EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BeLFG-Net: A lightweight betel leaf freshness grading network via hybrid depthwise separable convolutions

Afraz Ul Haque, Fahim Ur Rahman

Smart Agricultural Technology · 2026-12 · 15 · 102597

DOI: 10.1016/j.atech.2026.102597 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Smart Agricultural Technology, 2026-12. Verfasst von Afraz Ul Haque und 1 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Post-harvest quality grading of betel leaves ( Piper betle L.) is critical to supply chain efficiency across South and Southeast Asia, yet assessment remains an entirely manual process susceptible to inter-rater inconsistency and throughput bottlenecks. Visual freshness cues—saturated green pigmentation, surface desiccation, and brown discoloration—form a continuous rather than discrete progression, making threshold-based color analysis insufficient. We propose BeLFG-Net, a Betel Leaf Freshness Grading Network, that addresses this challenge through a hybrid four-block encoder combining standard convolutions for initial feature establishment with depthwise separable pairs for parameter-efficient cross-channel mixing, followed by global average pooling and a compact classification head. The key efficiency gain arises from the depthwise separable factorization, which decouples spatial filtering from channel-wise integration and reduces computation approximately 8–9 × relative to equivalent standard convolutions, yielding a total of only 979,651 parameters. We further introduce a progressive dropout schedule ( p ∈ {0.25, 0.25, 0.25, 0.50}) that imposes strongest regularization at the bottleneck transition, effectively curbing overfitting on the 766-image field dataset augmented to 6,262 samples. On the three-class freshness discrimination task—fresh, moderate, and stale—BeLFG-Net achieves 95.72% test accuracy with per-class F1-scores of 0.96, 0.96, and 0.95, outperforming ResNet-50 (93.77%) and MobileNetV2 (91.65%) while using 26 × and 3.5 × fewer parameters, respectively. Ablation experiments confirm that the hybrid depthwise separable block design, progressive dropout, and global average pooling each contribute independently to generalization, with combined improvements of + 6.76 % over a standard CNN baseline. These results establish that domain-specific lightweight architectures can deliver high-accuracy post-harvest classification under the resource constraints common to agricultural edge deployments.

Zitieren

APA

Haque, A. U., & Rahman, F. U. (2026). BeLFG-Net: A lightweight betel leaf freshness grading network via hybrid depthwise separable convolutions. Smart Agricultural Technology, 15, 102597. https://doi.org/10.1016/j.atech.2026.102597

Vancouver

Haque AU, Rahman FU. BeLFG-Net: A lightweight betel leaf freshness grading network via hybrid depthwise separable convolutions. Smart Agricultural Technology. 2026;15:102597. doi:10.1016/j.atech.2026.102597

BibTeX
@article{Haque2026,
  author = {Haque, Afraz Ul and Rahman, Fahim Ur},
  title = {BeLFG-Net: A lightweight betel leaf freshness grading network via hybrid depthwise separable convolutions},
  journal = {Smart Agricultural Technology},
  year = {2026},
  volume = {15},
  pages = {102597},
  doi = {10.1016/j.atech.2026.102597}
}
Kostenlos starten →