(Politeknik Perkapalan Negeri Surabaya, Indonesia)(2) Oskar Natan
(Universitas Gadjah Mada, Indonesia)(3) Yohanes Yohanie Fridelin Panduman
(The University of Osaka, Japan)(4) Anggarjuna Puncak Pujiputra
(Politeknik Perkapalan Negeri Surabaya, Indonesia)*corresponding author
AbstractWelding inspection plays an essential role in manufacturing industries to ensure the integrity and quality of weld joints. However, the prevalent manual inspection procedures are inherently subjective, prone to bias, and result in inconsistent quality assessments. Therefore, there is a strong need for an automated, intelligent system capable of objectively detecting welding spots. To address this, we propose an advanced segmentation model based on deep learning and computer vision techniques, specifically utilizing a Nested UNet (UNet++) architecture enhanced by extensive architectural modifications and comprehensive hyperparameter tuning. To further optimize segmentation performance, we systematically compare various convolutional blocks integrated into the bottleneck of the network architecture. Our experimental evaluation demonstrates that employing a VGG convolutional block at the bottleneck of Nested UNet achieves the highest performance, reaching an Intersection over Union (IoU) score of 76.18% and a validation loss of 0.1713 on our collected dataset. This research advances automated welding inspection by demonstrating that an enhanced Nested UNet with an optimized VGG bottleneck significantly improves weld spot segmentation accuracy. The proposed framework provides a robust benchmark for future studies on intelligent industrial visual inspection and deep learning-based quality assurance.
KeywordsCNN; Image Segmentation; Nested Unet; Welding Spot
|
DOIhttps://doi.org/10.26555/ijain.v12i2.2250 |
Article metricsAbstract views : 213 | PDF views : 8 |
Cite |
Full Text Download
|
References
[1] T. W. Purnomo, F. Danitasari, and D. Handoko, “Weld Defect Detection and Classification based on Deep Learning Method: A Review,” J. Ilmu Komput. dan Inf., vol. 16, no. 1, pp. 77–87, Mar. 2023, doi: 10.21609/jiki.v16i1.1147.
[2] R. Ghimire and R. Selvam, “Machine Learning-Based Weld Classification for Quality Monitoring,” in RAiSE-2023, Basel Switzerland: MDPI, Mar. 2024, p. 241. doi: 10.3390/engproc2023059241.
[3] S. Y. Prasetyo, G. Z. Nabiilah, Z. N. Izdihar, and S. M. Isa, “Pneumonia Detection on X-Ray Imaging using Softmax Output in Multilevel Meta Ensemble Algorithm of Deep Convolutional Neural Network Transfer Learning Models,” Int. J. Adv. Intell. Informatics, vol. 9, no. 2, p. 319, Jul. 2023, doi: 10.26555/ijain.v9i2.884.
[4] D. Palma-Ramírez et al., “Deep convolutional neural network for weld defect classification in radiographic images,” Heliyon, vol. 10, no. 9, p. e30590, May 2024, doi: 10.1016/j.heliyon.2024.e30590.
[5] M. Murinto and S. Winiarti, “Modified particle swarm optimization (MPSO) optimized CNN’s hyperparameters for classification,” Int. J. Adv. Intell. Informatics, vol. 11, no. 1, p. 133, Feb. 2025, doi: 10.26555/ijain.v11i1.1303.
[6] N. A. M. Roslan, N. M. Diah, Z. Ibrahim, Y. Munarko, and A. E. Minarno, “Automatic plant recognition using convolutional neural network on malaysian medicinal herbs: the value of data augmentation,” Int. J. Adv. Intell. Informatics, vol. 9, no. 1, p. 136, Mar. 2023, doi: 10.26555/ijain.v9i1.1076.
[7] R. Cahyaningtyas, S. Madenda, B. Bertalya, and D. Indarti, “Solar module defects classification using deep convolutional neural network,” Int. J. Adv. Intell. Informatics, vol. 11, no. 3, p. 499, Aug. 2025, doi: 10.26555/ijain.v11i3.1818.
[8] S. Surono, M. Rivaldi, D. A. Dewi, and N. Irsalinda, “New Approach to Image Segmentation: U-Net Convolutional Network for Multiresolution CT Image Lung Segmentation,” Emerg. Sci. J., vol. 7, no. 2, pp. 498–506, Feb. 2023, doi: 10.28991/ESJ-2023-07-02-014.
