Summary
This paper presents a non-destructive analytical method for quantifying egg yolk ratio using visible and near-infrared hyperspectral imaging combined with machine learning. The approach addresses the limitations of traditional destructive sampling methods used in poultry quality assessment. By incorporating explainable AI, the authors likely provide transparency into which spectral features most strongly predict yolk composition, potentially enabling rapid, in-line quality assessment in commercial egg production.
UK applicability
This method could support UK egg producers and processors in quality assurance and grading operations, particularly for premium or nutrient-claim products. Adoption would require integration with existing production infrastructure and validation against UK market standards.
Key measures
Egg yolk ratio (percentage of yolk by mass or volume); hyperspectral imaging wavelength ranges; machine learning model accuracy metrics; feature importance scores from explainable AI
Outcomes reported
The study reports development and validation of a non-destructive hyperspectral imaging method coupled with machine learning algorithms to quantify egg yolk ratio in whole eggs. The method was evaluated for accuracy and interpretability using explainable AI techniques.
Topic tags
Dig deeper with Pulse AI.
Pulse AI has read the whole catalogue. Ask about this record, its theme, or how the findings apply to UK farming and policy — every answer cites the underlying studies.