Abstract
[Objective] To develop an intelligent method for non-destructive recognition of pork loin freshness based on computer vision technology, which is to be achieved by establishing a classification model for accurate, fast, and non-destructive detection of pork freshness in the cold chain industry. [Methods] A classification detection model is proposed based on the YOLO v11 architecture. First, total volatile basic nitrogen (TVB-N) content and pH values are measured before the meat samples are divided into three categories: "fresh", "less fresh", and "spoiled". A dataset of 4 680 high-resolution images is constructed (generated from 1 247 original images enhanced through operations such as rotation, flipping, cropping, brightness adjustment, and blurring). Then, the dataset is divided into training, validation, and test sets in a 6∶2∶2 ratio. Utilizing a transfer learning strategy, the YOLO v11 model with pre-trained weights is initialized in the PyTorch framework and trained using the SGD optimizer (learning rate of 0.01). Finally, the model established is compared with six mainstream models: DenseNet 161, EfficientNet_b2, MobileNet_v2, ResNet 50, ShuffleNet_v2_x1, and ViT_base_patch16_224. [Results] The YOLO v11 model achieves excellent performance, with an overall classification precision of 1.000, significantly outperforming the best baseline model, ViT_base_patch16_224. Additionally, the proposed model demonstrates significant advantages over other models in both F1 score and accuracy metrics. [Conclusion] In this study, the YOLO v11 model is successfully applied to the non-destructive detection of pork loin freshness. With high-precision generalization capabilities, the proposed instance classification method achieves a detection rate of 1.000 for spoiled meat and ensures food safety. With an inference speed of 12 ms, this model is suitable for real-time non-destructive detection in production lines. Additionally, exhibiting a strong generalization ability, the model can evenly recognize multiple levels of freshness, with classification accuracy greater than 98% for each category.
Publication Date
7-25-2026
First Page
98
Last Page
105
DOI
10.13652/j.spjx.1003.5788.2025.80686
Recommended Citation
Zhonghui, Deng and Wei, Xie
(2026)
"Non-destructive detection of pork loin freshness based on the YOLO v 11 model,"
Food and Machinery: Vol. 42:
Iss.
7, Article 12.
DOI: 10.13652/j.spjx.1003.5788.2025.80686
Available at:
https://www.ifoodmm.cn/journal/vol42/iss7/12
References
[1] Li H,Sun D W,Han Z,et al.Effects of low temperature cooking methods and holding times on selected quality attributes of cooked pork longissimus dorsi [J].Journal of Food Process Engineering,2017,40(6):e12585.
[2] Chen J,Gu J H,Zhang R,et al.Freshness evaluation of three kinds of meats based on the electronic nose [J].Sensors,2019,19(3):605.
[3] Yang Q,Sun D W,Cheng W W.Development of simplified models for nondestructive hyperspectral imaging monitoring of TVB-N contents in cured meat during drying process [J].Journal of Food Engineering,2017,192:53-60.|[4] Dong H L,Ling Z,Zhang X,et al.Smart colorimetric sensing films with high mechanical strength and hydrophobic properties for visual monitoring of shrimp and pork freshness [J].Sensors and Actuators B:Chemical,2020,309:127752.
[5] Taiwo O R,Onyeaka H,Oladipo E K,et al.Advancements in predictive microbiology:integrating new technologies for efficient food safety models [J].International Journal of Microbiology,2024,2 024(1):6612162.
[6] 邱洪涛,孙裴,侯金波,等.基于 Caffe的猪肉新鲜度分级的设计与实现 [J].江苏农业学报,2019,35(2):461-468.Qiu H T,Sun P,Hou J B,et al.Design and implementation of pork freshness grading based on Caffe [J].Jiangsu Journal of Agricultural Sciences,2019,35(2):461-468.
[7] Shafiq M,Gu Z Q.Deep residual learning for image recognition:a survey [J].Applied Sciences,2022,12(18):8 972.
[8] Li G Q,Zhang M,Li J J,et al.Efficient densely connected convolutional neural networks [J].Pattern Recognition,2021,109:107610.
[9] 王伟,杨世忠,宫钰程,等.EfficientNet V 2算法融合 GCN和CA-Transformer 的腐烂草莓分类方法 [J].食品与机械,2024,40(12):81-88.Wang W,Yang S Z,Gong Y C,et al.Rotten strawberry classification based on EfficientNet V 2 algorithm fused with GCN and CA-Transformer [J].Food & Machinery,2024,40(12):81-88.
[10] Elfatimi E,Eryigit R,Elfatimi L.Beans leaf diseases classification using MobileNet models [J].IEEE Access,2022,10:9 471-9 482.
[11] 赵谦,孙炎.基于图像采集优化识别的白酒酒花分类方法[J].食品与机械,2025,41(1):9-17.Zhao Q,Sun Y.Foam classification method of Chinese spirits based on image acquisition optimization recognition [J].Food & Machinery,2025,41(1):9-17.
[12] 蒋瑜,王灵敏.基于改进 Alexnet的轻量化香蕉成熟度检测[J].食品与机械,2024,40(5):128-136.Jiang Y,Wang L.Lightweight banana ripeness detection based on improved Alexnet [J].Food & Machinery,2024,40(5):128-136.
[13] Ramos L T,Sappa A D.A decade of you only look once (YOLO ) for object detection:a review [J].IEEE Access,2025,13:192 747-192 758.
[14] Rasheed A F,Zarkoosh M.YOLOv 11 optimization for efficient resource utilization [J].The Journal of Supercomputing,2025,81(9):1 085.
[15] Lalinia M,Sahafi A.Colorectal polyp detection in colonoscopy images using YOLO-V 8 network [J].Signal,Image and Video Processing,2024,18(3):2 047-2 058.
[16] Zhou S Y,Li N,Peng H N,et al.The development of highly pH-sensitive bacterial cellulose nanofibers/gelatin-based intelligent films loaded with anthocyanin/curcumin for the fresh-keeping and freshness detection of fresh pork [J].Foods,2023,12(20):3 719.
[17] Xing X Y,Zhao M C,Qi L,et al.Visualization and prediction of TVB-N content in chilled pork by hyperspectral imaging [J].Food Science and Technology,2023,43:e002523.
[18] 刘超,张家瑜,戚超,等.基于 EfficientNet 网络模型的猪肉新鲜度智能识别方法 [J].食品科学,2023,44(24):369-376.Liu C,Zhang J Y,Qi C,et al.An intelligent method for pork freshness identification based on EfficientNet model [J].Food Science,2023,44(24):369-376.
