Object Segmentation in Stunted Face Images using Deeplabv3+ with Resnet-50
##plugins.themes.bootstrap3.article.main##
Keywords
Stunting, segmentation, ResNet-50, accuracy
Abstract
Stunting is the impaired growth and development that children experience from poor nutrition, repeated infection, and inadequate psychosocial stimulation. This study explores the impact of data preprocessing, specifically using DeepLabV3+ segmentation, on the performance of ResNet-50 in classifying stunting and non-stunting facial images. Initially, ResNet-50 achieved 99% accuracy and a 3.22% loss with the unsegmented dataset. By applying DeepLabV3+ to remove irrelevant features and backgrounds, the model's performance improved to a perfect 100% accuracy and a reduced loss of 0.45%. These results underscore the importance of high-quality data preprocessing in enhancing model precision and reliability. The findings have significant implications for practical applications, particularly in medical imaging, where improved diagnostic accuracy can benefit patient outcomes. Further research is recommended to explore additional preprocessing methods and their effects on model performance across diverse domains. This study highlights the transformative potential of effective data preprocessing in optimizing deep learning models for more accurate and reliable machine learning solutions.
References
[1] C. Scheffler et al., “Stunting is not a synonym of malnutrition,” Eur. J. Clin. Nutr., vol. 74, no. 3, pp. 377–386, 2020, Accessed: Aug. 10, 2024. [Online]. Available: https://www.nature.com/articles/s41430-019-0439-4
[2] S. K. Zhou et al., “A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises,” Proc. IEEE, vol. 109, no. 5, pp. 820–838, 2021, Accessed: Aug. 10, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9363915/
[3] Y. Yunidar, R. Roslidar, M. Oktiana, Y. Yusni, N. Nasaruddin, and F. Arnia, “Classification of stunted and normal children using novel facial image database and convolutional neural network,” Radioelectron. Comput. Syst., vol. 2024, no. 1, pp. 76–86, 2024, Accessed: Jul. 17, 2024. [Online]. Available: https://nti.khai.edu/ojs/index.php/reks/article/view/reks.2024.1.07
[4] Y. Liu, X. Bai, J. Wang, G. Li, J. Li, and Z. Lv, “Image semantic segmentation approach based on DeepLabV3 plus network with an attention mechanism,” Eng. Appl. Artif. Intell., vol. 127, p. 107260, 2024, Accessed: Aug. 10, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0952197623014446
[5] В. М. Рувінська and Ю. Ю. Тімков, “Deep learning technology for videoframe processing in face segmentation on mobile devices,” Вісник Сучасних Інформаційних Технологій, vol. 4, no. 2, pp. 185–194, 2021, Accessed: Aug. 10, 2024. [Online]. Available: https://hait.od.ua/index.php/journal/article/view/109
[6] S. Patel, “Deep learning models for image segmentation,” in 2021 8th International conference on computing for sustainable global development (INDIACom), IEEE, 2021, pp. 149–154. Accessed: Aug. 10, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9441388/
[7] A. Y. Agyeman and S. G. Tetteh, “Technical Evaluation of Machine Learning Models: An Empirical Study,” ESP Int. J. Adv. Comput. Technol. ESP-IJACT, vol. 2, no. 1, pp. 1–9, Jan. 2024, Accessed: Nov. 05, 2024. [Online]. Available: https://www.espjournals.org/IJACT/ijact-v2i1p101
[8] Z. H. U. Runhu, X. I. N. Binjie, D. Na, and F. A. N. Mingzhu, “Semantic segmentation using deeplabv3+ model for fabric defect detection,” Wuhan Univ. J. Nat. Sci., vol. 27, no. 6, pp. 539–549, 2022, Accessed: Aug. 10, 2024. [Online]. Available: https://wujns.edpsciences.org/articles/wujns/abs/2022/06/wujns-1007-1202-2022-06-0539-11/wujns-1007-1202-2022-06-0539-11.html
[9] H. Polat, “A modified DEEPLABV3 + based semantic segmentation of chest computed tomography images for COVID ‐19 lung infections,” Int. J. Imaging Syst. Technol., vol. 32, no. 5, pp. 1481–1495, Sep. 2022, doi: 10.1002/ima.22772.
