A hybrid spectral prediction model for printed images based on whale-optimized deep neural network

In the process of color reproduction, the accurate prediction of color halftone images’ characteristics and the development of a spectral reflectance prediction model are pivotal for print image device characterization and quality control. Traditional models such as Murray-Davis, Clapper-Yule, Yule-...

Full description

Saved in:
Bibliographic Details
Main Authors: Dongwen Tian, Jinghuan Ge, Na Su
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-12-01
Series:Frontiers in Physics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fphy.2024.1429621/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850250639154610176
author Dongwen Tian
Dongwen Tian
Jinghuan Ge
Na Su
author_facet Dongwen Tian
Dongwen Tian
Jinghuan Ge
Na Su
author_sort Dongwen Tian
collection DOAJ
description In the process of color reproduction, the accurate prediction of color halftone images’ characteristics and the development of a spectral reflectance prediction model are pivotal for print image device characterization and quality control. Traditional models such as Murray-Davis, Clapper-Yule, Yule-Nielsen, and their modifications have been preferred for their high accuracy in color and spectral predictions. However, they overlook the role of black ink in CMYK printing, limiting their effectiveness in predicting the spectral properties of four-color inks and demonstrating notable in-accuracies in light color tones. A hybrid model combining a prior model based on physics with a deep neural network has been proposed. On the input side, the Neugebauer equation and the superposition of 4-color inks are considered, and the 4-color CMYK input is expanded to 16 Neugebauer primary colors. On the output side, the PCA dimensionality reduction algorithm extracts 7 principal components with a contribution of 99.99%. Finally, the Improved Whale Optimization Algorithm (IWOA) is employed to optimize the parameters of the deep neural network (DNN) model. The experimental results show that our model significantly outperforms traditional methods in reducing CIEDE2000 color differences, enabling the early prediction of spectral colors in printed images and improving print image quality. What is more, the proposed model does not need to take into account the effect of dot gain in the printing process.
format Article
id doaj-art-b8d95efed9d240f38efc6bf06b3f2faf
institution OA Journals
issn 2296-424X
language English
publishDate 2024-12-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Physics
spelling doaj-art-b8d95efed9d240f38efc6bf06b3f2faf2025-08-20T01:58:08ZengFrontiers Media S.A.Frontiers in Physics2296-424X2024-12-011210.3389/fphy.2024.14296211429621A hybrid spectral prediction model for printed images based on whale-optimized deep neural networkDongwen Tian0Dongwen Tian1Jinghuan Ge2Na Su3Department of Printing and Packaging Engineering, Shanghai Publishing and Printing College, Shanghai, ChinaSchool of Optical-Electrical and computer Engineering, University of Shanghai for Science and Technology, Shanghai, ChinaDepartment of Printing and Packaging Engineering, Shanghai Publishing and Printing College, Shanghai, ChinaDepartment of Printing and Packaging Engineering, Shanghai Publishing and Printing College, Shanghai, ChinaIn the process of color reproduction, the accurate prediction of color halftone images’ characteristics and the development of a spectral reflectance prediction model are pivotal for print image device characterization and quality control. Traditional models such as Murray-Davis, Clapper-Yule, Yule-Nielsen, and their modifications have been preferred for their high accuracy in color and spectral predictions. However, they overlook the role of black ink in CMYK printing, limiting their effectiveness in predicting the spectral properties of four-color inks and demonstrating notable in-accuracies in light color tones. A hybrid model combining a prior model based on physics with a deep neural network has been proposed. On the input side, the Neugebauer equation and the superposition of 4-color inks are considered, and the 4-color CMYK input is expanded to 16 Neugebauer primary colors. On the output side, the PCA dimensionality reduction algorithm extracts 7 principal components with a contribution of 99.99%. Finally, the Improved Whale Optimization Algorithm (IWOA) is employed to optimize the parameters of the deep neural network (DNN) model. The experimental results show that our model significantly outperforms traditional methods in reducing CIEDE2000 color differences, enabling the early prediction of spectral colors in printed images and improving print image quality. What is more, the proposed model does not need to take into account the effect of dot gain in the printing process.https://www.frontiersin.org/articles/10.3389/fphy.2024.1429621/fullcolor predictionspectral reflectancecolor modeldeep neural networkprinted image
spellingShingle Dongwen Tian
Dongwen Tian
Jinghuan Ge
Na Su
A hybrid spectral prediction model for printed images based on whale-optimized deep neural network
Frontiers in Physics
color prediction
spectral reflectance
color model
deep neural network
printed image
title A hybrid spectral prediction model for printed images based on whale-optimized deep neural network
title_full A hybrid spectral prediction model for printed images based on whale-optimized deep neural network
title_fullStr A hybrid spectral prediction model for printed images based on whale-optimized deep neural network
title_full_unstemmed A hybrid spectral prediction model for printed images based on whale-optimized deep neural network
title_short A hybrid spectral prediction model for printed images based on whale-optimized deep neural network
title_sort hybrid spectral prediction model for printed images based on whale optimized deep neural network
topic color prediction
spectral reflectance
color model
deep neural network
printed image
url https://www.frontiersin.org/articles/10.3389/fphy.2024.1429621/full
work_keys_str_mv AT dongwentian ahybridspectralpredictionmodelforprintedimagesbasedonwhaleoptimizeddeepneuralnetwork
AT dongwentian ahybridspectralpredictionmodelforprintedimagesbasedonwhaleoptimizeddeepneuralnetwork
AT jinghuange ahybridspectralpredictionmodelforprintedimagesbasedonwhaleoptimizeddeepneuralnetwork
AT nasu ahybridspectralpredictionmodelforprintedimagesbasedonwhaleoptimizeddeepneuralnetwork
AT dongwentian hybridspectralpredictionmodelforprintedimagesbasedonwhaleoptimizeddeepneuralnetwork
AT dongwentian hybridspectralpredictionmodelforprintedimagesbasedonwhaleoptimizeddeepneuralnetwork
AT jinghuange hybridspectralpredictionmodelforprintedimagesbasedonwhaleoptimizeddeepneuralnetwork
AT nasu hybridspectralpredictionmodelforprintedimagesbasedonwhaleoptimizeddeepneuralnetwork