Neural plant inverse control approach to color error reduction for scanner and printer

Gao Wei Chang, Po Rong Chang

研究成果: 書貢獻/報告類型會議貢獻

摘要

The process of eliminating the color errors froni the gamut mismatch, resolution conversion, quantization and nonlinearity between scanner and printer is usually recognized as an essential issue of color reproduction. This paper presents a new formulation based on the inverse plant control for the color error reduction process. In our formulation, the printer input and scanner output correspond to the input and output of a system plant respectively. Obviously, if the printer input equals the scanner output, then there are no color errors involved in the entire system. In other words, the plant becomes an identity system. To achieve this goal, a plant inverse should be identified and added to the original system. Since the system of a combination of both scanner and printer is highly nonlinear, a multilayer back-propagation neural networks, which have the capability to learn arbitrary nonlinearity, are applied to identify the plant inverse. Finally, a number of test samples are conducted to verify the effectiveness of the proposed method.

原文英語
主出版物標題1993 IEEE International Conference on Neural Networks, ICNN 1993
發行者Institute of Electrical and Electronics Engineers Inc.
頁面1979-1983
頁數5
1993-January
ISBN(電子)0780309995
DOIs
出版狀態已發佈 - 1993 一月 1
事件IEEE International Conference on Neural Networks, ICNN 1993 - San Francisco, 美国
持續時間: 1993 三月 281993 四月 1

其他

其他IEEE International Conference on Neural Networks, ICNN 1993
國家美国
城市San Francisco
期間93/3/2893/4/1

指紋

Color
Backpropagation
Multilayers
Neural networks

ASJC Scopus subject areas

  • Software

引用此文

Chang, G. W., & Chang, P. R. (1993). Neural plant inverse control approach to color error reduction for scanner and printer. 於 1993 IEEE International Conference on Neural Networks, ICNN 1993 (卷 1993-January, 頁 1979-1983). [298860] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICNN.1993.298860

Neural plant inverse control approach to color error reduction for scanner and printer. / Chang, Gao Wei; Chang, Po Rong.

1993 IEEE International Conference on Neural Networks, ICNN 1993. 卷 1993-January Institute of Electrical and Electronics Engineers Inc., 1993. p. 1979-1983 298860.

研究成果: 書貢獻/報告類型會議貢獻

Chang, GW & Chang, PR 1993, Neural plant inverse control approach to color error reduction for scanner and printer. 於 1993 IEEE International Conference on Neural Networks, ICNN 1993. 卷 1993-January, 298860, Institute of Electrical and Electronics Engineers Inc., 頁 1979-1983, IEEE International Conference on Neural Networks, ICNN 1993, San Francisco, 美国, 93/3/28. https://doi.org/10.1109/ICNN.1993.298860
Chang GW, Chang PR. Neural plant inverse control approach to color error reduction for scanner and printer. 於 1993 IEEE International Conference on Neural Networks, ICNN 1993. 卷 1993-January. Institute of Electrical and Electronics Engineers Inc. 1993. p. 1979-1983. 298860 https://doi.org/10.1109/ICNN.1993.298860
Chang, Gao Wei ; Chang, Po Rong. / Neural plant inverse control approach to color error reduction for scanner and printer. 1993 IEEE International Conference on Neural Networks, ICNN 1993. 卷 1993-January Institute of Electrical and Electronics Engineers Inc., 1993. 頁 1979-1983
@inproceedings{b96e0ed18e1e473fafdfabdb0afbe2ec,
title = "Neural plant inverse control approach to color error reduction for scanner and printer",
abstract = "The process of eliminating the color errors froni the gamut mismatch, resolution conversion, quantization and nonlinearity between scanner and printer is usually recognized as an essential issue of color reproduction. This paper presents a new formulation based on the inverse plant control for the color error reduction process. In our formulation, the printer input and scanner output correspond to the input and output of a system plant respectively. Obviously, if the printer input equals the scanner output, then there are no color errors involved in the entire system. In other words, the plant becomes an identity system. To achieve this goal, a plant inverse should be identified and added to the original system. Since the system of a combination of both scanner and printer is highly nonlinear, a multilayer back-propagation neural networks, which have the capability to learn arbitrary nonlinearity, are applied to identify the plant inverse. Finally, a number of test samples are conducted to verify the effectiveness of the proposed method.",
author = "Chang, {Gao Wei} and Chang, {Po Rong}",
year = "1993",
month = "1",
day = "1",
doi = "10.1109/ICNN.1993.298860",
language = "English",
volume = "1993-January",
pages = "1979--1983",
booktitle = "1993 IEEE International Conference on Neural Networks, ICNN 1993",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Neural plant inverse control approach to color error reduction for scanner and printer

AU - Chang, Gao Wei

AU - Chang, Po Rong

PY - 1993/1/1

Y1 - 1993/1/1

N2 - The process of eliminating the color errors froni the gamut mismatch, resolution conversion, quantization and nonlinearity between scanner and printer is usually recognized as an essential issue of color reproduction. This paper presents a new formulation based on the inverse plant control for the color error reduction process. In our formulation, the printer input and scanner output correspond to the input and output of a system plant respectively. Obviously, if the printer input equals the scanner output, then there are no color errors involved in the entire system. In other words, the plant becomes an identity system. To achieve this goal, a plant inverse should be identified and added to the original system. Since the system of a combination of both scanner and printer is highly nonlinear, a multilayer back-propagation neural networks, which have the capability to learn arbitrary nonlinearity, are applied to identify the plant inverse. Finally, a number of test samples are conducted to verify the effectiveness of the proposed method.

AB - The process of eliminating the color errors froni the gamut mismatch, resolution conversion, quantization and nonlinearity between scanner and printer is usually recognized as an essential issue of color reproduction. This paper presents a new formulation based on the inverse plant control for the color error reduction process. In our formulation, the printer input and scanner output correspond to the input and output of a system plant respectively. Obviously, if the printer input equals the scanner output, then there are no color errors involved in the entire system. In other words, the plant becomes an identity system. To achieve this goal, a plant inverse should be identified and added to the original system. Since the system of a combination of both scanner and printer is highly nonlinear, a multilayer back-propagation neural networks, which have the capability to learn arbitrary nonlinearity, are applied to identify the plant inverse. Finally, a number of test samples are conducted to verify the effectiveness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=84943236344&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943236344&partnerID=8YFLogxK

U2 - 10.1109/ICNN.1993.298860

DO - 10.1109/ICNN.1993.298860

M3 - Conference contribution

VL - 1993-January

SP - 1979

EP - 1983

BT - 1993 IEEE International Conference on Neural Networks, ICNN 1993

PB - Institute of Electrical and Electronics Engineers Inc.

ER -