Study on Printer Characterization Based on BP Neural Network

DOI

10.2991/itms-15.2015.412How to use a DOI?

Keywords

BP neural network; Characterization model; Hue angle range; Color printer

Abstract

There is a very complicated nonlinear relationship between the input digital image pixel value and the printed color chromatic values, which is difficult to be described by traditional linear methods to achieve high accuracy. In the study, a printer characterization model is established based on artificial BP neural network theory and by the hue angle range of the experimental data print classification. Because of the good simulation of nonlinear properties of the BP neural network, the characterization model achieves high accuracy. The mean color error value between the chromatic value to be printed and the chromatic value driven by the image pixel value which is calculated by the characterization model is rather less than that of the minimum range of the human eye can identify. The characterization model could be used in the gamut matching of the printing color management system, when the printer is severed as an output device.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Lei Zhao
PY  - 2015/11
DA  - 2015/11
TI  - Study on Printer Characterization Based on BP Neural Network
BT  - Proceedings of the 2015 International Conference on Industrial Technology and Management Science
PB  - Atlantis Press
SP  - 1693
EP  - 1696
SN  - 2352-538X
UR  - https://doi.org/10.2991/itms-15.2015.412
DO  - 10.2991/itms-15.2015.412
ID  - Zhao2015/11
ER  -