[9] A. Desiani et al., “Simple Data Augmentation and U-Net CNN for Neclui Binary Segmentation on Pap Smear Images,” J. Electron. Electromed. Eng. Med. Informatics, vol. 6, no. 3, pp. 264–275, Jul. 2024, doi: 10.35882/jeeemi.v6i3.442.
[10] W. Baccouch, S. Oueslati, B. Solaiman, and S. Labidi, “A comparative study of CNN and U-Net performance for automatic segmentation of medical images: application to cardiac MRI,” Procedia Comput. Sci., vol. 219, pp. 1089–1096, Jan. 2023, doi: 10.1016/j.procs.2023.01.388.
[11] O. Natan, D. U. K. Putri, and A. Dharmawan, “Deep learning-based weld spot segmentation using modified unet with various convolutional blocks,” ICIC Express Lett. Part B Appl., vol. 12, no. 12, pp. 1169–1176, Dec. 2021, Accessed: Jun. 06, 2026. [Online]. Available: https://www.researchgate.net/publication/355732437_Deep_Learning-Based_Weld_Spot_Segmentation_Using_Modified_UNet_with_Various_Convolutional_Blocks.
[12] J. Videira, P. D. Gaspar, V. N. da G. de J. Soares, and J. M. L. P. Caldeira, “Detecting and monitoring the development stages of wild flowers and plants using computer vision: approaches, challenges and opportunities,” Int. J. Adv. Intell. Informatics, vol. 9, no. 3, p. 347, Oct. 2023, doi: 10.26555/ijain.v9i3.1012.
[13] R. N. Razak and H. N. Abdullah, “Improving multi-object detection and tracking with deep learning, DeepSORT, and frame cancellation techniques,” Open Eng., vol. 14, no. 1, pp. 1–18, Sep. 2024, doi: 10.1515/eng-2024-0056.
[14] N. Shamna and B. Aziz Musthafa, “Feature Extraction Method using HoG with LTP for Content-Based Medical Image Retrieval,” Int. J. Electr. Comput. Eng. Syst., vol. 14, no. 3, pp. 267–275, Mar. 2023, doi: 10.32985/ijeces.14.3.4.
[15] D. F. Abdulabass and M. E. Abdulmunim, “Traffic Sign Detection Using You Only Look Once (YOLOv3) Technique,” Iraqi J. Sci., vol. 65, no. 10, pp. 5741–5753, Oct. 2024, doi: 10.24996/IJS.2024.65.10.34.
[16] D. Liu, D. Zhang, L. Wang, and J. Wang, “Semantic segmentation of autonomous driving scenes based on multi-scale adaptive attention mechanism,” Front. Neurosci., vol. 17, p. 1291674, Oct. 2023, doi: 10.3389/fnins.2023.1291674.
[17] S. Mhatre, A. Singh, and S. Shinde, “Enhancing Nucleus and Cytoplasm Segmentation in Cervical Cytology Using Deep Learning,” in 2024 IEEE Pune Section International Conference (PuneCon), IEEE, Dec. 2024, pp. 1–6. doi: 10.1109/PuneCon63413.2024.10895296.
[18] L. Yang, H. Wang, W. Meng, and H. Pan, “CvT-UNet: A weld pool segmentation method integrating a CNN and a transformer,” Heliyon, vol. 10, no. 15, p. e34738, Aug. 2024, doi: 10.1016/j.heliyon.2024.e34738.
[19] M. Vadduri, “DAUCD: Deep Attention U-Net for Cataract Detection Leveraging CNN Frameworks,” Int. J. Intell. Eng. Syst., vol. 18, no. 1, p. 2025, doi: 10.22266/ijies2025.0229.15.
[20] H. K. Abass, M. H. Al-Hashimi, A. S. Al-Zubaidi, and M. Al-Mukhtar, “GastroFPN: Advanced Deep Segmentation Model for Gastrointestinal Disease with Enhanced Feature Pyramid Network Decoder,” Int. J. Intell. Eng. Syst., vol. 17, no. 4, 2024, doi: 10.22266/ijies2024.0831.34.
[21] I. B. Santoso, Supriyono, and S. N. Utama, “Multi-Model of Convolutional Neural Networks for Brain Tumor Classification in Magnetic Resonance Imaging Images,” Int. J. Intell. Eng. Syst., vol. 17, no. 5, pp. 741–758, Oct. 2024, doi: 10.22266/ijies2024.1031.56.
