COMPARATIVE EVALUATION OF GRADIENT OPERATORS WITH OTSU THRESHOLDING FOR MICROSCOPIC POROSITY DETECTION
Abstract
This study demonstrates the comparison of five well-known gradient operators —Sobel, Prewitt, Roberts, Scharr, and Laplacian of Gaussian (LoG)—using the classical technique of Otsu thresholding to detect microscopic porosities in SMAW welds of ship structures. This was done using 33 images of micrographs taken at 25x magnification, with all images preprocessed using standardization techniques (grayscale conversion, Gaussian filtering, and normalization), and the results were compared using six different performance evaluation criteria —Precision, Recall, F-Measure, Peak Signal-to-Noise Ratio (PSNR), Edge Co-occurrence Matrix (ECM), and Matthews Correlation Coefficient (MCC). The results indicate that the Sobel operator produced the largest PSNR value (≈42.5 dB) indicating that the Sobel operator provided the greatest fidelity in image quality. Additionally, the Scharr operator had the largest MCC (0.94) and ECM correlation (0.99), indicating that it provided the greatest reliability and coherence in texture. The Roberts operator produced the largest F-measure (0.23), indicating that it provided a good balance between the two evaluation metrics. In summary, the Scharr operator demonstrated the most consistent and interpretable performance among the three performance evaluation metrics, providing both the best visual fidelity and structural texture stability. Therefore, the proposed methodology represents a reproducible and computationally-efficient reference for automated microscopic inspections and smart NDT in maritime welding applications.
Keywords
Full Text:
PDFReferences
V. Crupi, G. Epasto, E. Guglielmino, and A. Marinò, “Influence of weld-porosity defects on fatigue strength of AH36 butt joints used in ship structures,” Metals, vol. 11, no. 3, p. 444, 2021. [Google Scholar]
Z. Guo, X. Liu, X. Rao, and C. Yuan, “Effect of defects on the structural integrity of ship piping welds under simulated piping conditions,” Ocean Engineering, vol. 308, p. 118372, 2024. [Google Scholar]
M. Jung and R. Fenzl, “Influence of pores on the fatigue life of welded joints and investigation of acceptance criteria defined in standard documents,” Welding in the World, vol. 69, no. 3, pp. 671–686, 2025. [Google Scholar]
M. Orlando, M. De Maddis, V. Razza, and V. Lunetto, “Non-destructive detection and analysis of weld defects in dissimilar pulsed GMAW and FSW joints of aluminium castings and plates through 3D X-ray computed tomography,” The International Journal of Advanced Manufacturing Technology, vol. 132, no. 5, pp. 2957–2970, 2024. [Google Scholar]
J. C. Garcia-Guerrero, F. F. Curiel-López, V. H. López-Morelos, J. J. Taha-Tijerina, T. J. Sánchez-Cruz, M. D. C. Ramirez-Lopez, and M. A. Quinones-Salinas, "Impact of welding parameters in the porosity of a dissimilar welded lap joint of CP800-XPF1000 steel weldment by GMAW-P," Metals, vol. 14, no. 3, p. 309, 2024. [Google Scholar]
V. K. Gaidhane and S. R. Kolhe, “A Review on Advances in Computer Aided Weld Defects Detection,” in Proceedings of the 2024 International Conference on Electronics, Computing, Communication and Control Technology (ICECCC), IEEE, 2024, pp. 1–5. [Google Scholar
L. Liu, Z. Liu, A. Hou, X. Qian, and H. Wang, “Adaptive edge detection of rebar thread head image based on improved Canny operator,” IET Image Processing, vol. 18, no. 5, pp. 1145–1160, 2024. [Google Scholar]
