EUVIMEDEUVIMED entdecken
Crossref

Spectral reflectance reconstruction via extreme learning machine: Cross‐dataset evaluation and generalisation analysis

Zhitong Xing, Chenfei Han, Rong Li

Coloration Technology · 02.11.2026

DOI: 10.1111/cote.70123 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Coloration Technology, online erschienen am 02.11.2026. Verfasst von Zhitong Xing und 2 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study was designed to reconstruct 31‐band spectral reflectance from CIE XYZ values using an extreme learning machine (ELM), and its within‐dataset and cross‐dataset performance was evaluated. The Sino dataset, containing 10,770 samples, was divided into an independent 20% subset for hyperparameter selection and an 80% subset for formal evaluation. By means of a full grid search over hidden‐layer size, activation function and regularisation coefficient, an ELM with 350 hidden neurons, radbas activation and a regularisation coefficient of 0 was selected. On the independent evaluation subset, a mean ΔE 00 of 0.082 ± 0.002, an RMSE of 0.005 ± 0.000 and a spectral angle of 0.020 ± 0.001 rad were achieved by the optimised ELM. Among the seven reconstruction methods, RBF achieved the lowest reconstruction errors, whereas ELM required less computational time than RBF and BP while maintaining relatively low reconstruction errors. Cross‐dataset performance differed markedly with the training‐test direction. Sino‐trained models produced mean ΔE 00 values of 7.936 ± 0.361 on Munsell and 6.829 ± 0.348 on Coloro, whereas Munsell‐ and Coloro‐trained models transferred to Sino with substantially lower colour‐difference errors. For the Sino‐trained models, large reconstruction errors occurred over broad wavelength ranges rather than being concentrated in a single spectral region. Using XYZ information under both D65 and illuminant A reduced the within‐dataset reconstruction errors, but similarly low errors were not obtained for all cross‐dataset directions. The MI ab results showed poorer cross‐illuminant consistency for the transfer directions with larger spectral reconstruction errors.

Zitieren

APA

Xing, Z., Han, C., & Li, R. (2026). Spectral reflectance reconstruction via extreme learning machine: Cross‐dataset evaluation and generalisation analysis. Coloration Technology. https://doi.org/10.1111/cote.70123

Vancouver

Xing Z, Han C, Li R. Spectral reflectance reconstruction via extreme learning machine: Cross‐dataset evaluation and generalisation analysis. Coloration Technology. 2026. doi:10.1111/cote.70123

BibTeX
@article{Xing2026,
  author = {Xing, Zhitong and Han, Chenfei and Li, Rong},
  title = {Spectral reflectance reconstruction via extreme learning machine: Cross‐dataset evaluation and generalisation analysis},
  journal = {Coloration Technology},
  year = {2026},
  doi = {10.1111/cote.70123}
}
Kostenlos starten →