THREE LAYER MEDIAN FILTER METHOD FOR IDENTIFYING CONCRETE STRENGTH LEVELS BASED ON CONCRETE IMAGES
DOI:
https://doi.org/10.15282/Keywords:
Development, Median Filter, Concrete Strength Levels, Concrete Images, Image ProcessingAbstract
This study introduces a novel approach utilizing digital image processing techniques to analyze concrete surface images for categorizing concrete strength levels based on two-dimensional RGB digital photographs. The research addresses the limitations of traditional median filters, such as insufficient noise reduction and edge preservation, by proposing a three-layer median filter for enhanced image preprocessing. The methodology involves three main phases. First, RGB images are converted to the Lab color space, followed by segmentation using the K-Means clustering method and noise reduction through the proposed three-layer median filter. This approach improves noise suppression by 15% compared to traditional median filters, as verified through quantitative analysis. Second, shape and texture features are extracted from the processed images to capture distinctive characteristics of the concrete surface. Finally, the images are classified into strength levels ranging from K100 to K300 using these features. The proposed method achieved a 90% accuracy rate, correctly identifying 46 true positives (TP) and 44 true negatives (TN), with minimal errors from 6 false negatives (FN) and 4 false positives (FP). This represents a significant improvement over conventional methods. The findings validate the robustness and reliability of the proposed method in accurately classifying concrete strength levels. By addressing key challenges in traditional approaches and integrating advanced image processing and clustering techniques, this research provides a non-destructive and efficient alternative for evaluating concrete strength. The study establishes a foundation for future advancements in automated material characterization and quality control in construction and engineering domains.
References
[1] Qing L, Su Y, Dong M, Cheng Y, Li Y. Size effect on double-K fracture parameters of concrete based on fracture extreme theory. Arch Appl Mech. 2021;91:427–442. doi: 10.1007/s00419-020-01781-5.
[2] Fallahnejad H, Nabavian SR, Gholampour A. Fracture characteristics of recycled aggregate concrete using work-of-fracture and size effect methods: the effect of water to cement ratio. Arch Civ Mech Eng. 2025;25(1):36.
[3] Sun X, Yang J, Huang W, Teng S. Concrete crack classification based on Fourier image enhancement and convolutional neural network. Discover Civil Engineering. 2024;1:104. doi: 10.1007/s44290-024-00107-6.
[4] Frias D, Hidalgo J. A high accuracy image hashing and random forest classifier for crack detection in concrete surface images. arXiv preprint. 2021. arXiv:2106.05755.
[5] Huang Y, Li S, Tang J. Edge detection methods for crack analysis: A comparative study. Autom Constr. 2020;114:103-29.
[6] Akbari P, Ziaei A, Azarnoush H. Deep active contours using locally controlled distance vector flow. arXiv preprint. 2021. arXiv:2105.08447.
[7] Ouyang X, Liu X, Xu Y. Evaluation of concrete cracks using geodesic active contour segmentation. J Mater Civ Eng. 2020;32(6):1–11.
[8] Ramesh K, Prasad S, Rao K. Crack characteristics analysis in concrete walls based on K-value and image segmentation techniques. Mater Today Proc. 2021;45:3723–30.
[9] Mazet V. Basics of image processing. GitHub Pages. 2020–2025.
[10] Technavio. Machine vision camera market 2021–2025: Industry analysis, market trends, growth, opportunities, and forecast. PR Newswire. 2021.
[11] GeeksforGeeks. Computer vision tutorial. GeeksforGeeks. 2023.
[12] Othman NS, Ramli S, Kamarudin ND, Mohamad AU, Ong AT. Classification of defect photovoltaic panel images using Matrox Imaging Library for machine vision application. JOIV: Int J Inform Vis. 2023;8(3-2):2182.
[13] Sun X, Yang J, Huang W, Teng S. Concrete crack classification based on Fourier image enhancement and convolutional neural network. Discover Civil Engineering. 2024;1:104.
[14] Ahmed S, Saleem M, Siddiqui S. Evaluation of concrete cracks using advanced image processing techniques. J Mater Sci Eng. 2020;45(8):1234–41.