J. Saydazimov, S. Ergashev, and A. Nosirkulov, "Research of Some Image Filter Algorithms Used in Object Detection," Proceedings of the 8th International Conference on Future Networks & Distributed Systems, pp. 781–785, 2024. [Google Scholar]
W. Zhang, W. Liu, W. Yu, D. Kang, Z. Xiong, X. Lv, and Y. Li, "Deep learning-based automated detection of welding defects in pressure pipeline radiograph," Coatings, vol. 15, no. 7, p. 808, 2025. [Google Scholar]
N. Thi Hoa, T. Ha Minh Quan, and Q. B. Diep, "Weld-CNN: Advancing non-destructive testing with a hybrid deep learning model for weld defect detection," Advances in Mechanical Engineering, vol. 17, no. 5, p. 16878132251341615, 2025. [Google Scholar]
H. Wicaksono, “Comparative analysis of gradient operators in Canny edge detection for Bacillus sp. microscopic imaging,” JTT (Jurnal Teknologi Terpadu), vol. 13, no. 1, pp. 77–93, 2025. [Google Scholar]
H. Wicaksono, A. Alamsyah, S. Suardi, and M. M. Mulki, “Dataset gambar mikroskopik pada pola visual hasil pengelasan SMAW pada struktur kapal dengan kategori porositas (Porosity),” Hak Cipta No. 000918677, Kementerian Hukum dan Hak Asasi Manusia Republik Indonesia, Balikpapan, 2025. [Online]. Available: https://pdki-indonesia.dgip.go.id/detail/e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855
V. Maksimovic, B. Jaksic, M. Milosevic, J. Todorovic, and L. Mosurovic, “Comparative analysis of edge detection operators using a threshold estimation approach on medical noisy images with different complexities,” Sensors, vol. 25, no. 1, p. 87, 2024. [Google Scholar]
R. Sun, T. Lei, Q. Chen, Z. Wang, X. Du, W. Zhao, and A. K. Nandi, “Survey of image edge detection,” Frontiers in Signal Processing, vol. 2, p. 826967, 2022. [Google Scholar]
D. E. Elgezouli and A. B. M. Alzahrani, “Optimizing edge detection efficiency with a Grünwald–Letnikov fractional network,” Electronics, vol. 13, no. 16, p. 3298, 2024. [Google Scholar]
C. Yu, W. Wu, J. Zheng, W. Zeng, D. Zheng, Z. Li, and S. Wang, “A multi-stage adaptive Otsu thresholding algorithm for pore segmentation in rock thin-section images,” Earth Science Informatics, vol. 18, no. 2, pp. 1–15, 2025. [Google Scholar]
H. Li and K. Xu, “Innovative adaptive edge detection for noisy images using wavelet and Gaussian method,” Scientific Reports, vol. 15, no. 1, p. 5838, 2025. [Google Scholar]
S. Singh, N. Mittal, H. Singh, and D. Oliva, “Improving the segmentation of digital images by using a modified Otsu’s between-class variance,” Multimedia Tools and Applications, vol. 82, no. 26, pp. 40701–40743, 2023. [Google Scholar]
G. Ma, L. Yu, H. Yuan, W. Xiao, and Y. He, “A vision-based method for lap weld defects monitoring of galvanized steel sheets using convolutional neural network,” Journal of Manufacturing Processes, vol. 64, pp. 130–139, 2021. [Google Scholar]
S. I. Wahidi, S. Oterkus, and E. Oterkus, “Robotic welding techniques in marine structures and production processes: A systematic literature review,” Marine Structures, vol. 95, p. 103608, 2024. [Google Scholar]
P. Liao and L. Guixiong, “Pressure vessel-oriented visual inspection method based on deep learning,” PLOS ONE, vol. 17, no. 5, e0267743, 2022. [Google Scholar]
M. Gouda, M. Abu-hashim, A. Nassrallah, M. N. Khalil, E. Hendawy, F. F. Benhasher, and E. S. Mohamed, “Integration of remote sensing and artificial neural networks for prediction of soil organic carbon in arid zones,” Frontiers in Environmental Science, vol. 12, p. 1448601, 2024. [Google Scholar]
