Intelligent classification and identification method for Conger myriaster freshness based on DWG-YOLOv8 network model

Abstract

The freshness of aquatic products is directly related to the safety and health of the people. Traditional methods of detecting the freshness of Conger myriaster rely on manual operations, which are labor-intensive, inefficient, and highly subjective. This paper combines computer vision and the DWG-YOLOv8 network model to establish an intelligent classification method for C. myriaster freshness. Through image augmentation, 484 C. myriaster samples were expanded to 2904 samples. The YOLOv8n model was improved by simplifying the network backbone, introducing Ghost convolution and the new DW-GhostConv, thereby reducing the number of parameters and computational load. Test results show that the recognition accuracy of the DWG-YOLOv8 model reached 98.958%, out-performing models such as ResNet18, Mobilenetv3 small, and Swin transformer v2 tiny. The model’s parameter count is 16.609 K, the inference time is 57.80 ms, and the model size is only 102 KB. The research provides a reliable method for online intelligent and nondestructive detection of C. myriaster freshness.

Keywords

classification recognition / computer vision / Conger myriaster freshness / deep learning / DWG-YOLOv8 network

References

[1] Bernardi, D. C., Mársico, E. T., & Freitas, M. Q. (2013). Quality Index Method (QIM) to assess the freshness and shelf life of fish. Brazilian Archives of Biology and Technology, 56(4), 587–598.

[2] Bian, R., Cao, R., Zhao, L., Liu, Q., & Ren, D. (2017). Application of the electronic nose for assessing the freshness of Cololabis saira. Modern Food Science and Technology, 33(1), 243–247+260. https://doi.org/10.13982/j.mfst.1673-9078.2017.1.037

[3] Chakraborty, S., Shamrat, F. M. J. M., Billah, M. M., Jubair, M. A., Alauddin, M., & Ranjan, R. (2021). Implementation of deep learning methods to identify rotten fruits, In 2021 5th International Conference on Trends in Electronics and Informatics (ICOEI) (pp. 1207–1212). IEEE.

[4] Cheng, J., Sun, J., Shi, L., & Dai, C. (2024). An effective method fusing electronic nose and fluorescence hyperspectral imaging for the detection of pork freshness. Food Bioscience, 59, 103880.

[5] Chmiel, M., Słowiński, M., & Dasiewicz, K. (2011). Lightness of the color measured by computer image analysis as a factor for assessing the quality of pork meat. Meat Science, 88(3), 566–570.

[6] Chmiel, M., Słowiński, M., Dasiewicz, K., & Florowski, T. (2016). Use of computer vision system (CVS) for detection of PSE pork meat obtained from m. semimembranosus. LWT, 65, 532–536.

[7] Chouhan, S. S., Singh, U. P., Sharma, U., & Jain, S. (2021). Leaf disease segmentation and classification of Jatropha Curcas L. and Pongamia Pinnata L. biofuel plants using computer vision based approaches. Measurement, 171, 108796.

[8] Dias, P. A., Tabb, A., & Medeiros, H. (2018). Multispecies fruit flower detection using a refined semantic segmentation network. IEEE Robotics and Automation Letters, 3(4), 3003–3010.

[9] Du, L., Chai, C., Guo, M., & Lu, X. (2015). A model for discrimination freshness of shrimp. Sensing and Bio-Sensing Research, 6, 28–32.

[10] Fengou, L.-C., Lianou, A., Tsakanikas, P., Gkana, E. N., Panagou, E. Z., & Nychas, G.-J. E. (2019). Evaluation of Fourier transform infrared spectroscopy and multispectral imaging as means of estimating the microbiological spoilage of farmed sea bream. Food Microbiology, 79, 27–34.

[11] Gao, Y., Tang, H., Ou, C., Li, Y., Wu, C., & Cao, J. (2016). Differentiation between fresh and frozen-thawed large yellow croaker based on front-face fluorescence spectroscopy technique. Transactions of the Chinese Society of Agricultural Engineering, 32(16), 279–285.

[12] Girolami, A., Napolitano, F., Faraone, D., & Braghieri, A. (2013). Measurement of meat color using a computer vision system. Meat Science, 93(1), 111–118.

[13] Gumus, B., Balaban, M., & Ünlüsayin, M. (2011). Machine vision applications to aquatic foods: A review. Turkish Journal of Fisheries and Aquatic Sciences, 11, 171–181. https://doi.org/10.4194/trjfas.2010.0124

[14] Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., & Xu, C. (2020, March 13). GhostNet: More features from cheap operations. arXiv, arXiv:1911.11907. https://doi.org/10.48550/arXiv.1911.11907.

[15] Hu, J., Zhou, C., Zhao, D., Zhang, L., Yang, G., & Chen, W. (2020). A rapid, low-cost deep learning system to classify squid species and evaluate freshness based on digital images. Fisheries Research, 221, 105376.

