Multiscale Spectral–Spatial Fusion for Controlled-Mixture Food Foreign-Object Localization with Conditional Stability Bounds
Algorithms · 16.11.2026 · 19 (11) · 1006
DOI: 10.3390/a19111006 ↗Kurz gefasst
Fachartikel in der Zeitschrift Algorithms, online erschienen am 16.11.2026. Verfasst von Yuheng Wan und 2 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Localizing small foreign objects in hyperspectral food images requires distinguishing materials while preserving spatial detail. This study presents a multiscale spectral–spatial fusion network with wavelength-aware branches and adaptive fusion weights that incorporate branch sensitivity bounds. A detection-margin analysis accounts for changes in both branch features and fusion weights. The bound uses centered feature disagreement and a finite-radius interaction term to give a sufficient condition for pixel-label stability under bounded perturbations of calibrated reflectance. A predicted foreground component is preserved if the condition holds for its pixels and those of its external background ring. We evaluate localization and prediction stability on controlled mixtures of public fruit recordings and material-library spectra, with prescribed masks, fixed geometry, and bounded reflectance errors.
Zitieren
APA
Wan, Y., Liu, M., & Wang, B. (2026). Multiscale Spectral–Spatial Fusion for Controlled-Mixture Food Foreign-Object Localization with Conditional Stability Bounds. Algorithms, 19(11), 1006. https://doi.org/10.3390/a19111006
Vancouver
Wan Y, Liu M, Wang B. Multiscale Spectral–Spatial Fusion for Controlled-Mixture Food Foreign-Object Localization with Conditional Stability Bounds. Algorithms. 2026;19(11):1006. doi:10.3390/a19111006
BibTeX
@article{Wan2026,
author = {Wan, Yuheng and Liu, Mingyang and Wang, Baoping},
title = {Multiscale Spectral–Spatial Fusion for Controlled-Mixture Food Foreign-Object Localization with Conditional Stability Bounds},
journal = {Algorithms},
year = {2026},
volume = {19},
number = {11},
pages = {1006},
doi = {10.3390/a19111006}
}
EUVIMED