S. Kim and W.-K. Min, “Toward high-quality real-world laboratory data in the era of healthcare big data,” Annals of Laboratory Medicine, vol. 45, no. 1, pp. 1–11, 2025. [Google Scholar]
I. D. M. O. Dharmawan and J. Lee, “Integrated image processing toolset for tracking direction of metal grain deformation,” Applied Sciences, vol. 13, no. 1, p. 45, 2022. [Google Scholar]
Z. Jiao, H. Qin, X. Gao, Z. Feng, Y. Xu, S. Chen, and W. Liu, “Image processing and feature extraction for hull structure GMAW based on weld pool visual sensing,” Journal of Sensors, vol. 2023, p. 6317992, 2023. [Google Scholar]
S. Campbell, M. Greenwood, S. Prior, T. Shearer, K. Walkem, S. Young, and K. Walker, “Purposive sampling: complex or simple? Research case examples,” Journal of Research in Nursing, vol. 25, no. 8, pp. 652–661, 2020. [Google Scholar]
J. Goldman and J. K. Tsotsos, “Statistical challenges with dataset construction: Why you will never have enough images,” arXiv preprint arXiv:2408.11160, 2024. [Google Scholar]
N. Thi Hoa, T. Ha Minh Quan, and Q. B. Diep, “Weld-CNN: Advancing non-destructive testing with a hybrid deep learning model for weld defect detection,” Advances in Mechanical Engineering, vol. 17, no. 5, 2025. [Google Scholar]
G. L. Xu, Q. Cheng, L. X. Wei, and J. X. Mi, “Research on porosity detection method for welding X-ray images,” Journal of Network Intelligence, vol. 7, no. 3, pp. 805–817, 2022. [Google Scholar]
F. Staab, M. Prescher, F. Balle, and L. Kirste, “3D X-ray microscopy of ultrasonically welded aluminum/fiber-reinforced polymer hybrid joints,” Materials, vol. 14, no. 7, p. 1784, 2021. [Google Scholar]
D. Das, S. K. Dinda, A. K. Das, D. K. Pratihar, and G. G. Roy, “Study of micro-porosity in electron beam butt welding,” The International Journal of Advanced Manufacturing Technology, vol. 121, no. 7, pp. 4583–4600, 2022. [Google Scholar]
X. Meng, M. Bachmann, F. Yang, and M. Rethmeier, “Toward prediction and insight of porosity formation in laser welding: A physics-informed deep learning framework,” Acta Materialia, vol. 286, p. 120740, 2025. [Google Scholar]
H. Li, X. Peng, B. Wang, F. Shi, Y. Xia, S. Li, and S. Li, “Automated detection of micro-scale porosity defects in reflective metal parts via deep learning and polarization imaging,” Nanomaterials, vol. 15, no. 11, p. 795, 2025. [Google Scholar]
H. Nasibov, “Evaluation of focus measures for hyperspectral imaging microscopy using principal component analysis,” Journal of Imaging, vol. 10, no. 10, p. 240, 2024. [Google Scholar]
O. Turk, E. Acar, E. Irmak, M. Yilmaz, and E. Bakis, “A hybrid 2D Gaussian filter and deep learning approach with visualization of class activation for automatic lung and colon cancer diagnosis,” Technology in Cancer Research & Treatment, vol. 23, p. 15330338241301297, 2024. [Google Scholar]
S. Salwig, J. Drefs, and J. Lücke, “Zero-shot denoising of microscopy images recorded at high-resolution limits,” PLOS Computational Biology, vol. 20, no. 6, p. e1012192, 2024. [Google Scholar]
A. K. Kakumani and L. P. Sree, “Image enhancement with deep learning and intensity transformation of no-reference grayscale fluorescence microscopy images,” in Proceedings of the International Conference on Recent Innovations in Computing, Singapore: Springer Nature, pp. 401–410, 2022. [Google Scholar]