[22] A. ANHAR and R. A. PUTRA, “Perancangan dan Implementasi Self-Checkout System pada Toko Ritel menggunakan Convolutional Neural Network (CNN),” ELKOMIKA J. Tek. Energi Elektr. Tek. Telekomun. Tek. Elektron., vol. 11, no. 2, p. 466, Apr. 2023, doi: 10.26760/elkomika.v11i2.466.
[23] S. U. Masruroh, A. Fiade, M. I. Tanggok, R. A. Putri, and L. A. Pratiwi, “Convolutional Neural Network for Colorization of Black and White Photos,” MATRIK J. Manajemen, Tek. Inform. dan Rekayasa Komput., vol. 22, no. 2, pp. 393–404, Mar. 2023, doi: 10.30812/matrik.v22i2.2652.
[24] S. Kumaresan, K. S. J. Aultrin, S. S. Kumar, and M. D. Anand, “Deep learning-based weld defect classification using VGG16 transfer learning adaptive fine-tuning,” Int. J. Interact. Des. Manuf., vol. 17, no. 6, pp. 2999–3010, Dec. 2023, doi: 10.1007/s12008-023-01327-3.
[25] V. Yadav, D. Banerjee, N. Sharma, and V. Singh, “Automated Welding Defect Recognition through Deep Learning Fusion: CNN and SVM Integration,” in 2023 4th International Conference on Intelligent Technologies (CONIT), IEEE, Jun. 2024, pp. 1–6. doi: 10.1109/CONIT61985.2024.10627403.
[26] Y. Yang, S. Dasmahapatra, and S. Mahmoodi, “ADS_UNet: A nested UNet for histopathology image segmentation,” Expert Syst. Appl., vol. 226, no. September, p. 120128, Sep. 2023, doi: 10.1016/j.eswa.2023.120128.
[27] Z. Jian et al., “An Improved Nested U-Net Network for Fluorescence In Situ Hybridization Cell Image Segmentation,” Sensors, vol. 24, no. 3, p. 928, Jan. 2024, doi: 10.3390/s24030928.
[28] C. Mathews and A. Mohamed, “Nested U-Net with Enhanced Attention Gate and Compound Loss for Semantic Segmentation of Brain Tumor from Multimodal MRI,” Int. J. Intell. Eng. Syst., vol. 15, no. 4, p. 2022, Aug. 2022, doi: 10.22266/ijies2022.0831.23.
[29] M. A. Sundaram, “Channel and Spatial Attention Aware UNet Architecture for Segmentation of Blood Vessels, Exudates and Microaneurysms in Diabetic Retinopathy,” Int. J. Intell. Eng. Syst., vol. 17, no. 2, pp. 1–16, Apr. 2024, doi: 10.22266/ijies2024.0430.01.
[30] W. Zhang, Y. Liu, Y. Feng, L. Quan, G. Zhang, and C. Zhang, “Deep-broad learning network model for precision identification and diagnosis of grape leaf diseases,” Front. Plant Sci., vol. 16, p. 1611301, Sep. 2025, doi: 10.3389/FPLS.2025.1611301/TEXT.
[31] S. Lika, Y. Pernando, and A. Kurniawan, “Lightweight Deep Learning for Object Detection on Mobile Device,” Bull. Informatics Data Sci., vol. 2, no. 2, p. 106, Nov. 2023, doi: 10.61944/bids.v2i2.82.
[32] B. K. Triwijoyo, A. Adil, and A. Anggrawan, “Convolutional Neural Network With Batch Normalization for Classification of Emotional Expressions Based on Facial Images,” MATRIK J. Manajemen, Tek. Inform. dan Rekayasa Komput., vol. 21, no. 1, pp. 197–204, Nov. 2021, doi: 10.30812/matrik.v21i1.1526.
[33] Herman et al., “A Comperative Study on Efficacy of CNN VGG-16, DenseNet121, ResNet50V2, And EfficientNetB0 in Toraja Carving Classification,” Indones. J. Data Sci., vol. 6, no. 1, pp. 123–133, Mar. 2025, doi: 10.56705/ijodas.v6i1.220.