[10] S. O. Atik, M. E. Atik, and C. Ipbuker, “Comparative research on different backbone architectures of DeepLabV3+ for building segmentation,” J. Appl. Remote Sens., vol. 16, no. 2, pp. 024510–024510, 2022, Accessed: Nov. 05, 2024. [Online]. Available: https://www.spiedigitallibrary.org/journals/journal-of-applied-remote-sensing/volume-16/issue-2/024510/Comparative-research-on-different-backbone-architectures-of-DeepLabV3-for-building/10.1117/1.JRS.16.024510.short
[11] H. Polat, “Multi-task semantic segmentation of CT images for COVID-19 infections using DeepLabV3+ based on dilated residual network,” Phys. Eng. Sci. Med., vol. 45, no. 2, pp. 443–455, Jun. 2022, doi: 10.1007/s13246-022-01110-w.
[12] M. A. Butt and F. Riaz, “CARL-D: A vision benchmark suite and large scale dataset for vehicle detection and scene segmentation,” Signal Process. Image Commun., vol. 104, p. 116667, 2022, Accessed: Aug. 11, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0923596522000224
[13] M. Cai et al., “Image segmentation method for sweetgum leaf spots based on an improved DeeplabV3+ network,” Forests, vol. 13, no. 12, p. 2095, 2022, Accessed: Aug. 11, 2024. [Online]. Available: https://www.mdpi.com/1999-4907/13/12/2095
[14] T. Ashine, “Image-Based Rose Leaf Diseases Detection Using Deep Learning,” Thesis, St. Mary’s University, 2024. Accessed: Aug. 11, 2024. [Online]. Available: https://repository.smuc.edu.et/handle/123456789/7886
[15] B. Li and D. Lima, “Facial expression recognition via ResNet-50,” Int. J. Cogn. Comput. Eng., vol. 2, pp. 57–64, 2021, Accessed: Aug. 11, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2666307421000073
[16] G. Singh, A. Mittal, and N. Aggarwal, “ResDNN: deep residual learning for natural image denoising,” IET Image Process., vol. 14, no. 11, pp. 2425–2434, Sep. 2020, doi: 10.1049/iet-ipr.2019.0623.
[17] A. Amelio et al., “Representation and compression of Residual Neural Networks through a multilayer network based approach,” Expert Syst. Appl., vol. 215, p. 119391, 2023, Accessed: Aug. 11, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0957417422024095
[18] H. Tahir, M. S. Khan, and M. O. Tariq, “Performance analysis and comparison of faster R-CNN, mask R-CNN and ResNet50 for the detection and counting of vehicles,” in 2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), IEEE, 2021, pp. 587–594. Accessed: Aug. 11, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9397079/
[19] M. M. Murimi, “Identification Of Maize Leaf Diseases Using Support Vector Machine And Convolutional Neural Networks Alexnet And Resnet50,” Phd Thesis, Karatina University, 2023. Accessed: Jul. 16, 2024. [Online]. Available: https://karuspace.karu.ac.ke/bitstream/handle/20.500.12092/2999/FULLTEXT.pdf?sequence=1
[20] P. Venugopal, P. K. R. Maddikunta, T. R. Gadekallu, A. Al-Rasheed, M. Abbas, and B. O. Soufiene, “An adaptive DeepLabv3+ for semantic segmentation of aerial images using improved golden eagle optimization algorithm,” IEEE Access, 2023, Accessed: Aug. 11, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10261990/
[21] Y. Wang, C. Wang, H. Wu, and P. Chen, “An improved Deeplabv3+ semantic segmentation algorithm with multiple loss constraints,” PLOS ONE.
[22] N. Siddique, “Estimation of Road Boundary for Intelligent Vehicles Based on DeepLabV3+ Architecture,” vol. 9, 2021.
[23] C. Cai, J. Tan, P. Zhang, Y. Ye, and J. Zhang, “Determining Strawberries’ Varying Maturity Levels by Utilizing Image Segmentation Methods of Improved DeepLabV3+,” Agronomy, vol. 12, no. 8, p. 1875, Aug. 2022, doi: 10.3390/agronomy12081875.
[24] Y. Gong, G. Liu, Y. Xue, R. Li, and L. Meng, “A survey on dataset quality in machine learning,” Inf. Softw. Technol., vol. 162, p. 107268, 2023, Accessed: Aug. 11, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0950584923001222
[25] A. W. Salehi et al., “A study of CNN and transfer learning in medical imaging: Advantages, challenges, future scope,” Sustainability, vol. 15, no. 7, p. 5930, 2023, Accessed: Aug. 11, 2024. [Online]. Available: https://www.mdpi.com/2071-1050/15/7/5930
[26] M. Muntean and F.-D. Militaru, “Metrics for Evaluating Classification Algorithms,” in Education, Research and Business Technologies, vol. 321, C. Ciurea, P. Pocatilu, and F. G. Filip, Eds., in Smart Innovation, Systems and Technologies, vol. 321. , Singapore: Springer Nature Singapore, 2023, pp. 307–317. doi: 10.1007/978-981-19-6755-9_24.
