Few-Shot Ordinal Learning for Day-Wise Freshness Estimation with Hyperspectral Fish Images
2026-08-12 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors developed a new method to estimate how fresh fish fillets are using a special imaging technique that detects chemical changes over time without damaging the food. Unlike previous methods that needed lots of labeled data for each fish, their approach learns from only a few labeled examples per fillet. They treat each fish as a separate task and use a prediction model that understands the natural order in freshness levels. Tested on salmon stored for 16 days, their method predicted freshness more accurately than other models while needing less training data.
hyperspectral imagingfood quality assessmentfew-shot learningdeep learningordinal predictionmonotonicity constraintembedding smoothnesssalmon freshnessmean absolute errorunseen data protocol
Authors
Kazi Nabiul Alam, Pooneh Bagheri Zadeh, Akbar Sheikh-Akbari
Abstract
Non-destructive food quality assessment has increasingly benefited from hyperspectral imaging (HSI), which captures spectral signatures linked to biochemical changes during storage. Estimating day-wise freshness, however, remains challenging owing to strong inter-fillet variability and scarce labelled data per product. All existing deep learning approaches for HSI-based freshness prediction operate under full supervision, requiring densely annotated training sets that are costly to obtain at the individual-product level. We introduce, to the best of our knowledge, the first few-shot learning framework for HSI-based food quality estimation. Each fillet defines a distinct episodic task, and a CORAL-style ordinal prediction head captures the ranked nature of freshness progression through cumulative threshold modelling. Biologically grounded monotonicity and embedding smoothness constraints further guide predictions toward plausible trajectories. On a 16-day salmon HSI dataset under a strict unseen-fillet protocol, our method achieves a mean absolute error of 1.58 days and 2-day accuracy of 72.3% with only three labelled days per fillet, substantially outperforming scalar regression and label-distribution baselines under an identical unseen-fillet protocol.