[34] B. Tasci, M. R. Acharya, M. Baygin, S. Dogan, T. Tuncer, and S. B. Belhaouari, “InCR: Inception and concatenation residual block-based deep learning network for damaged building detection using remote sensing images,” Int. J. Appl. Earth Obs. Geoinf., vol. 123, no. September, p. 103483, Sep. 2023, doi: 10.1016/j.jag.2023.103483.
[35] K. Benali, L. Bouzar-Benlabiod, and A. McIntyre, “Squeeze and Excitation Block Based Neural Architecture Search with Randomization for CNN Construction,” in 2024 IEEE International Conference on Information Reuse and Integration for Data Science (IRI), IEEE, Aug. 2024, pp. 49–54. doi: 10.1109/IRI62200.2024.00022.
[36] M. Shafiq and Z. Gu, “Deep Residual Learning for Image Recognition: A Survey,” Appl. Sci., vol. 12, no. 18, p. 8972, Sep. 2022, doi: 10.3390/app12188972.
[37] W. W. Kusuma, R. R. Isnanto, and A. Fauzi, “Comparison Analysis of CNN Model VGG16 and DenseNet121 using TensorFlow Framework to Detect Animal Images,” J. Tek. Komput., vol. 1, no. 4, pp. 141–147, 2023, [Online]. Available: https://ejournal3.undip.ac.id/index.php/jtk/article/view/37009/28851.
[38] A. U. Ruby, Prasannavenkatesan Theerthagiri, Jeena Jacob, and Y.Vamsidhar, “Binary cross entropy with deep learning technique for Image classification,” Int. J. Adv. Trends Comput. Sci. Eng., vol. 9, no. 4, pp. 5393–5397, Aug. 2020, doi: 10.30534/ijatcse/2020/175942020.
[39] Q. Ming and X. Xiao, “Towards Accurate Medical Image Segmentation With Gradient-Optimized Dice Loss,” IEEE Signal Process. Lett., vol. 31, pp. 191–195, 2024, doi: 10.1109/LSP.2023.3329437.
[40] M. Yeung, L. Rundo, Y. Nan, E. Sala, C.-B. Schönlieb, and G. Yang, “Calibrating the Dice Loss to Handle Neural Network Overconfidence for Biomedical Image Segmentation,” J. Digit. Imaging, vol. 36, no. 2, pp. 739–752, Dec. 2022, doi: 10.1007/s10278-022-00735-3.
[41] J. Kim and H.-S. Lim, “Neural Network With Binary Cross Entropy for Antenna Selection in Massive MIMO Systems: Convolutional Neural Network Versus Fully Connected Network,” IEEE Access, vol. 11, pp. 111410–111421, 2023, doi: 10.1109/ACCESS.2023.3322679.
[42] H. Tessier, V. Gripon, M. Léonardon, M. Arzel, T. Hannagan, and D. Bertrand, “Rethinking Weight Decay for Efficient Neural Network Pruning,” J. Imaging, vol. 8, no. 3, p. 64, Mar. 2022, doi: 10.3390/jimaging8030064.
[43] M. S. Harisha, A. A. Bhosale, and M. Narender, “Deep learning-powered segmentation and classification of diabetic retinopathy for enhanced diagnostic precision,” Artif. Intell. Heal., vol. 1, no. 4, p. 30, Sep. 2024, doi: 10.36922/aih.2783.
[44] Y. Tian, Y. Zhang, and H. Zhang, “Recent Advances in Stochastic Gradient Descent in Deep Learning,” Mathematics, vol. 11, no. 3, p. 682, Jan. 2023, doi: 10.3390/math11030682.
[45] F. T. Admojo and Y. I. Sulistya, “Analisis Performa Algoritma Stochastic Gradient Descent (SGD) Dalam Mengklasifikasi Tahu Berformalin,” Indones. J. Data Sci., vol. 3, no. 1, pp. 1–8, Mar. 2022, doi: 10.56705/ijodas.v3i1.42.
[46] Y. Jiao, X. Lu, P. Wu, and J. Z. Yang, “Convergence Analysis for Over-Parameterized Deep Learning,” Commun. Comput. Phys., vol. 36, no. 1, pp. 71–103, Jul. 2024, doi: 10.4208/cicp.OA-2023-0264.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
___________________________________________________________
International Journal of Advances in Intelligent Informatics
ISSN 2442-6571 (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
andri.pranolo.id@ieee.org (publication issues)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0