[27] M. Melinda et al., “Image Segmentation Performance using Deeplabv3+ with Resnet-50 on Autism Facial Classification,” J. INFOTEL, vol. 16, no. 2, Art. no. 2, May 2024, doi: 10.20895/infotel.v16i2.1144.
[28] C. Sahaya Pushpa Sarmila Star, T. M. Inbamalar, and A. Milton, “Automatic semantic segmentation of breast cancer in DCE-MRI using DeepLabV3+ with modified ResNet50,” Biomed. Signal Process. Control, vol. 99, p. 106691, Jan. 2025, doi: 10.1016/j.bspc.2024.106691.
[29] D. Xiangwu, L. Song, Q. Long, and Y. Shuting, “Method study on semantic segmentation of weeds at seedling stage in paddy fields based on DeepLabV3+ model,” J. Chin. Agric. Mech., vol. 44, no. 4, p. 174, Apr. 2023, doi: 10.13733/j.jcam.issn.2095-5553.2023.04.024.
[30] H. Polat, “A modified DeepLabV3+ based semantic segmentation of chest computed tomography images for COVID-19 lung infections,” Int. J. Imaging Syst. Technol., vol. 32, no. 5, pp. 1481–1495, 2022, doi: 10.1002/ima.22772.
[31] R. Preethi, R. Sudharsan, P. Swetha, C. Rajasekaran, and S. Kausalya, “Deep Learning-Based Semantic Segmentation of Turmeric Crop Images Using the DeepLabV3+ Architecture,” in 2024 2nd International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA), IEEE, 2024, pp. 1–6. Accessed: Nov. 28, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10531416/
[32] J. Fu, X. Yi, G. Wang, L. Mo, P. Wu, and K. E. Kapula, “Research on ground object classification method of high resolution remote-sensing images based on improved DeeplabV3+,” Sensors, vol. 22, no. 19, p. 7477, 2022, Accessed: Aug. 10, 2024. [Online]. Available: https://www.mdpi.com/1424-8220/22/19/7477
[33] C. S. P. S. Star, T. M. Inbamalar, and A. Milton, “Automatic semantic segmentation of breast cancer in DCE-MRI using DeepLabV3+ with modified ResNet50,” Biomed. Signal Process. Control, vol. 99, p. 106691, 2025, Accessed: Nov. 05, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1746809424007493
[2] S. K. Zhou et al., “A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises,” Proc. IEEE, vol. 109, no. 5, pp. 820–838, 2021, Accessed: Aug. 10, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9363915/
[3] Y. Yunidar, R. Roslidar, M. Oktiana, Y. Yusni, N. Nasaruddin, and F. Arnia, “Classification of stunted and normal children using novel facial image database and convolutional neural network,” Radioelectron. Comput. Syst., vol. 2024, no. 1, pp. 76–86, 2024, Accessed: Jul. 17, 2024. [Online]. Available: https://nti.khai.edu/ojs/index.php/reks/article/view/reks.2024.1.07
[4] Y. Liu, X. Bai, J. Wang, G. Li, J. Li, and Z. Lv, “Image semantic segmentation approach based on DeepLabV3 plus network with an attention mechanism,” Eng. Appl. Artif. Intell., vol. 127, p. 107260, 2024, Accessed: Aug. 10, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0952197623014446
[5] В. М. Рувінська and Ю. Ю. Тімков, “Deep learning technology for videoframe processing in face segmentation on mobile devices,” Вісник Сучасних Інформаційних Технологій, vol. 4, no. 2, pp. 185–194, 2021, Accessed: Aug. 10, 2024. [Online]. Available: https://hait.od.ua/index.php/journal/article/view/109
[6] S. Patel, “Deep learning models for image segmentation,” in 2021 8th International conference on computing for sustainable global development (INDIACom), IEEE, 2021, pp. 149–154. Accessed: Aug. 10, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9441388/
[7] A. Y. Agyeman and S. G. Tetteh, “Technical Evaluation of Machine Learning Models: An Empirical Study,” ESP Int. J. Adv. Comput. Technol. ESP-IJACT, vol. 2, no. 1, pp. 1–9, Jan. 2024, Accessed: Nov. 05, 2024. [Online]. Available: https://www.espjournals.org/IJACT/ijact-v2i1p101
[8] Z. H. U. Runhu, X. I. N. Binjie, D. Na, and F. A. N. Mingzhu, “Semantic segmentation using deeplabv3+ model for fabric defect detection,” Wuhan Univ. J. Nat. Sci., vol. 27, no. 6, pp. 539–549, 2022, Accessed: Aug. 10, 2024. [Online]. Available: https://wujns.edpsciences.org/articles/wujns/abs/2022/06/wujns-1007-1202-2022-06-0539-11/wujns-1007-1202-2022-06-0539-11.html
[9] H. Polat, “A modified DEEPLABV3 + based semantic segmentation of chest computed tomography images for COVID ‐19 lung infections,” Int. J. Imaging Syst. Technol., vol. 32, no. 5, pp. 1481–1495, Sep. 2022, doi: 10.1002/ima.22772.
