Lightweight Semantic Segmentation for Fermentation Foam Monitoring: A Comparative Study of U-Net, DeepLabV3+, Fast-SCNN, and SegNet
Source abstract
Abstract
This study aims to identify an effective neural network architecture for the task of semantic segmentation of the surface of beer wort at the stage of primary fermentation, using deep learning methodologies. Four contemporary architectures were evaluated and contrasted. The following networks are presented in both baseline and optimized forms: U-Net, DeepLabV3+, Fast-SCNN, and SegNet. The models were trained on a dataset of images depicting real beer surfaces at the primary fermentation stage. This was followed by the validation of the models using key metrics, including pixel classification accuracy, Mean Intersection over Union (mIoU), Dice Coefficient, inference time per image, and Graphics Processing Unit (GPU) resource utilization. Results indicate that the optimized U-Net achieved the optimal balance between performance and efficiency, attaining a validation accuracy of 88.85%, mIoU of 76.72%, and a Dice score of 86.71%. With an inference time of 49.5 milliseconds per image, coupled with minimal GPU utilization (18%), the model proves suitable for real-time deployment in production environments. Conversely, complex architectures, such as DeepLabV3+, did not yield the anticipated benefits, thereby underscoring the viability of utilizing compact models for highly specialized industrial tasks. This study establishes a novel quantitative metric for the assessment of fermentation. This is based on the characteristics of the foam surface and thus offers an objective alternative to traditional subjective inspections. The findings emphasize the potential of adapting optimized deep learning architectures to quality control tasks within the food industry, particularly in the brewing sector, and they pave the way for further integration into automated computer vision systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fermentation and Sensory Analysis · Spectroscopy and Chemometric Analyses · Advanced Chemical Sensor Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Institute of Power Engineering and Control Systems, Lviv Polytechnic National University, 12 Stepan Bandera Str., 79013 Lviv, Ukraine
Department of Fundamentals of Computer Science, University of the National Education Commission, 30-084 Krakow, Poland
Department of Technical and Computer Education, University of the National Education Commission, 30-084 Krakow, Poland
References (40)
Show source-provided references
1. Recent Advances and Applications of Artificial Intelligence and Related Technologies in the Food Industry10.1016/j.afres.2022.100126 ↗
2. Gonzalez Viejo, C., Torrico, D.D., Dunshea, F.R., and Fuentes, S. (2019). Emerging Technologies Based on Artificial Intelligence to Assess the Quality and Consumer Preference of Beverages. Beverages, 5.10.3390/beverages5040062 ↗
3. Kunze, W., and Manger, H.-J. (2014). Technology Brewing & Malting, VLB. 5th revised English ed.
4. Computer Vision Based Food Grain Classification: A Comprehensive Survey10.1016/j.compag.2021.106287 ↗
5. Bowler, A.L., Pound, M.P., and Watson, N.J. (2021). Domain Adaptation and Federated Learning for Ultrasonic Monitoring of Beer Fermentation. Fermentation, 7.10.3390/fermentation7040253 ↗
6. Diéguez, Á., Moreno, S., Moncada-Madrazo, S., Caravaca, O., Diéguez, J., Canals, J., Benito-Altamirano, I., Prades, J.D., and Vilà, A. (2024). Chip-Sized Microscopy for Continuous Monitoring: Application in White Wine Fermentation and Yeast Cell Counting via Deep Learning. Eng. Proc., 78.10.3390/engproc2024078001 ↗
7. U-Net: Convolutional Networks for Biomedical Image Segmentation
8. UNet++: A Nested U-Net Architecture for Medical Image Segmentation
9. Inverse Architecture U-Net—InvU-Net
10. Chen, L.-C., Papandreou, G., Schroff, F., and Adam, H. (2017). Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv.
11. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs10.1109/TPAMI.2017.2699184 ↗
12. Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., and Adam, H. (2018, January 8–14). Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_49 ↗
13. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation10.1109/TPAMI.2016.2644615 ↗
14. A State-of-the-Art Survey for Microorganism Image Segmentation Methods and Future Potential10.1109/ACCESS.2019.2930111 ↗
15. A Survey on Image Data Augmentation for Deep Learning10.1186/s40537-019-0197-0 ↗
16. Poudel, R.P.K., Liwicki, S., and Cipolla, R. (2019, January 9–12). Fast-SCNN: Fast Semantic Segmentation Network. Proceedings of the British Machine Vision Conference (BMVC), Cardiff, UK.
17. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv.
18. Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for MobileNetV3. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.
19. Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., and Kalenichenko, D. (2018, January 18–23). Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00286 ↗
20. Gonzalez Viejo, C., Fuentes, S., and Hernandez-Brenes, C. (2021). Smart Detection of Faults in Beers Using Near-Infrared Spectroscopy, a Low-Cost Electronic Nose and Artificial Intelligence. Fermentation, 7.10.3390/fermentation7030117 ↗
21. Gonzalez Viejo, C., Torrico, D.D., Dunshea, F.R., and Fuentes, S. (2019). Development of Artificial Neural Network Models to Assess Beer Acceptability Based on Sensory Properties Using a Robotic Pourer: A Comparative Model Approach to Achieve an Artificial Intelligence System. Beverages, 5.10.3390/beverages5020033 ↗
22. Buonocore, D., Ciavolino, G., Dello Iacono, S., and Liguori, C. (2024). Online Identification of Beer Fermentation Phases. Fermentation, 10.10.3390/fermentation10080399 ↗
23. From Data to Draught: Modelling and Predicting Mixed-Culture Beer Fermentation Dynamics Using Autoregressive Recurrent Neural Networks10.3390/modelling5010011 ↗
24. Blur Unblurred—A Mini Tutorial10.1177/2041669518765850 ↗
25. Improving the Effectiveness of the Median Filter
26. OpenCV (2025, January 20). Contours: Getting Started (Python). Available online: https://docs.opencv.org/4.x/d4/d73/tutorial_py_contours_begin.html.
27. The OpenCV Library
28. A Comparative Study of Efficient Initialization Methods for the K-Means Clustering Algorithm10.1016/j.eswa.2012.07.021 ↗
29. Practical Recommendations for Gradient-Based Training of Deep Architectures
30. The Pascal Visual Object Classes (VOC) Challenge10.1007/s11263-009-0275-4 ↗
31. Measures of the Amount of Ecologic Association Between Species10.2307/1932409 ↗
32. Kingma, D.P., and Ba, J. (2015, January 7–9). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations (ICLR), San Diego, CA, USA.
33. Ioffe, S., and Szegedy, C. (2015, January 6–11). Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Proceedings of the 32nd International Conference on Machine Learning (ICML), Lille, France.
34. Jung, W., Jung, D., Kim, B., Lee, S., Rhee, W., and Ahn, J.H. (April, January 31). Restructuring Batch Normalization to Accelerate CNN Training. Proceedings of the SysML Conference, Palo Alto, CA, USA.
35. Han, S., Mao, H., and Dally, W.J. (2016, January 2–4). Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding. Proceedings of the International Conference on Learning Representations (ICLR), San Juan, Puerto Rico.
36. Chollet, F. (2017). Xception: Deep Learning with Depthwise Separable Convolutions. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR.2017.195 ↗
37. He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.10.1109/CVPR.2016.90 ↗
38. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE.10.1109/CVPR.2018.00474 ↗
39. Chen, T., Moreau, T., Jiang, Z., Zheng, L., Yan, E., Cowan, M., Shen, H., Wang, L., Hu, Y., and Ceze, L. (2018, January 8–10). TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI’18), Carlsbad, CA, USA.
40. Milletari, F., Navab, N., and Ahmadi, S.-A. (2016). V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. Proceedings of the 2016 Fourth International Conference on 3D Vision (3DV), IEEE.10.1109/3DV.2016.79 ↗