The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
As cores dos objetos em imagens naturais são afetadas pela cor da iluminação, e estimar com precisão a cor de um iluminante é indispensável na análise de cenas iluminadas por iluminações coloridas. Ambientes de iluminação recentes aumentam o colorido devido à disseminação de iluminações de diodo emissor de luz (LED), cujas cores são controladas de forma flexível em um espectro visível completo. No entanto, as estimativas de cores existentes concentram-se principalmente no iluminante único das faixas de cores normais. A estimativa de múltiplos iluminantes com configurações de cores incomuns, como azul ou vermelho de alta croma, ainda não foi estudada. Portanto, novas estimativas de cores devem ser desenvolvidas para múltiplos iluminantes de diversas cores. Neste artigo, propomos uma estimativa de cores para iluminações LED utilizando recursos Color Line, que considera a distribuição de cores como uma linha reta em uma área local. Esta estimativa local é adequada para estimar várias cores de múltiplos iluminantes. Os recursos são amostrados em muitas regiões pequenas de uma imagem e agregados para estimar algumas cores globais usando aprendizado supervisionado com uma rede neural convolucional. Demonstramos a maior precisão do nosso método em relação aos existentes para ambientes de iluminação coloridos, produzindo o conjunto de dados de imagens iluminado por múltiplas iluminações LED em uma faixa colorida.
Quan XIU HO
Toyohashi University of Technology
Takao JINNO
Osaka Institute of Technology
Yusuke UCHIMI
Toyohashi University of Technology
Shigeru KURIYAMA
Toyohashi University of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Quan XIU HO, Takao JINNO, Yusuke UCHIMI, Shigeru KURIYAMA, "Estimation of Multiple Illuminant Colors Using Color Line Features" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 10, pp. 1751-1758, October 2022, doi: 10.1587/transinf.2022EDP7010.
Abstract: The colors of objects in natural images are affected by the color of lighting, and accurately estimating an illuminant's color is indispensable in analyzing scenes lit by colored lightings. Recent lighting environments enhance colorfulness due to the spread of light-emitting diode (LED) lightings whose colors are flexibly controlled in a full visible spectrum. However, existing color estimations mainly focus on the single illuminant of normal color ranges. The estimation of multiple illuminants of unusual color settings, such as blue or red of high chroma, has not been studied yet. Therefore, new color estimations should be developed for multiple illuminants of various colors. In this article, we propose a color estimation for LED lightings using Color Line features, which regards the color distribution as a straight line in a local area. This local estimate is suitable for estimating various colors of multiple illuminants. The features are sampled at many small regions in an image and aggregated to estimate a few global colors using supervised learning with a convolutional neural network. We demonstrate the higher accuracy of our method over existing ones for such colorful lighting environments by producing the image dataset lit by multiple LED lightings in a full-color range.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDP7010/_p
Copiar
@ARTICLE{e105-d_10_1751,
author={Quan XIU HO, Takao JINNO, Yusuke UCHIMI, Shigeru KURIYAMA, },
journal={IEICE TRANSACTIONS on Information},
title={Estimation of Multiple Illuminant Colors Using Color Line Features},
year={2022},
volume={E105-D},
number={10},
pages={1751-1758},
abstract={The colors of objects in natural images are affected by the color of lighting, and accurately estimating an illuminant's color is indispensable in analyzing scenes lit by colored lightings. Recent lighting environments enhance colorfulness due to the spread of light-emitting diode (LED) lightings whose colors are flexibly controlled in a full visible spectrum. However, existing color estimations mainly focus on the single illuminant of normal color ranges. The estimation of multiple illuminants of unusual color settings, such as blue or red of high chroma, has not been studied yet. Therefore, new color estimations should be developed for multiple illuminants of various colors. In this article, we propose a color estimation for LED lightings using Color Line features, which regards the color distribution as a straight line in a local area. This local estimate is suitable for estimating various colors of multiple illuminants. The features are sampled at many small regions in an image and aggregated to estimate a few global colors using supervised learning with a convolutional neural network. We demonstrate the higher accuracy of our method over existing ones for such colorful lighting environments by producing the image dataset lit by multiple LED lightings in a full-color range.},
keywords={},
doi={10.1587/transinf.2022EDP7010},
ISSN={1745-1361},
month={October},}
Copiar
TY - JOUR
TI - Estimation of Multiple Illuminant Colors Using Color Line Features
T2 - IEICE TRANSACTIONS on Information
SP - 1751
EP - 1758
AU - Quan XIU HO
AU - Takao JINNO
AU - Yusuke UCHIMI
AU - Shigeru KURIYAMA
PY - 2022
DO - 10.1587/transinf.2022EDP7010
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2022
AB - The colors of objects in natural images are affected by the color of lighting, and accurately estimating an illuminant's color is indispensable in analyzing scenes lit by colored lightings. Recent lighting environments enhance colorfulness due to the spread of light-emitting diode (LED) lightings whose colors are flexibly controlled in a full visible spectrum. However, existing color estimations mainly focus on the single illuminant of normal color ranges. The estimation of multiple illuminants of unusual color settings, such as blue or red of high chroma, has not been studied yet. Therefore, new color estimations should be developed for multiple illuminants of various colors. In this article, we propose a color estimation for LED lightings using Color Line features, which regards the color distribution as a straight line in a local area. This local estimate is suitable for estimating various colors of multiple illuminants. The features are sampled at many small regions in an image and aggregated to estimate a few global colors using supervised learning with a convolutional neural network. We demonstrate the higher accuracy of our method over existing ones for such colorful lighting environments by producing the image dataset lit by multiple LED lightings in a full-color range.
ER -