[10] S. O. Atik, M. E. Atik, and C. Ipbuker, “Comparative research on different backbone architectures of DeepLabV3+ for building segmentation,” J. Appl. Remote Sens., vol. 16, no. 2, pp. 024510–024510, 2022, Accessed: Nov. 05, 2024. [Online]. Available: https://www.spiedigitallibrary.org/journals/journal-of-applied-remote-sensing/volume-16/issue-2/024510/Comparative-research-on-different-backbone-architectures-of-DeepLabV3-for-building/10.1117/1.JRS.16.024510.short
[11] H. Polat, “Multi-task semantic segmentation of CT images for COVID-19 infections using DeepLabV3+ based on dilated residual network,” Phys. Eng. Sci. Med., vol. 45, no. 2, pp. 443–455, Jun. 2022, doi: 10.1007/s13246-022-01110-w.
[12] M. A. Butt and F. Riaz, “CARL-D: A vision benchmark suite and large scale dataset for vehicle detection and scene segmentation,” Signal Process. Image Commun., vol. 104, p. 116667, 2022, Accessed: Aug. 11, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0923596522000224
[13] M. Cai et al., “Image segmentation method for sweetgum leaf spots based on an improved DeeplabV3+ network,” Forests, vol. 13, no. 12, p. 2095, 2022, Accessed: Aug. 11, 2024. [Online]. Available: https://www.mdpi.com/1999-4907/13/12/2095
[14] T. Ashine, “Image-Based Rose Leaf Diseases Detection Using Deep Learning,” Thesis, St. Mary’s University, 2024. Accessed: Aug. 11, 2024. [Online]. Available: https://repository.smuc.edu.et/handle/123456789/7886
[15] B. Li and D. Lima, “Facial expression recognition via ResNet-50,” Int. J. Cogn. Comput. Eng., vol. 2, pp. 57–64, 2021, Accessed: Aug. 11, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2666307421000073
[16] G. Singh, A. Mittal, and N. Aggarwal, “ResDNN: deep residual learning for natural image denoising,” IET Image Process., vol. 14, no. 11, pp. 2425–2434, Sep. 2020, doi: 10.1049/iet-ipr.2019.0623.
[17] A. Amelio et al., “Representation and compression of Residual Neural Networks through a multilayer network based approach,” Expert Syst. Appl., vol. 215, p. 119391, 2023, Accessed: Aug. 11, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0957417422024095
[18] H. Tahir, M. S. Khan, and M. O. Tariq, “Performance analysis and comparison of faster R-CNN, mask R-CNN and ResNet50 for the detection and counting of vehicles,” in 2021 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), IEEE, 2021, pp. 587–594. Accessed: Aug. 11, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9397079/
[19] M. M. Murimi, “Identification Of Maize Leaf Diseases Using Support Vector Machine And Convolutional Neural Networks Alexnet And Resnet50,” Phd Thesis, Karatina University, 2023. Accessed: Jul. 16, 2024. [Online]. Available: https://karuspace.karu.ac.ke/bitstream/handle/20.500.12092/2999/FULLTEXT.pdf?sequence=1
[20] P. Venugopal, P. K. R. Maddikunta, T. R. Gadekallu, A. Al-Rasheed, M. Abbas, and B. O. Soufiene, “An adaptive DeepLabv3+ for semantic segmentation of aerial images using improved golden eagle optimization algorithm,” IEEE Access, 2023, Accessed: Aug. 11, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10261990/
[21] Y. Wang, C. Wang, H. Wu, and P. Chen, “An improved Deeplabv3+ semantic segmentation algorithm with multiple loss constraints,” PLOS ONE.