[16] Huang, X., Guan, C., Ding, R., & Lü R. (2015). Freshness evaluation of sea bass using multi-sensor information fusion based on olfactory visualization and NIR spectroscopy technique. Transactions of the Chinese Society of Agricultural Engineering, 31(8), 277–282.

[17] Jackman, P., Sun, D.-W., & Allen, P. (2011). Recent advances in the use of computer vision technology in the quality assessment of fresh meats. Trends in Food Science & Technology, 22(4), 185–197.

[18] Ji, X., Dong, Z., Han, Y., Lai, C. S., & Qi, D. (2023). A brain-inspired hierarchical interactive in-memory computing system and its application in video sentiment analysis. IEEE Transactions on Circuits and Systems for Video Technology, 33(12), 7928–7942.

[19] Ji, X., Dong, Z., Han, Y., Lai, C. S., Zhou, G., & Qi, D. (2023). EMSN: An energy-efficient memristive sequencer network for human emotion classification in mental health monitoring. IEEE Transactions on Consumer Electronics, 69, 1005–1016.

[20] Jun, J., Wang, W., Hou, J., Sun, P., He, Y., & Gu, L. (2019). Freshness identification of Iberico pork based on improved residual network and transfer learning. Transactions of Agricultural Machinery, 50(8), 364–371.

[21] Li, Z., Li, M., Zhao, Y., Guo, R., & Chen, Y. (2021). Iced pomfret freshness evaluation method based on improved VGG-19 convolutional neural networks. Transactions of the Chinese Society of Agricultural Engineering, 37(22), 286–294.

[22] Li, Z. L., & Ma, Y. (2019). Changes of freshness and texture of Fenneropenaeus chinensis during frozen storage. Food Industry, 40, 122–126. https://doc.taixueshu.com/journal/20190529spgy.html

[23] Liu, C., Zhang, J., Qi, C., Huang, J., & Chen, K. (2023). An intelligent method for pork freshness identification based on EfficientNet model. Food Science, 44(24), 369–376.

[24] Liu, Q., Peng, J., Chen, N., Sun, W., Ning, Y., & Du, Q. (2023). Category-specific prototype self-refinement contrastive learning for few-shot hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 61, 1–16.

[25] Liu, W., Liu, K., Sun, W., Yang, G., Ren, K., Meng, X., & Peng, J. (2023). Self-supervised feature learning based on spectral masking for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 61, 1–15.

[26] Ma, C., Zhang, H., Ma, X., Wang, J., Zhang, Y., & Zhang, X. (2024). Method for the lightweight detection of wheat disease using improved YOLOv8. Transactions of the Chinese Society of Agricultural Engineering, 40(5), 187–195.

[27] Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6(1), 60.

[28] Taheri-Garavand, A., Fatahi, S., Banan, A., & Makino, Y. (2019). Real-time nondestructive monitoring of Common Carp Fish freshness using robust vision-based intelligent modeling approaches. Computers and Electronics in Agriculture, 159, 16–27.

[29] Tong, Y., Xie, J., Xiao, H., & Yang, S. (2010). Prediction model of shelf life of Trichiurus haumela using an electric nose. Transactions of the CSAE, 26(2), 356–360.

[30] Wang, K., Zhang, C., & Wang, R. (2023). Intelligent recognition of freshness of chilled red shrimp based on deep learning. Automation & Instrumentation, 38(11), 84–87+114. https://doi.org/10.19557/j.cnki.1001-9944.2023.11.018

[31] Wu, L., Pu, H., & Sun, D.-W. (2019). Novel techniques for evaluating freshness quality attributes of fish: A review of recent developments. Trends in Food Science & Technology, 83, 259–273.

[32] Wu, X., Guo, W., Zhu, Y., Zhu, H., & Wu, H. (2024). Transplant status detection algorithm of cabbage in the field based on improved YOLOv8s. Smart Agriculture, 6(2), 107–117.

[33] Xu, R., Wang, Y., Ding, W., Yu, J., Yan, M., & Chen, C. (2024). Shrimp diseases detection method based on improved YOLOv8 and multiple features. Smart Agriculture, 6(2), 62–71.

[34] Zheng, S., & Chen, W. (2019). Evaluation of code freshness based on electronic nose and electronic tongue technology. China Condiment, 44(5), 164–169.

[35] Zhou, H., Jin, S., Zhou, L., Guo, Z., Sun, M., & Shi, M. (2023). Classification and recognition of camellia oleifera fruit in the field based on transfer learning and YOLOv8n. Transactions of the Chinese Society of Agricultural Engineering, 39(20), 159–166.

[36] Zhu, L., & Spachos, P. (2021). Support vector machine and YOLO for a mobile food grading system. Internet of Things, 13, 100359.

RIGHTS & PERMISSIONS

2024 The Author(s). Food Bioengineering published by John Wiley & Sons Australia, Ltd. on behalf of State Key Laboratory of Bioreactor Engineering, East China University of Science and Technology.