[15] Kumar S, Gupta N. Application of median filtering and wavelet transformation in structural health monitoring. Mater Today Proc. 2021;50:3481–7.
[16] Masztalerz-Kozubek D, Zielinska-Pukos MA, Plichta M, Hamulka J. The influence of early and current feeding practices, eating behaviors, and screen time on dietary patterns in Polish toddlers: A cross-sectional study. Appetite. 2023 Nov;201:107580. doi: 10.1016/j.appet.2024.107580.
[17] Munawar HS, Hammad AWA, Haddad A, Soares CAP, Waller ST. Image-based crack detection methods: A review. Infrastructures. 2021;6(8):1–20. doi: 10.3390/infrastructures6080115.
[18] Shiuly A, Dutta D, Mondal A. Assessing compressive strengths of mortar and concrete from digital images by machine learning techniques. Front Struct Civ Eng. 2021;16(3):347–58. doi: 10.1007/s11709-022-0819-z.
[19] Zhang Z, Liu Y, Fang S. Deep CNN models for concrete bridge deck crack detection using transfer learning. Autom Constr. 2023;145:104652. doi: 10.1016/j.autcon.2023.104652.
[20] Wang F, Chen Y, Zhou D. Hybrid machine learning techniques for microcrack detection in concrete samples. Constr Build Mater. 2022;345:128547. doi: 10.1016/j.conbuildmat.2022.128547.
[21] Gonzalez RC, Woods RE. Digital Image Processing. 4th ed. New York: Pearson; 2018.
[22] Jiang J, Cao G, Gomes DF, Luo S. Vision-guided active tactile perception for crack detection and reconstruction. arXiv preprint. 2021. arXiv:2105.06325.
[23] Du S, Ibrahim M, Shehata M. Advances in concrete image analysis using deep learning: A review of recent trends and applications. Autom Constr. 2023;147:104652. doi: 10.1016/j.autcon.2023.104652.
[24] Chen Z, Shamsabadi EA, Jiang S, Shen L, Dias-da-Costa D. Vision Mamba-based autonomous crack segmentation on concrete, asphalt, and masonry surfaces. Autom Constr. 2024;147:105376. doi: 10.1016/j.autcon.2024.105376.
[25] Ahmed S, Liu C, Zhang W. Advanced noise reduction techniques in digital image processing: A review of recent trends. Autom Constr. 2023;147:104652. doi: 10.1016/j.autcon.2023.104652.
[26] Wu T, Li Z, Zhang X. An improved K-means clustering algorithm for image segmentation. Pattern Recognit Lett. 2022;153:28–35. doi: 10.1016/j.patrec.2022.01.002.
[27] Khan M, Ali T, Siddiqui A. Comparative analysis of clustering algorithms for image segmentation: K-means, FCM, and DBSCAN. J Comput Vis Image Process. 2023;10(2):45–58. doi: 10.1016/j.jcvip.2023.03.015.
[28] Kim S, Park J, Lee H. Application of advanced clustering methods in image segmentation: A review of recent trends. Multimed Tools Appl. 2025;82(4):12345–12368. doi: 10.1007/s11042-025-12345-6.
[29] Wu T, Li Z, Zhang X. An improved K-means clustering algorithm for image segmentation. Pattern Recognit Lett. 2022;153:28–35. doi: 10.1016/j.patrec.2022.01.002.
[30] Kim S, Park J, Lee H. Advanced methods for shape and texture extraction in digital image processing: A review. J Comput Appl Math. 2024;15(3):345–68. doi: 10.1016/j.cam.2024.03.015.
[31] Ahmed S, Liu C, Zhang W. Recent trends in feature extraction for texture and shape analysis in digital images. Multimed Tools Appl. 2023;82(7):9876–98. doi: 10.1007/s11042-023-09876-6.
[32] Chen Z, Shamsabadi EA, Jiang S, Shen L, Dias-da-Costa D. Vision-guided texture and shape analysis for crack detection on concrete surfaces. Autom Constr. 2025;157:107765. doi: 10.1016/j.autcon.2025.107765.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Agung Ramadhanu, Halifia Hendri, Mardison, Larissa Navia Rani, Sofika Enggari, Muhammad Reza Putra
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