H. Govindaraju, M. N. Tahir, and U. Hassan, “HIST-DIP: histogram thresholding and deep image priors assisted smartphone-based fluorescence microscopy imaging,” Analyst, vol. 150, no. 17, pp. 3909–3917, 2025. [Google Scholar]
D. Tang, Y. Xu, and X. Liu, “Application of an improved Laplacian-of-Gaussian filter for bearing fault signal enhancement of motors,” Machines, vol. 12, no. 6, p. 389, 2024. [Google Scholar]
J. E. Alcaraz-Chavez, A. C. Téllez-Anguiano, J. C. Olivares-Rojas, G. M. Chávez-Campos, and J. Alcaraz-Chavez, “Laplacian of Gaussian for fast cell detection and segmentation in cervical cytology to help in cancer diagnosis,” Cureus, vol. 17, no. 2, 2025. [Google Scholar]
Y. Li, L. Jin, M. Liu, Y. Mo, W. Zheng, D. Ge, and Y. Bai, “Research on adaptive edge detection method of part images using selective processing,” Processes, vol. 12, no. 10, p. 2271, 2024. [Google Scholar]
B. Li, S. Song, and L. Ai, “Rethinking the Non-Maximum Suppression Step in 3D Object Detection from a Bird’s-Eye View,” Electronics, vol. 13, no. 20, p. 4034, 2024. [Google Scholar]
X. Yang and C. Li, “A new edge detection method for noisy image based on discrete fractional wavelet transform and improved Canny algorithm,” Expert Systems with Applications, p. 129668, 2025. [Google Scholar]
T. Huang, H. Yin, and X. Huang, “Improved genetic algorithm for multi-threshold optimization in digital pathology image segmentation,” Scientific Reports, vol. 14, no. 1, p. 22454, 2024. [Google Scholar]
A. Yadav, V. Bhateja, D. Singh, and B. K. Chauhan, “Segmentation of microscopy images using guided filter and Otsu thresholding,” in Evolution in Signal Processing and Telecommunication Networks: Proceedings of Sixth International Conference on Microelectronics, Electromagnetics and Telecommunications (ICMEET 2021), vol. 2, Singapore: Springer, 2022, pp. 233–239. [Google Scholar]
L. Hu, L. Hu, and M. Chen, “Edge-enhanced infrared image super-resolution reconstruction model under transformer,” Scientific Reports, vol. 14, no. 1, p. 15585, 2024. [Google Scholar]
A. R. Zubair and O. A. Alo, “Grey level co-occurrence matrix (GLCM) based second-order statistics for image texture analysis,” arXiv preprint arXiv:2403.04038, 2024. [Google Scholar]
A. K. Pritoonka and F. Kiani, “Texture image analysis based on joint of multi-directions GLCM and local ternary patterns,” arXiv preprint, arXiv:2209.01866, 2022. [Google Scholar]
D. Bermejo-Peláez, S. Rueda Charro, M. García Roa, R. Trelles-Martínez, A. Bobes-Fernández, M. Hidalgo Soto, and M. Luengo-Oroz, “Digital microscopy augmented by artificial intelligence to interpret bone marrow samples for hematological diseases,” Microscopy and Microanalysis, vol. 30, no. 1, pp. 151–159, 2024. [Google Scholar]
A. Bilodeau, A. Michaud-Gagnon, J. Chabbert, B. Turcotte, J. Heine, A. Durand, and F. Lavoie-Cardinal, “Development of AI-assisted microscopy frameworks through realistic simulation with pySTED,” Nature Machine Intelligence, vol. 6, no. 10, pp. 1197–1215, 2024. [Google Scholar]
F. Rehn, M. Pils, T. Bujnicki, O. Bannach, and D. Willbold, “Artifact detection in fluorescence microscopy using convolutional autoencoder,” Scientific Reports, vol. 15, no. 1, p. 32482, 2025. [Google Scholar]
A. Keikhosravi, F. Almansour, C. H. Bohrer, N. A. Fursova, K. Guin, V. Sood, and G. Pegoraro, “High-throughput image processing software for the study of nuclear architecture and gene expression,” Scientific Reports, vol. 14, no. 1, p. 18426, 2024. [Google Scholar]
