Please use this identifier to cite or link to this item: http://hdl.handle.net/10995/103326
Title: The forward problem of spectral reflection prediction: Mutual match between framework selection and the training set volume
Authors: Tarasov, D. A.
Milder, O. B.
Issue Date: 2020
Publisher: American Institute of Physics Inc.
Citation: Tarasov D. A. The forward problem of spectral reflection prediction: Mutual match between framework selection and the training set volume / D. A. Tarasov, O. B. Milder. — DOI 10.1063/5.0026740 // AIP Conference Proceedings. — 2020. — Vol. 2293. — 140011.
Abstract: Novel technology of the color reproduction is closely related to a variety of color prediction techniques. Along with the deterministic models, those based on the use of artificial neural networks have recently begun to appear. An important problem in the application of a neural network approach is the choice of the training set and network training algorithms. In our work, we describe the results of a computational experiment where various configurations of the artificial neural networks along the different volumes of training subsamples were simultaneously determined providing a satisfactory accuracy of the spectral reflection prediction. The results show that each subsample might be mapped to a particular network configuration. © 2020 American Institute of Physics Inc.. All rights reserved.
Keywords: ARTIFICIAL NEURAL NETWORKS
COLOR REPRODUCTION
FRAMEWORK
SPECTRAL REFLECTION PREDICTION
TRAINING SET
URI: http://hdl.handle.net/10995/103326
Access: info:eu-repo/semantics/openAccess
SCOPUS ID: 85097997793
PURE ID: 20391620
ded6cb9d-b38a-47c2-9d46-935f6b8f1643
ISSN: 0094243X
ISBN: 9780735440258
DOI: 10.1063/5.0026740
Appears in Collections:Научные публикации, проиндексированные в SCOPUS и WoS CC

Files in This Item:
File Description SizeFormat 
2-s2.0-85097997793.pdf342,39 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.