EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Parameter- and Compute-Efficient Spatial–Spectral Transformer Framework for Pixel-Level Classification of Foreign Plastic Objects on Broiler Meat Using NIR–Hyperspectral Imaging

Zirak Khan iD, Seung-Chul Yoon iD, Suchendra M Bhandarkar

Sensors · 2026

DOI: 10.3390/s26082459 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Zirak Khan und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computing, University of Georgia, Athens, GA 30602, USA. Hauptthemen laut MEDLINE: Plastics, Meat, Hyperspectral Imaging. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: USDA-ARS and the University of Georgia, USDA—Agricultural Research Service, University of Georgia.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Foreign plastic objects (FPOs) in poultry products present significant food safety risks and cause economic losses for the industry. Conventional detection methods, including X-rays and color imaging, often struggle to identify small or low-density plastics. Hyperspectral imaging (HSI) offers both spatial and spectral information but suffers from high computational cost when applied for FPO identification in industrial environments. This study introduces a parameter-efficient and computationally efficient spatial–spectral transformer framework for pixel-level classification of FPOs on broiler meat using NIR-HSI (1000–1700 nm). The framework integrates three innovations: (1) center-focused linear attention (CFLA) to reduce computational complexity from O(n2) to O(n); (2) patch-local mixed-axis 2D rotary position embedding to preserve geometric relationships within hyperspectral patches; and (3) low-rank factorized projection (LRP) matrices to reduce parameters by approximately 50% within projection weight matrices. The framework was trained and evaluated on a dataset of 52 chicken fillets, comprising 295,340 labeled target hyperspectral pixels from 12 common polymer types and 1 fillet class. The model achieved 99.39% overall accuracy, 99.57% average accuracy, and a 99.31 Kappa coefficient across 248,540 test pixels. Per-class precision, recall, and F1-score exceeded 98.05%, 98.59%, and 98.76%, respectively, across all classes. Efficiency analyses showed an 83% reduction in multiply–accumulate operations (MACs), a 22% reduction in trainable parameters, and a model size reduction from 1.72 MB to 1.35 MB relative to the baseline configuration. These gains also translated into practical inference benefits, with the final model achieving a throughput of 212,971.5 hyperspectral patch cubes/s and a 4.19× speedup over the baseline. These results demonstrate that the proposed framework combines strong classification performance with high efficiency, supporting high-throughput inference for real-time monitoring and enabling contamination source traceability and preventive quality control in industrial poultry processing. The approach provides a benchmark for applying transformer-based models to food safety inspection tasks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PlasticsMeatHyperspectral ImagingAnimalsChickensSpectroscopy, Near-Infrared

Stichwörter der Autor:innen

computational efficiencyefficient attentionfood safetyforeign object detectionforeign plastic objectshyperspectral imagingpixel-wise classificationreal-time inspectionsensor technologytransformer

Substanzen

Plastics

Autor:innen und Institutionen

  • School of Computing, University of Georgia, Athens, GA 30602, USA.
  • Quality and Safety Research Unit, U.S. National Poultry Research Center, U.S. Department of Agriculture-Agricultural Research Service, Athens, GA 30605, USA.

ORCID-Profile: Zirak Khan, Seung-Chul Yoon

Förderung

  • USDA-ARS and the University of Georgia
  • USDA—Agricultural Research Service
  • University of Georgia

Zitieren

APA

Khan, Z., Yoon, S. C., & Bhandarkar, S. M. (2026). Parameter- and Compute-Efficient Spatial–Spectral Transformer Framework for Pixel-Level Classification of Foreign Plastic Objects on Broiler Meat Using NIR–Hyperspectral Imaging. Sensors. https://doi.org/10.3390/s26082459

Vancouver

Khan Z, Yoon SC, Bhandarkar SM. Parameter- and Compute-Efficient Spatial–Spectral Transformer Framework for Pixel-Level Classification of Foreign Plastic Objects on Broiler Meat Using NIR–Hyperspectral Imaging. Sensors. 2026. doi:10.3390/s26082459

BibTeX
@article{Khan2026,
  author = {Khan, Zirak and Yoon, Seung-Chul and Bhandarkar, Suchendra M},
  title = {Parameter- and Compute-Efficient Spatial–Spectral Transformer Framework for Pixel-Level Classification of Foreign Plastic Objects on Broiler Meat Using NIR–Hyperspectral Imaging},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26082459}
}
Kostenlos starten →