[22] N. Siddique, “Estimation of Road Boundary for Intelligent Vehicles Based on DeepLabV3+ Architecture,” vol. 9, 2021.
[23] C. Cai, J. Tan, P. Zhang, Y. Ye, and J. Zhang, “Determining Strawberries’ Varying Maturity Levels by Utilizing Image Segmentation Methods of Improved DeepLabV3+,” Agronomy, vol. 12, no. 8, p. 1875, Aug. 2022, doi: 10.3390/agronomy12081875.
[24] Y. Gong, G. Liu, Y. Xue, R. Li, and L. Meng, “A survey on dataset quality in machine learning,” Inf. Softw. Technol., vol. 162, p. 107268, 2023, Accessed: Aug. 11, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0950584923001222
[25] A. W. Salehi et al., “A study of CNN and transfer learning in medical imaging: Advantages, challenges, future scope,” Sustainability, vol. 15, no. 7, p. 5930, 2023, Accessed: Aug. 11, 2024. [Online]. Available: https://www.mdpi.com/2071-1050/15/7/5930
[26] M. Muntean and F.-D. Militaru, “Metrics for Evaluating Classification Algorithms,” in Education, Research and Business Technologies, vol. 321, C. Ciurea, P. Pocatilu, and F. G. Filip, Eds., in Smart Innovation, Systems and Technologies, vol. 321. , Singapore: Springer Nature Singapore, 2023, pp. 307–317. doi: 10.1007/978-981-19-6755-9_24.
[27] M. Melinda et al., “Image Segmentation Performance using Deeplabv3+ with Resnet-50 on Autism Facial Classification,” J. INFOTEL, vol. 16, no. 2, Art. no. 2, May 2024, doi: 10.20895/infotel.v16i2.1144.
[28] C. Sahaya Pushpa Sarmila Star, T. M. Inbamalar, and A. Milton, “Automatic semantic segmentation of breast cancer in DCE-MRI using DeepLabV3+ with modified ResNet50,” Biomed. Signal Process. Control, vol. 99, p. 106691, Jan. 2025, doi: 10.1016/j.bspc.2024.106691.
[29] D. Xiangwu, L. Song, Q. Long, and Y. Shuting, “Method study on semantic segmentation of weeds at seedling stage in paddy fields based on DeepLabV3+ model,” J. Chin. Agric. Mech., vol. 44, no. 4, p. 174, Apr. 2023, doi: 10.13733/j.jcam.issn.2095-5553.2023.04.024.
[30] H. Polat, “A modified DeepLabV3+ based semantic segmentation of chest computed tomography images for COVID-19 lung infections,” Int. J. Imaging Syst. Technol., vol. 32, no. 5, pp. 1481–1495, 2022, doi: 10.1002/ima.22772.
[31] R. Preethi, R. Sudharsan, P. Swetha, C. Rajasekaran, and S. Kausalya, “Deep Learning-Based Semantic Segmentation of Turmeric Crop Images Using the DeepLabV3+ Architecture,” in 2024 2nd International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA), IEEE, 2024, pp. 1–6. Accessed: Nov. 28, 2024. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/10531416/
[32] J. Fu, X. Yi, G. Wang, L. Mo, P. Wu, and K. E. Kapula, “Research on ground object classification method of high resolution remote-sensing images based on improved DeeplabV3+,” Sensors, vol. 22, no. 19, p. 7477, 2022, Accessed: Aug. 10, 2024. [Online]. Available: https://www.mdpi.com/1424-8220/22/19/7477
[33] C. S. P. S. Star, T. M. Inbamalar, and A. Milton, “Automatic semantic segmentation of breast cancer in DCE-MRI using DeepLabV3+ with modified ResNet50,” Biomed. Signal Process. Control, vol. 99, p. 106691, 2025, Accessed: Nov. 05, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1746809424007493
##plugins.themes.bootstrap3.article.sidebar##
Published
Nov 30, 2024
##plugins.themes.bootstrap3.article.details##
How to Cite
Yunidar, Y., Melinda, M., & Irhamsyah, M. (2024). Object Segmentation in Stunted Face Images using Deeplabv3+ with Resnet-50. Jurnal Nasional Teknik Elektro, 13(3), 137–143. https://doi.org/10.25077/jnte.v13n3.1253.2024
Section
Telecommunication
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
The authors declare that:
1. This paper has not been published in the same form elsewhere.
2. It will not be submitted anywhere else for publication prior to acceptance/rejection by this Journal.
3. A copyright permission is obtained for materials published elsewhere and which require this permission for reproduction.