N. Driver, A. Mikheykin, S. Kobley, M. Mostashari, L. Picco, S. Berger, and J. Reed, “Computer vision techniques for high-speed atomic force microscopy of DNA molecules,” Nanotechnology, 2025. [Google Scholar]
H. K. Chau, C. H. Yang, T. C. Yang, and W. C. Lee, “Developing an easy-to-use image-based system for offline tool-wear detection,” Journal of Engineering Research, 2024. [Google Scholar]
H. Adrian, B. Björn-Ivo, S. Sebastian, and M. Frank, “An automated machine learning-based approach for a reproducible and efficient evaluation of industrial Charpy V-notch specimens,” Materials & Design, p. 114424, 2025. [Google Scholar]
J. von Bahr, V. Diwan, A. Mårtensson, N. Linder, and J. Lundin, “AI-supported digital microscopy diagnostics in primary health care laboratories: Protocol for a scoping review,” JMIR Research Protocols, vol. 13, no. 1, e58149, 2024. [Google Scholar]
C. Qiao, Y. Zeng, Q. Meng, X. Chen, H. Chen, T. Jiang, and Q. Dai, “Zero-shot learning enables instant denoising and super-resolution in optical fluorescence microscopy,” Nature Communications, vol. 15, no. 1, p. 4180, 2024. [Google Scholar]
D. Hou, D. Bian, Z. Luo, Y. Luo, W. Jiang, and L. Yang, “A lightweight super-resolution reconstruction method for phase contrast interferometric microscopy images,” Optics Communications, p. 132050, 2025. [Google Scholar]
F. Rehn, M. Pils, T. Bujnicki, O. Bannach, and D. Willbold, “Artifact detection in fluorescence microscopy using convolutional autoencoder,” Scientific Reports, vol. 15, no. 1, p. 32482, 2025. [Google Scholar]
F. Schwarzhans, G. George, L. E. Sanchez, O. Zaric, J. E. Abraham, R. Woitek, and S. Hatamikia, “Image normalization techniques and their effect on the robustness and predictive power of breast MRI radiomics,” European Journal of Radiology, vol. 187, p. 112086, 2025. [Google Scholar]
R. Y. Yan and D. Q. Zhang, “Edge detection based on channel attention and inter-region independence test,” arXiv preprint, arXiv:2505.01040, 2025. [Google Scholar]
K. S. Si, L. Sun, W. Zhang, T. Gong, J. Wang, J. Liu, and H. Sun, “Accelerating non-maximum suppression: A graph theory perspective,” Advances in Neural Information Processing Systems, vol. 37, pp. 121992–122028, 2024. [Google Scholar]
H. Li and K. Xu, “Innovative adaptive edge detection for noisy images using wavelet and Gaussian method,” Scientific Reports, vol. 15, no. 1, p. 5838, 2025. [Google Scholar]
R. Yan and D. Q. Zhang, “Edge-preserving image denoising via multi-scale adaptive statistical independence testing,” arXiv preprint, arXiv:2505.01032, 2025. [Google Scholar]
J. Jing, S. Liu, G. Wang, W. Zhang, and C. Sun, “Recent advances on image edge detection: A comprehensive review,” Neurocomputing, vol. 503, pp. 259–271, 2022. [Google Scholar]
N. Tariq, R. A. Hamzah, T. F. Ng, S. L. Wang, and H. Ibrahim, “Quality assessment methods to evaluate the performance of edge detection algorithms for digital image: A systematic literature review,” IEEE Access, vol. 9, pp. 87763–87776, 2021. [Google Scholar]
D. Li, P. C. I. Pang, and C. K. Lam, “Contrast-invariant edge detection: A methodological advance in medical image analysis,” Applied Sciences, vol. 15, no. 2, p. 963, 2025. [Google Scholar]
Y. Du, B. Liu, H. Chen, and Y. Fu, “Label-free microscopic cell images adaptive enhancement via weighted fusion of bright, dark, and weak structure features,” Biomedical Signal Processing and Control, vol. 91, p. 105973, 2024. [Google Scholar]
J. Chen, J. Xu, J. Gu, B. Chen, H. Zhang, H. Qian, and G. Han, “Low-power edge detection based on ferroelectric field-effect transistor,” Nature Communications, vol. 16, no. 1, p. 565, 2025. [Google Scholar]
R. Barker-Clarke, D. T. Weaver, and J. G. Scott, “Graph ‘texture’ features as novel metrics that can summarize complex biological graphs,” Physics in Medicine & Biology, vol. 68, no. 17, p. 174001, 2023. [Google Scholar]
M. Rusanovsky, O. Beeri, and G. Oren, “An end-to-end computer vision methodology for quantitative metallography,” Scientific Reports, vol. 12, no. 1, p. 4776, 2022. [Google Scholar]
B. A. Varghese, B. K. Fields, D. H. Hwang, V. A. Duddalwar, G. R. Matcuk Jr., and S. Y. Cen, “Spatial assessments in texture analysis: what the radiologist needs to know,” Frontiers in Radiology, vol. 3, p. 1240544, 2023. [Google Scholar]
P. Sferrazza, “Grey level co-occurrence matrix and learning algorithms to quantify and classify use-wear on experimental flint tools,” Journal of Archaeological Science: Reports, vol. 48, p. 103869, 2023. [Google Scholar]
A. Makandar, S. Kaman, R. Biradar, and S. B. Javeriya, “Impact of edge detection algorithms on different types of images using PSNR and MSE,” LC International Journal of STEM (ISSN: 2708-7123), vol. 3, no. 4, pp. 1–11, 2022. [Google Scholar]
R. Yan and D.-Q. Zhang, “Edge-preserving image denoising via multi-scale adaptive statistical independence testing,” arXiv preprint arXiv:2505.01032, 2025. [Google Scholar]
C. O’Sullivan, S. Coveney, X. Monteys, and S. Dev, “The effectiveness of edge detection evaluation metrics for automated coastline detection,” in Proceedings of the 2023 Photonics & Electromagnetics Research Symposium (PIERS), pp. 31–40, IEEE, 2023. [Google Scholar]
S. Mathur and S. Gupta, “An enhanced edge detection using Laplacian Gaussian filtering method from different denoising images,” International Journal of Intelligent Systems and Applied Engineering, vol. 12, no. 18s, pp. 313–323, 2024. [Google Scholar]
R. Y. Yan and D.-Q. Zhang, “Edge detection based on channel attention and inter-region independence test,” arXiv preprint arXiv:2505.01040, 2025. [Google Scholar]
V. Maksimović, B. Jaksic, M. Milosevic, J. Todorovic, and L. Mosurovic, “Comparative analysis of edge detection operators using a threshold estimation approach on medical noisy images with different complexities,” Sensors, vol. 25, no. 1, p. 87, 2024. [Google Scholar]
R. Tang, S. Guo, K. Wang, H. Lin, L. Huang, and G. Mou, “A framework of insole blanking robot based on adaptive edge detection and FSPS-BIT* path planning,” Scientific Reports, vol. 14, no. 1, p. 20791, 2024. [Google Scholar]
K. Muntarina, R. Mostafiz, F. Khanom, S. B. Shorif, and M. S. Uddin, “MultiResEdge: A deep learning-based edge detection approach,” Intelligent Systems with Applications, vol. 20, p. 200274, 2023. [Google Scholar]
G. Hu, “A mathematical survey of image deep edge detection algorithms: From convolution to attention,” Mathematics, vol. 13, no. 15, p. 2464, 2025. [Google Scholar]
H. Wang, P. Liu, Q. Dou, Y. Song, M. Luo, R. Han, and B. Zhang, “Enhanced edge detection via dual-branch attention fusion with Canny-assisted supervision: H. Wang et al.,” The Visual Computer, pp. 1–16, 2025. [Google Scholar]
DOI: https://doi.org/10.32487/jtt.v14i1.3004
Refbacks
- There are currently no refbacks.
JTT (Jurnal Teknologi Terpadu) has been indexed by:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
