FISH-SPEC: Fast identification system for handheld spectroscopy and species classification

• Handheld multi-mode point spectroscopy with AI identifies fish fillet species. • A hierarchical dispute model improves fish species classification for many classes. • Fusion of spectroscopic modes enhances fish fillet classification accuracy. • The portable system provides rapid, non-destructive fish identification in seconds. • Integrates fluorescence, visible, near and short-wave infra-red spectroscopy modes. Accurate fish species identification is critical to prevent mislabeling and fraud in the seafood industry. We present a handheld multi-mode point spectroscopy system that combines fluorescence (365 and 395 nm excitation) and reflectance measurements in the visible to near-infrared (∼350–900 nm) and short-wave infrared (∼900–1700 nm) regions for rapid, non-destructive classification of fish fillets. Tissue spectra were acquired at 25 positions on 68 fillets from 11 species, in both frozen and thawed states. Feature-level fusion across all four modes enabled higher classification accuracy than any single mode alone. A global machine-learning model classified all species with 85 ± 2.8 %, while specialized dispute models for commonly misclassified species improved performance to 90 % ± 6.1 %. Individual models for thawed and frozen fillets achieved 90 ± 6.0 % and 90 ± 5.4 %, respectively, with dispute models in the thawed dataset increasing accuracy to 93 ± 4.3 %. These results demonstrate that portable multi-mode spectroscopy, combined with machine learning, provides a fast and reliable tool for on-site fish species identification.