Early Detection of Postharvest Potato Tuber Dry Rot Based on Hyperspectral Imaging and a Dual-Branch ResNet12-SE Spatial–Spectral Fusion Network
Journal of Fungi · 20.09.2026 · 12 (9) · 702
DOI: 10.3390/jof12090702 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Fungi, online erschienen am 20.09.2026. Verfasst von Hanwen Cao und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Department of Science and Technology of Inner Mongolia Autonomous Region, Science and Technology Innovation Capacity Improvement Program of Inner Mongolia Autonomous Region.
Abstract (Originalsprache)
Potato tuber dry rot is a major postharvest decay caused predominantly by Fusarium spp. During early infection, external symptoms may be absent even when faint internal browning, localized dehydration, and tissue structure changes have begun. Manual inspection, destructive cutting, and culture- or molecular-based assays are therefore poorly suited to rapid, nondestructive, high-throughput screening. We developed a near-infrared hyperspectral imaging method that combines spatial and spectral representations in a dual-branch ResNet12-SE network. The working dataset contained 1725 labeled records (862 healthy and 863 early-infected records); records were assigned to subsets by tuber identifier, and an infected volume ratio below 5% was used as an operational early infection threshold. The calibrated model input was a 224-band, 224 × 224 hyperspectral cube. The spatial branch used a ResNet-12 backbone with spatial squeeze-and-excitation (SE), whereas the spectral branch used spectral SE followed by bidirectional long short-term memory (BiLSTM). The two feature vectors were concatenated for binary classification. In the single-split test, the proposed model achieved 98.22% accuracy, compared with 90.67% for the ResNet-12 baseline and 97.43% for Vision Transformer. Preprocessing, principal component image, local binary pattern, and gray-level co-occurrence matrix analyses provide complementary interpretation of the spectral and spatial responses. The results support the feasibility of hyperspectral screening under the controlled laboratory protocol and define the validation work required before broader deployment.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, China.
- Key Laboratory of the Development and Resource Utilization of Biological Pesticide in Inner Mongolia, Inner Mongolia Agricultural University, Hohhot 010018, China.
- College of Science, Gansu Agricultural University, Lanzhou 730070, China.
ORCID-Profile: Hanwen Cao, Huali Xue
Förderung
- National Natural Science Foundation of China
- Department of Science and Technology of Inner Mongolia Autonomous Region
- Science and Technology Innovation Capacity Improvement Program of Inner Mongolia Autonomous Region
Zitieren
APA
Cao, H., Liu, J., Liu, T., Zhao, M., Xue, H., & Hao, M. (2026). Early Detection of Postharvest Potato Tuber Dry Rot Based on Hyperspectral Imaging and a Dual-Branch ResNet12-SE Spatial–Spectral Fusion Network. Journal of Fungi, 12(9), 702. https://doi.org/10.3390/jof12090702
Vancouver
Cao H, Liu J, Liu T, Zhao M, Xue H, Hao M. Early Detection of Postharvest Potato Tuber Dry Rot Based on Hyperspectral Imaging and a Dual-Branch ResNet12-SE Spatial–Spectral Fusion Network. Journal of Fungi. 2026;12(9):702. doi:10.3390/jof12090702
BibTeX
@article{Cao2026,
author = {Cao, Hanwen and Liu, Jiahui and Liu, Tao and Zhao, Mingmin and Xue, Huali and Hao, Min},
title = {Early Detection of Postharvest Potato Tuber Dry Rot Based on Hyperspectral Imaging and a Dual-Branch ResNet12-SE Spatial–Spectral Fusion Network},
journal = {Journal of Fungi},
year = {2026},
volume = {12},
number = {9},
pages = {702},
doi = {10.3390/jof12090702}
}
EUVIMED