The Comparison of U-net and Deeplab V3 as Semantic Segmentation Models for Food Images

Natanael Richie Irwanto(1*), Gede Putra Kusuma(2),

(1) Universitas Bina Nusantara, Jakarta, Indonesia
(2) Universitas Bina Nusantara, Jakarta, Indonesia
(*) Corresponding Author

Abstract


The Semantic segmentation models have been used for many things, namely image classification, image detection, and other activities, including outdoor and object segmentation. Those models can either work with having a good result with a custom dataset and give up an excellent accurate process or a bad one. This research aimed to compare two models of semantic segmentation model, namely Unet and Deepvlab, for food images. The research procedure is to create an original food image dataset, process the dataset with two models, analyze the IoU of two models, and compare the mIoU between the models.  The research results show that U-net has a higher mIoU value of 0.01 than Deeplab V3 but has less processing time and some parameters. The research results also show that the completeness of performance details and the prediction segmentation results in the Deeplab v3 segmentation model are superior to this research. This research supports previous research findingsregarding the use of U-net and Deeplab v3 in semantic segmentation models. It enriches research on using these models in food image recognition. Further research is needed to evaluate other models in semantic segmentation for food images.


Full Text:

PDF

References


Amber L. Mueller, Maeve S.McNamara, and David A. Sinclair, “Why does COVID-19 disproportionately affect older people?” Aging (Albany. NY)., vol. 12, no. 10, pp. 9959–9981, 2020.

I. A. Fajarini and R. A. D. Sartika, “Obesity as a common type-2 diabetes comorbidity: Eating behaviors and other determinants in Jakarta, Indonesia,” Kesmas, vol. 13, no. 4, pp. 157–163, 2019, doi: 10.21109/kesmas.v13i4.2483.

S. Dixit and G. Nandakumar, “Promoting healthy lifestyles using information technology during the COVID-19 pandemic,” Rev. Cardiovasc. Med., vol. 22, no. 1, pp. 115–125, 2021, doi: 10.31083/J.RCM.2021.01.187.

F. Zhu et al., “The use of mobile devices in aiding dietary assessment and evaluation,” IEEE J. Sel. Top. Signal Process., vol. 4, no. 4, pp. 756–766, 2010, doi: 10.1109/JSTSP.2010.2051471.

Y. Zhang, S. Mehta, and A. Caspi, “Rethinking Semantic Segmentation Evaluation for Explainability and Model Selection,” 2021, [Online]. Available: http://arxiv.org/abs/2101.08418.

M. K. Kar, M. K. Nath, and D. R. Neog, A Review on Progress in Semantic Image Segmentation and Its Application to Medical Images, vol. 2, no. 5. Springer Singapore, 2021.

F. S. Konstantakopoulos, E. I. Georga, and D. I. Fotiadis, “A Review of Image-based Food Recognition and Volume Estimation Artificial Intelligence Systems,” IEEE Rev. Biomed. Eng., pp. 1–17, 2023, doi: 10.1109/RBME.2023.3283149.

X.-Y. Kong et al., “Food Calorie Estimation System Based on Semantic Segmentation Network,” Sensors Mater., vol. 35, no. 6, p. 2013, 2023, doi: 10.18494/sam4061.

Y. J. Kwon, H. S. Lee, J.-Y. Park, and J. W. Lee, “Associating intake proportion of carbohydrate, fat, and protein with all-cause mortality in Korean adults.,” Nutrients, vol. 12, pp. 1–12, 2020.

S. Wang, Z. Zhou, and W. Zhao, “Semantic Segmentation and Defect Detection of Aerial Insulators of Transmission Lines,” J. Phys. Conf. Ser., vol. 2185, no. 1, 2022, doi: 10.1088/1742-6596/2185/1/012086.

X. Xia, Q. Lu, and X. Gu, “Exploring An Easy Way for Imbalanced Data Sets in Semantic Image Segmentation,” J. Phys. Conf. Ser., vol. 1213, no. 2, 2019, doi: 10.1088/1742-6596/1213/2/022003.

H. Zeng, S. Peng, and D. Li, “Deeplabv3+ semantic segmentation model based on feature cross attention mechanism,” J. Phys. Conf. Ser., vol. 1678, no. 1, 2020, doi: 10.1088/1742-6596/1678/1/012106.

L. C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, “DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 40, no. 4, pp. 834–848, 2018, doi: 10.1109/TPAMI.2017.2699184.

G. J. Son, D. H. Kwak, M. K. Park, Y. D. Kim, and H. C. Jung, “U-Net-based foreign object detection method using effective image acquisition system: A case of almond and green onion flake food process,” Sustain., vol. 13, no. 24, 2021, doi: 10.3390/su132413834.

L. Mo, Y. Fan, G. Wang, X. Yi, X. Wu, and P. Wu, “DeepMDSCBA: An Improved Semantic Segmentation Model Based on DeepLabV3+ for Apple Images,” Foods, vol. 11, no. 24, pp. 1–19, 2022, doi: 10.3390/foods11243999.

