Adjunct Proceedings of the 2016 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 151-153. 7836485 https://doi.org/10.1109/ISMAR-Adjunct.2016.0064
Lee, Kang Kyu ; Kim, Jae Woo ; Ryu, Je Ho ; Kim, Jong-Ok. / Chromaticity Based Local Linear Regression for Color Distortion Estimation of Optical See-Through Displays. Adjunct Proceedings of the 2016 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 151-153
@inproceedings{8b079f5b052f4a34b64e86d9101f9d85,
title = "Chromaticity Based Local Linear Regression for Color Distortion Estimation of Optical See-Through Displays",
abstract = "Optical See-Through displays (OST Displays) require the appearance of the virtual content to closely resemble that of the real world. However, current OST displays typically show color distortion due to hardware limitations. To overcome this problem, we propose a chromaticity based local linear regression model for color distortion estimation of OST displays. From our initial experiments, it was observed that local samples with similar chromaticity can be modeled more linearly rather than simple nearest neighbors in a color space. We argue that the accuracy of local linear regression can be further improved by placing emphasis on similarity of chromaticity. Experimental results showed that the proposed chromaticity based color correction achieves higher accuracy compared to the nearest neighbor method, for any training set size or neighborhood size as well as global regression. It confirms that chromaticity based nearest neighbors can be modeled more linearly together than simple nearest neighbors in a color space.",
keywords = "augmented reality, color correction, color distortion model, local linear regression, OST Display",
author = "Lee, {Kang Kyu} and Kim, {Jae Woo} and Ryu, {Je Ho} and Jong-Ok Kim",
year = "2017",
month = "1",
day = "30",
doi = "10.1109/ISMAR-Adjunct.2016.0064",
language = "English",
pages = "151--153",
booktitle = "Adjunct Proceedings of the 2016 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Chromaticity Based Local Linear Regression for Color Distortion Estimation of Optical See-Through Displays

AU - Lee, Kang Kyu

AU - Kim, Jae Woo

AU - Ryu, Je Ho

AU - Kim, Jong-Ok

PY - 2017/1/30

Y1 - 2017/1/30

N2 - Optical See-Through displays (OST Displays) require the appearance of the virtual content to closely resemble that of the real world. However, current OST displays typically show color distortion due to hardware limitations. To overcome this problem, we propose a chromaticity based local linear regression model for color distortion estimation of OST displays. From our initial experiments, it was observed that local samples with similar chromaticity can be modeled more linearly rather than simple nearest neighbors in a color space. We argue that the accuracy of local linear regression can be further improved by placing emphasis on similarity of chromaticity. Experimental results showed that the proposed chromaticity based color correction achieves higher accuracy compared to the nearest neighbor method, for any training set size or neighborhood size as well as global regression. It confirms that chromaticity based nearest neighbors can be modeled more linearly together than simple nearest neighbors in a color space.

AB - Optical See-Through displays (OST Displays) require the appearance of the virtual content to closely resemble that of the real world. However, current OST displays typically show color distortion due to hardware limitations. To overcome this problem, we propose a chromaticity based local linear regression model for color distortion estimation of OST displays. From our initial experiments, it was observed that local samples with similar chromaticity can be modeled more linearly rather than simple nearest neighbors in a color space. We argue that the accuracy of local linear regression can be further improved by placing emphasis on similarity of chromaticity. Experimental results showed that the proposed chromaticity based color correction achieves higher accuracy compared to the nearest neighbor method, for any training set size or neighborhood size as well as global regression. It confirms that chromaticity based nearest neighbors can be modeled more linearly together than simple nearest neighbors in a color space.

KW - augmented reality

KW - color correction

KW - color distortion model

KW - local linear regression

KW - OST Display

UR - http://www.scopus.com/inward/record.url?scp=85015253158&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015253158&partnerID=8YFLogxK

U2 - 10.1109/ISMAR-Adjunct.2016.0064

DO - 10.1109/ISMAR-Adjunct.2016.0064

M3 - Conference contribution

AN - SCOPUS:85015253158

SP - 151

EP - 153

BT - Adjunct Proceedings of the 2016 IEEE International Symposium on Mixed and Augmented Reality, ISMAR-Adjunct 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -