Decoding the spectrum of meat quality: advances in hyperspectral imaging for multi-attribute analysis

Area of Science:

• Food Science
• Analytical Chemistry
• Spectroscopy

Background:

• Fresh meat quality evaluation is crucial for consumer satisfaction and safety.
• Traditional methods are often destructive, time-consuming, or lack comprehensive analysis.
• Hyperspectral imaging (HSI) presents a promising non-destructive alternative.

Purpose of the Study:

• To review recent advancements in HSI applications for evaluating fresh meat quality (beef, pork, poultry).
• To explore HSI's capability in assessing key quality parameters and traits.
• To discuss modern data analysis techniques and their impact on HSI implementation in the meat industry.

Main Methods:

• Review of scientific literature on HSI applications in fresh meat quality assessment.
• Analysis of HSI principles, instrumentation, and data processing techniques.
• Focus on integration with artificial intelligence and deep learning for enhanced prediction.

Main Results:

• HSI effectively decodes various meat quality attributes including freshness, intramuscular fat (IMF), adulteration, microbial contamination, and nutritional composition.
• HSI can predict traits like tenderness, pH, and water-holding capacity.
• Advanced data analysis, including AI and deep learning, significantly improves prediction accuracy and reliability.

Conclusions:

• HSI is a revolutionary technology for comprehensive and non-destructive fresh meat quality evaluation.
• Integration of AI and deep learning is key to overcoming current challenges and enabling widespread industrial adoption.
• Further research and development are needed to optimize HSI systems for real-world meat industry applications.