산업경영시스템학회지 (Journal of Korean Society of Industrial and Systems Engineering)

  • 제45권2호
  • /
  • Pages.48-55
  • /
  • 2022
  • /
  • 2005-0461(pISSN)
  • /
  • 2287-7975(eISSN)
한국산업경영시스템학회 (Society of Korea Industrial and System Engineering)
권호 표지
DOI QR코드

DOI QR Code

딥러닝 알고리즘을 이용한 인쇄된 별색 잉크의 색상 예측 연구

A Study on A Deep Learning Algorithm to Predict Printed Spot Colors

  • 전수현 (한국생산기술연구원 디지털헬스케어연구부문) ;
  • 박재상 (삼성전자) ;
  • 태현철 (한국생산기술연구원 디지털헬스케어연구부문)
  • Jun, Su Hyeon (Department of Digital Healthcare Research Korea Institute of Industrial Technology) ;
  • Park, Jae Sang (Samsung Electronics) ;
  • Tae, Hyun Chul (Department of Digital Healthcare Research Korea Institute of Industrial Technology)
  • 투고 : 2022.05.10
  • 심사 : 2022.06.27
  • 발행 : 2022.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

The color image of the brand comes first and is an important visual element that leads consumers to the consumption of the product. To express more effectively what the brand wants to convey through design, the printing market is striving to print accurate colors that match the intention. In 'offset printing' mainly used in printing, colors are often printed in CMYK (Cyan, Magenta, Yellow, Key) colors. However, it is possible to print more accurate colors by making ink of the desired color instead of dotting CMYK colors. The resulting ink is called 'spot color' ink. Spot color ink is manufactured by repeating the process of mixing the existing inks. In this repetition of trial and error, the manufacturing cost of ink increases, resulting in economic loss, and environmental pollution is caused by wasted inks. In this study, a deep learning algorithm to predict printed spot colors was designed to solve this problem. The algorithm uses a single DNN (Deep Neural Network) model to predict printed spot colors based on the information of the paper and the proportions of inks to mix. More than 8,000 spot color ink data were used for learning, and all color was quantified by dividing the visible light wavelength range into 31 sections and the reflectance for each section. The proposed algorithm predicted more than 80% of spot color inks as very similar colors. The average value of the calculated difference between the actual color and the predicted color through 'Delta E' provided by CIE is 5.29. It is known that when Delta E is less than 10, it is difficult to distinguish the difference in printed color with the naked eye. The algorithm of this study has a more accurate prediction ability than previous studies, and it can be added flexibly even when new inks are added. This can be usefully used in real industrial sites, and it will reduce the attempts of the operator by checking the color of ink in a virtual environment. This will reduce the manufacturing cost of spot color inks and lead to improved working conditions for workers. In addition, it is expected to contribute to solving the environmental pollution problem by reducing unnecessarily wasted ink.

키워드

과제정보

This research was a part of the project titled 'forest science-technology R&D program (2021383A00-2223-0101)', funded by the Korea Forestry Promotion Institute (Korea National Arboretum), Korea.

참고문헌

  1. A Guide to Understanding Color, Retrieved from X-Rite, 2016.
  2. Choe, H.-Y. and Min, Y-H., Introduction to Deep Learning and its main issues, Korea Information Processing Society Review, 2015, Vol. 22, No. 1, pp. 7-21.
  3. Choi, S.-K., Hwang, S.Y., and Kim, W.-J., A Study on the Influence of Brand Identity Color on Consumers' Psychology: Focusing on Brand Coffee Shops, Such as Starbucks, Coffee Bean, Pascucci, and Twosome Place, Journal of Korea Society of Color Studies, 2008, Vol. 22, No. 3, pp. 25-33.
  4. Gooran, S. and Namedanian, M., A New Approach to Calculate Colour Values of Halftone Prints, IARIGAI, 2009.
  5. Hyun, Y.J., Park, J.-S., and Tae, H.-C., Prediction of Color Reproduction using the Scattering and Absorption Coefficients Derived from the Kubelka-Munk Model in Package Printing, Korea Institute of Industrial Technology, 2021, Vol. 27, No. 3, pp. 203-210.
  6. Kim, S., Chung, W., and Shin, S., Acoustic Full-waveform Inversion using Adam Optimizer, Geophysics and Geophysical Exploration, 2019, Vol. 22, No. 4, pp. 202-209. https://doi.org/10.7582/GGE.2019.22.4.202
  7. Kim, Y.S., Uhm, H.S., and Tae, H.C., Deep Neural Network Modeling for the Prediction of Reflexibility from Printed Outputs in the Spot Color Printing System: Focusing on the Aggregating and Processing of Dataset from the Real-world Printing System, Journal of Korea Society of Color Studies, 2022, Vol. 36, No. 1, pp. 5-12.
  8. Kingma, D.P. and Ba, J., Adam: A method for stochastic optimization, International Conference on Learning Representations (ICLR), 2015.
  9. Machizaud, J. and Hebert, M., Spectral Reflectance and Transmittance Prediction Model for Stacked Transparency and Paper Both Printed with Halftone Colors, JOSA A, 2012, Vol. 29, No. 8, pp. 1537-1548. https://doi.org/10.1364/JOSAA.29.001537
  10. Park, C. and Choi, K., Employment Effect of Advanced Printing Industry, Ministry of Employment and Labor, Korea Labor Institute, 2020.
  11. Precise Color Communication, Retrieved from Konica Minolta.
  12. Rhie, J., Research about the Influence of Color Communication on Brand Images - based on Industrial Logos, The Journal of the Korea Contents Association, 2012, Vol. 12, No. 5, pp. 154-162. https://doi.org/10.5392/JKCA.2012.12.05.154
  13. Rousselle, F., Hebert, M., and Hersch, R., Predicting the Reflectance of Paper Dyed with Ink Mixtures by Describing Light Scattering as a Function of Ink Absorbance, Journal of Imaging Science and Technology, 2010, Vol. 54, No. 5.
  14. Seo, J. and Cho, Y., Comparison of Deep Learning Loss Function Performance for Medical Video Biomarker Extraction, Korean Institute of Information and Communication Sciences Conference, 2021, Vol. 25, No. 1, pp. 72-74.