以人工智慧預測彩色隱性螢光墨之色彩

Artificial Intelligence Predicts Color of Invisible Fluorescent Ink

江瑞璋(Raymond Chiang) ； 孫沛立(Pei-Li Sun)

《中華印刷科技年報》 2020 (2020/06) Pp. 73-78

摘要

彩色隱性螢光墨在印製時看不到任何色彩，必須在紫外光下才能顯色，為了避免肉眼傷害及減少接觸紫外光的時間，將以數位取像設備的RGB訊號預測CIE LAB色度值。本研究採用迴歸分析、多元感知器學習法及卷積神經網路等三種方法進行色彩預測，其中以卷積神經網路可以得到最精準的預測值。

關鍵字

人工智慧 ； 隱性螢光墨 ； CIELAB ； 色彩

並列摘要

The color of invisible fluorescent inks do not be seen any color without UV light during printing. In order to avoid naked eye damage and reduce the time of exposure to UV light, the RGB signal of digital imaging equipment will be used to predict the CIE LAB chromaticity. This study uses regression analysis, Multilayer Perceptron learning, and convolutional neural networks for color prediction. Among them, convolutional neural networks can get the most accurate predictions.

並列關鍵字

AI ； Invisible Fluorescent Inks ； CIELAB ； Color

參考文獻

G Cui，a M R Luo， B Rigg， M Butterworth， N Maplesdenc and J Dakind. Grading textile fastness. Part 4: An interlaboratory trial using DigiEye systems. Color. Technol. 2004;120: 231-235.

SHOJI TOMINAGA，KEITA HIRAI， AND TAKAHIKO HORIUCHI， Estimation of bispectral Donaldson matrices of fluorescent objects by using two illuminant projections. JOSA 2015; Vol. 32， No. 6:1068-1078.

Bishop， Christopher. Pattern recognition and machine learning. Berlin: Springer. ISBN 0-387-31073-8. 2006

Po-Tong Wang， Jui Jen Chou， Chiu Wang Tseng. Colorimetric Characterization of Color Image Sensors Based on Convolutional Neural Network Modeling， Sensors and Materials2019;Vol. 31，No. 5:1513-1522

Alex Krizhevsky， Ilya Sutskever， Geoffrey E.Hinton， “ImageNet Classification with Deep Convolution Neural Networks， University of Toronto，2012”