H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, and S. Savarese, “Generalized intersection over union: A metric and a loss for bounding box regression,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2019-June, pp. 658–666, 2019, doi 10.1109/CVPR.2019.00075.

X. Wang, Z. Hu, S. Shi, M. Hou, L. Xu, and X. Zhang, “A deep learning method for optimizing semantic segmentation accuracy of remote sensing images based on improved UNet,” Sci. Rep., vol. 13, no. 1, pp. 1–13, 2023, doi: 10.1038/s41598-023-34379-2.

M. Thoma, “A Survey of Semantic Segmentation,” ArXiv, pp. 1–16, 2016, [Online]. Available: http://arxiv.org/abs/1602.06541.

X. Liu, Z. Deng, and Y. Yang, “Recent progress in semantic image segmentation,” Artif. Intell. Rev., vol. 52, no. 2, pp. 1089–1106, 2019, doi: 10.1007/s10462-018-9641-3.

V. Burkapalli and P. Patil, “A Review on Segmentation Techniques for Food Images,” Int. J. Emerg. Technol. Comput. Sci. Electron., vol. 23, no. 6, pp. 250–255, 2016.

X. Wu, X. Fu, Y. Liu, E. P. Lim, S. C. H. Hoi, and Q. Sun, A Large-Scale Benchmark for Food Image Segmentation, vol. 1, no. 1. Association for Computing Machinery, 2021.

H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid scene parsing network,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 6230–6239, 2017, doi: 10.1109/CVPR.2017.660.

Z. Wu, C. Shen, and A. van den Hengel, “Wider or Deeper: Revisiting the ResNet Model for Visual Recognition,” Pattern Recognit., vol. 90, no. December 2016, pp. 119–133, 2019, doi 10.1016/j.patcog.2019.01.006.

H. Sharif, F. Rehman, A. Rida, and A. Sharif, “Segmentation of Images Using Deep Learning: A Survey,” 2022 2nd Int. Conf. Digit. Futur. Transform. Technol. ICoDT2 2022, 2022, doi: 10.1109/ICoDT255437.2022.9787440.

W. Weng and X. Zhu, “INet: Convolutional Networks for Biomedical Image Segmentation,” IEEE Access, vol. 9, pp. 16591–16603, 2021, doi: 10.1109/ACCESS.2021.3053408.

N. Navab, J. Hornegger, W. M. Wells, and A. F. Frangi, “Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015: 18th International Conference Munich, Germany, October 5-9, 2015 proceedings, part III,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 9351, no. Cvd, pp. 12–20, 2015, doi: 10.1007/978-3-319-24574-4.

X. Hao, L. Yin, X. Li, L. Zhang, and R. Yang, “A Multi-Objective Semantic Segmentation Algorithm Based on Improved U-Net Networks,” Remote Sens., vol. 15, no. 7, pp. 1–14, 2023, doi: 10.3390/rs15071838.

L. Xia et al., “Evaluation of deep learning segmentation models for detection of pine wilt disease in unmanned aerial vehicle images,” Remote Sens., vol. 13, no. 18, pp. 1–15, 2021, doi: 10.3390/rs13183594.

S. Zhao, G. Hao, Y. Zhang, and S. Wang, “A Real-Time Semantic Segmentation Method of Sheep Carcass Images Based on ICNet,” J. Robot., vol. 2021, 2021, doi: 10.1155/2021/8847984.

S. Gao and Z. Y. Chen, “Semantic Segmentation of Germinated Oil Palm Seeds Based on Deep Convolutional Neural Networks with a Novel Channel Attention Mechanism,” pp. 1–26.

T. Lee, J. H. Kim, S. J. Lee, S. K. Ryu, and B. C. Joo, “Improvement of

Concrete Crack Segmentation Performance Using Stacking Ensemble Learning,” Appl. Sci., vol. 13, no. 4, 2023, doi: 10.3390/app13042367.

H. Xu, J. Song, and Y. Zhu, “Evaluation and Comparison of Semantic Segmentation Networks for Rice Identification Based on Sentinel-2 Imagery,” Remote Sens., vol. 15, no. 6, 2023, doi: 10.3390/rs15061499.

D. Yang, Y. Du, H. Yao, and L. Bao, “Image semantic segmentation with hierarchical feature fusion based on deep neural network,” Conn. Sci., vol. 34, no. 1, pp. 1772–1784, 2022, doi: 10.1080/09540091.2022.2082384.

S. Aslan, G. Ciocca, D. Mazzini, and R. Schettini, “Benchmarking algorithms for food localization and semantic segmentation,” Int. J. Mach. Learn. Cybern., vol. 11, no. 12, pp. 2827–2847, 2020, doi: 10.1007/s13042-020-01153-z.




DOI: https://doi.org/10.30645/brahmana.v5i1.281

DOI (PDF): https://doi.org/10.30645/brahmana.v5i1.281.g278

Refbacks

  • There are currently no refbacks.


Published Papers Indexed/Abstracted By: