VIS–NIR–SWIR Hyperspectral Imaging and Advanced Machine and Deep Learning Algorithms for a Controlled Benchmark of Bean Seed Identification and Classification
Plants · 18.03.2026 · 15 (6) · 933
DOI: 10.3390/plants15060933 ↗Kurz gefasst
Fachartikel in der Zeitschrift Plants, online erschienen am 18.03.2026. Verfasst von Renan Falcioni und 6 weiteren Autor:innen. Beteiligte Einrichtung: Graduate Program in Agronomy, State University of Maringá, Av. Colombo 5790, Maringá 87020-900, Paraná, Brazil. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coordenação de Aperfeicoamento de Pessoal de Nível Superior, National Council for Scientific and Technological Development, Fundação Araucária.
Abstract (Originalsprache)
Reliable seed accession identification underpins germplasm conservation, traceability and breeding; however, conventional assays remain destructive, labour-intensive and difficult to scale. Here, visible–near-infrared–shortwave infrared (VIS–NIR–SWIR) hyperspectral imaging (HSI; 449.54–2399.17 nm; 563 bands) was used to classify 32 grain–legume accessions (n = 3200 seeds; 100 seeds per accession), comprising 30 common bean (Phaseolus vulgaris L.) landraces plus two outgroup legumes (Vigna angularis (Willd.) Ohwi & Ohashi and Cajanus cajan (L.) Huth). Each seed was represented by one ROI-averaged spectrum obtained from mean representative pixels within a standardised 10 × 10 pixel window at the centre of each seed. A fixed stratified 70:30 seed-level training:test partition was used, with 70 seeds per accession (n = 2240) reserved for fully independent training and 30 seeds per accession (n = 960) reserved as a fully independent test set. Principal component analysis (PCA) captured 97.42% of the spectral variance in the first three components (PC1 = 63.34%, PC2 = 23.78%, and PC3 = 10.31%). One-versus-rest wavelength association mapping revealed a maximum R2 of 0.775 at 461.37 nm, and ReliefF concentrated the strongest reduced-band signal within 449.54–456.30 nm and 577.02–597.54 nm. In the original ReliefF-selected 16-band benchmark, the subspace discriminant reached 68.25% macro-F1 and 68.54% balanced accuracy; after edge-band trimming, the alternative 16-band configuration decreased to 60.67% and 60.94%, respectively. With respect to the full-spectrum sensitivity benchmark, linear discriminant analysis achieved 96.35% balanced accuracy, followed by linear SVM (94.17%). Deep learning trained directly on the full 563-band spectra reached 84.90% test accuracy, 84.47% macro-F1, 86.27% precision and 84.90% recall, with MLP_Wide outperforming the convolutional, recurrent and attention-based alternatives. Overall, under controlled laboratory conditions, this benchmark shows that accession discrimination is driven mainly by visible-domain contrasts in the most compact representations, whereas the full spectral context remains important for the most confusable accessions and for cautious future sensor design. The reduced-band findings should therefore be interpreted as exploratory guidance for sensor design rather than as a validated deployment-ready specification.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Graduate Program in Agronomy, State University of Maringá, Av. Colombo 5790, Maringá 87020-900, Paraná, Brazil.
- Department of Soil Science, Luiz de Queiroz College of Agriculture, University of São Paulo, Av. Pádua Dias 11, Piracicaba 13418-260, São Paulo, Brazil.
ORCID-Profile: Renan Falcioni, Nicole Ghinzelli Vedana, Marcelo Luiz Chicati, José Alexandre M Demattê, Marcos Rafael Nanni
Förderung
- Coordenação de Aperfeicoamento de Pessoal de Nível Superior
- National Council for Scientific and Technological Development
- Fundação Araucária
- Financiadora de Estudos e Projetos
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
- National Council for Scientific and Technological Development: Programa de Apoio à Fixação de Jovens Doutores no Brasil
Zitieren
APA
Falcioni, R., Vedana, N. G., Oliveira, C. A., Gonçalves, J. V. F., Chicati, M. L., Demattê, J. A. M., & Nanni, M. R. (2026). VIS–NIR–SWIR Hyperspectral Imaging and Advanced Machine and Deep Learning Algorithms for a Controlled Benchmark of Bean Seed Identification and Classification. Plants, 15(6), 933. https://doi.org/10.3390/plants15060933
Vancouver
Falcioni R, Vedana NG, Oliveira CA, Gonçalves JVF, Chicati ML, Demattê JAM, et al. VIS–NIR–SWIR Hyperspectral Imaging and Advanced Machine and Deep Learning Algorithms for a Controlled Benchmark of Bean Seed Identification and Classification. Plants. 2026;15(6):933. doi:10.3390/plants15060933
BibTeX
@article{Falcioni2026,
author = {Falcioni, Renan and Vedana, Nicole Ghinzelli and Oliveira, Caio Almeida de and Gonçalves, João Vitor Ferreira and Chicati, Marcelo Luiz and Demattê, José Alexandre M and Nanni, Marcos Rafael},
title = {VIS–NIR–SWIR Hyperspectral Imaging and Advanced Machine and Deep Learning Algorithms for a Controlled Benchmark of Bean Seed Identification and Classification},
journal = {Plants},
year = {2026},
volume = {15},
number = {6},
pages = {933},
doi = {10.3390/plants15060933}
}
EUVIMED