Logo PTI Logo FedCSIS

Proceedings of the 18th Conference on Computer Science and Intelligence Systems

Annals of Computer Science and Information Systems, Volume 35

Analysis of the Impact of Data Augmentation on the Performance of Deep Learning Models in Multispectral Food Authenticity Identification

, , ,

DOI: http://dx.doi.org/10.15439/2023F3643

Citation: Proceedings of the 18th Conference on Computer Science and Intelligence Systems, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 35, pages 823–832 ()

Full text

Abstract. Food authenticity is a significant concern in the meat industry, demanding effective detection methods. This study explores the use of multispectral imaging (MSI) and deep learning for meat adulteration detection. We evaluate different deep learning models using transfer learning and preprocessing techniques in a multi-level adulteration classification task. In addition, we propose a novel approach called one-band mixed augmentation for band selection in MSI data, which outperforms traditional reflectance-based feature selection and enhances model robustness. Furthermore, employing the nine-crop approach for dataset augmentation improved the accuracy from 0.63 to 0.74 for DenseNet201 model without transfer learning. This research contributes to advancing food safety assessment practices and provides insights into the application of deep learning for preventing food adulteration. The proposed one-band mixed augmentation approach offers a novel strategy for handling band selection challenges in MSI data analysis.

References

  1. C. Yang, G. Zhong, S. Zhou, Y. Guo, D. Pan, S. Wang, Q. Liu, Q. Xia, and Z. Cai, “Detection and characterization of meat adulteration in various types of meat products by using a high-efficiency multiplex polymerase chain reaction technique,” Frontiers in Nutrition, vol. 9, 2022. [Online]. Available: https://www.frontiersin.org/articles/10.3389/fnut.2022.979977
  2. K. Edwards, M. Manley, L. C. Hoffman, and P. J. Williams, “Nondestructive spectroscopic and imaging techniques for the detection of processed meat fraud,” Foods, vol. 10, no. 2, p. 448, 2021.
  3. P. F. Pereira, P. H. de Sousa Picciani, V. Calado, and R. V. Tonon, “Electrical gas sensors for meat freshness assessment and quality monitoring: A review,” Trends in Food Science & Technology, vol. 118, pp. 36–44, 2021.
  4. R. S. Andre, M. H. Facure, L. A. Mercante, and D. S. Correa, “Electronic nose based on hybrid free-standing nanofibrous mats for meat spoilage monitoring,” Sensors and Actuators B: Chemical, vol. 353, p. 131114, 2022.
  5. H. J. Marvin, E. M. Janssen, Y. Bouzembrak, P. J. Hendriksen, and M. Staats, “Big data in food safety: An overview,” Critical reviews in food science and nutrition, vol. 57, no. 11, pp. 2286–2295, 2017.
  6. M. Peyvasteh, A. Popov, A. Bykov, and I. Meglinski, “Meat freshness revealed by visible to near-infrared spectroscopy and principal component analysis,” Journal of Physics Communications, vol. 4, no. 9, p. 095011, 2020.
  7. P. Tsakanikas, L.-C. Fengou, E. Manthou, A. Lianou, E. Z. Panagou, and G.-J. E. Nychas, “A unified spectra analysis workflow for the assessment of microbial contamination of ready-to-eat green salads: Comparative study and application of non-invasive sensors,” Computers and electronics in agriculture, vol. 155, pp. 212–219, 2018.
  8. C. H. Q. Rego, F. França-Silva, F. G. Gomes-Junior, M. H. D. d. Moraes, A. D. d. Medeiros, and C. B. d. Silva, “Using multispectral imaging for detecting seed-borne fungi in cowpea,” Agriculture, vol. 10, no. 8, p. 361, 2020.
  9. S. Younas, Y. Mao, C. Liu, M. A. Murtaza, Z. Ali, L. Wei, W. Liu, and L. Zheng, “Measurement of water fractions in freeze-dried shiitake mushroom by means of multispectral imaging (msi) and low-field nuclear magnetic resonance (lf-nmr),” Journal of Food Composition and Analysis, vol. 96, p. 103694, 2021.
  10. L.-C. Fengou, E. Spyrelli, A. Lianou, P. Tsakanikas, E. Z. Panagou, and G.-J. E. Nychas, “Estimation of minced pork microbiological spoilage through fourier transform infrared and visible spectroscopy and multispectral vision technology,” Foods, vol. 8, no. 7, p. 238, 2019.
  11. M. Kamruzzaman, Y. Makino, and S. Oshita, “Rapid and non-destructive detection of chicken adulteration in minced beef using visible near-infrared hyperspectral imaging and machine learning,” Journal of Food Engineering, vol. 170, pp. 8–15, 2016.
  12. A. I. Ropodi, E. Z. Panagou, and G.-J. E. Nychas, “Multispectral imaging (msi): A promising method for the detection of minced beef adulteration with horsemeat,” Food Control, vol. 73, pp. 57–63, 2017.
  13. ——, “Rapid detection of frozen-then-thawed minced beef using multispectral imaging and fourier transform infrared spectroscopy,” Meat science, vol. 135, pp. 142–147, 2018.
  14. L.-C. Fengou, A. Lianou, P. Tsakanikas, F. Mohareb, and G.-J. E. Nychas, “Detection of meat adulteration using spectroscopy-based sensors,” Foods, vol. 10, no. 4, p. 861, 2021.
  15. X. Li, X. Fan, L. Zhao, S. Huang, Y. He, and X. Suo, “Discrimination of pepper seed varieties by multispectral imaging combined with machine learning,” Applied Engineering in Agriculture, vol. 36, no. 5, pp. 743–749, 2020.
  16. M. A. Tamayo-Monsalve, E. Mercado-Ruiz, J. P. Villa-Pulgarin, M. A. Bravo-Ortíz, H. B. Arteaga-Arteaga, A. Mora-Rubio, J. A. Alzate-Grisales, D. Arias-Garzon, V. Romero-Cano, S. Orozco-Arias et al., “Coffee maturity classification using convolutional neural networks and transfer learning,” IEEE Access, vol. 10, pp. 42 971–42 982, 2022.
  17. J. M. Carstensen and J. Folm-Hansen, “An apparatus and a method of recording an image of an object,” nov 2000, granted nov. 2003.
  18. F. Chollet, “Keras,” https://github.com/fchollet/keras, 2015.
  19. K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint https://arxiv.org/abs/1409.1556, 2014.
  20. C. Szegedy, S. Ioffe, V. Vanhoucke, and A. Alemi, “Inception-v4, inception-resnet and the impact of residual connections on learning,” in Proceedings of the AAAI conference on artificial intelligence, vol. 31, no. 1, 2017.
  21. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1–9.
  22. G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 4700–4708.
  23. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, and L. Fei-Fei, “Imagenet large scale visual recognition challenge,” 2014. [Online]. Available: https://arxiv.org/abs/1409.0575
  24. L.-C. Fengou, P. Tsakanikas, and G.-J. E. Nychas, “Rapid detection of minced pork and chicken adulteration in fresh, stored and cooked ground meat,” Food Control, vol. 125, p. 108002, 2021. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0956713521001407
  25. K. He, R. Girshick, and P. Dollár, “Rethinking imagenet pre-training,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 4918–4927.