The relationship between freshness changes and visual images of Litopenaeus vannamei was established based on Sensory Evaluation, Total Volatile Base Nitrogen (TVB-N), Total Viable Count (TVC), and Gray Value during storage at 4 °C. A non-destructive detection system using the advanced YOLO(You Only Look Once)-Shrimp model was developed to evaluate shrimp freshness. The results revealed a gradual increase in freshness indices over time, with the gray value showing strong positive correlations with TVB-N and TVC (0.88 and 0.81). The advanced YOLO-Shrimp model demonstrated notable performance enhancements over the YOLOv8 model, as evidenced by a precision increase of 5.07 %, a recall improvement of 1.58 %, a 3.25 % rise in the F1 score, and a 2.84 % elevation in mAP50. This innovative approach offers substantial potential for enhancing food safety and quality control in the seafood industry.

中文翻译：

---

海鲜新鲜度的创新：使用 YOLO-shrimp 模型无损检测南美白对虾的新鲜度


根据 4 °C 贮藏期间的感官评价、总挥发性碱氮 （TVB-N）、总活菌数 （TVC） 和灰度值，建立了凡纳滨对虾新鲜度变化与视觉图像之间的关系。 使用先进的 YOLO（You Only Look Once）-Shrimp 模型开发了一种无损检测系统来评估虾的新鲜度。结果显示，新鲜度指数随着时间的推移逐渐增加，灰度值与 TVB-N 和 TVC 呈很强的正相关 （0.88 和 0.81）。与 YOLOv8 模型相比，先进的 YOLO-Shrimp 模型表现出显著的性能增强，精度提高了 5.07%，召回率提高了 1.58%，F1 分数提高了 3.25%，mAP50 提高了 2.84%。这种创新方法为加强海产品行业的食品安全和质量控制提供了巨大的潜力。