EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multispectral Fluorescence Imaging for Fast Identification of Cold Stress in Pepper Plants

Reza Adhitama Putra Hernanda iD, Whanjo Jung, Me-Hea Park, Hoonsoo Lee iD

Sensors · 12.03.2026 · 26 (6) · 1799

DOI: 10.3390/s26061799 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 12.03.2026. Verfasst von Reza Adhitama Putra Hernanda und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biosystems Engineering, College of Agriculture, Life, and Environment Sciences, Chungbuk National University, Cheongju 28644, Republic …. Hauptthemen laut MEDLINE: Capsicum, Optical Imaging, Cold-Shock Response. Die Arbeit nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Rural Development Administration, Cooperative Research Program for Agriculture Science and Technology Development, Rural Development Administration, Republic of Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper investigated the feasibility of snapshot multispectral fluorescence imaging for nondestructive identification of cold stress in pepper plants. Fluorescence spectra were obtained by exciting the plant with a 405 nm ultraviolet LED. The plants were grown under three temperature conditions: 17 °C (control), 10 °C (moderate cold stress), and 5 °C (severe cold stress). Raw fluorescence spectra extracted from the demosaiced snapshot images were used as inputs for a deep-learning pipeline consisting of feature extraction, an encoder–decoder GRU, and a multilayer perceptron (MLP), and the results were compared with conventional machine learning classifiers, including linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and a Gaussian support vector machine (G-SVM). Tukey’s HSD test indicated that the proposed deep-learning model achieved the highest cross-validation accuracy and consistently produced superior classification metrics (accuracy of 85.7%, precision of 85.3%, recall of 85.3%, F1-score of 85.2). The trained model was further applied to hyperspectral cubes to generate classification maps; however, moderate misclassification was observed, consistent with the overall prediction performance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CapsicumOptical ImagingCold-Shock ResponseDiscriminant AnalysisSupport Vector MachineCold TemperatureMultilayer PerceptronsDeep LearningClassification Algorithms

Stichwörter der Autor:innen

Capsicum annuum L.deep learninggated recurrent unitnondestructiveplant phenotypingsnapshot multispectral imaging

Autor:innen und Institutionen

  • Department of Biosystems Engineering, College of Agriculture, Life, and Environment Sciences, Chungbuk National University, Cheongju 28644, Republic of Korea.
  • Vegetable Research Division, National Institute of Horticultural and Herbal Science, Wanju 55365, Republic of Korea.

ORCID-Profile: Reza Adhitama Putra Hernanda, Hoonsoo Lee

Förderung

  • Rural Development Administration
  • Cooperative Research Program for Agriculture Science and Technology Development
  • Rural Development Administration, Republic of Korea

Zitieren

APA

Hernanda, R. A. P., Jung, W., Park, M. H., & Lee, H. (2026). Multispectral Fluorescence Imaging for Fast Identification of Cold Stress in Pepper Plants. Sensors, 26(6), 1799. https://doi.org/10.3390/s26061799

Vancouver

Hernanda RAP, Jung W, Park MH, Lee H. Multispectral Fluorescence Imaging for Fast Identification of Cold Stress in Pepper Plants. Sensors. 2026;26(6):1799. doi:10.3390/s26061799

BibTeX
@article{Hernanda2026,
  author = {Hernanda, Reza Adhitama Putra and Jung, Whanjo and Park, Me-Hea and Lee, Hoonsoo},
  title = {Multispectral Fluorescence Imaging for Fast Identification of Cold Stress in Pepper Plants},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {6},
  pages = {1799},
  doi = {10.3390/s26061799}
}
Kostenlos starten →