Comparison of the Surface Roughness of Crushed Stone from Sea and Lansot Based on GLCM and SVM
DOI:
https://doi.org/10.54065/artificial.2027Keywords:
Crushed Stone, Gray-Level Co-Occurrence Matrix, Image Classification, Support Vector Machine, Surface RoughnessAbstract
Surface roughness of crushed stone affects the adhesion between aggregates and cement paste, but its assessment is generally based on visual observation or indirect physical testing, which may vary between observers and lacks quantitative representation. This study aims to compare the surface roughness of crushed stone from Sea and Lansot, North Sulawesi, using Gray-Level Co-occurrence Matrix (GLCM) features and to evaluate the capability of Support Vector Machine (SVM) for roughness classification. The dataset consisted of 200 images, comprising 100 images from each location and equally divided into Smooth and Rough classes based on a composite scoring rubric referring to SNI 7619:2012. Pre-processing included RGB-to-HSV conversion using the Value channel, contrast stretching, and object cropping. Six GLCM features, namely Contrast, Dissimilarity, Homogeneity, Energy, Correlation, and Entropy, were extracted using distances of 1, 3, and 5 pixels and angles of 0°, 45°, 90°, and 135°. Classification was performed using SVM with GridSearchCV and 5-Fold Cross Validation. The location-based descriptive comparison showed that Lansot samples exhibited higher Contrast, Dissimilarity, and Entropy values and lower Homogeneity, Energy, and Correlation values than Sea samples, indicating greater image-texture variation in the Lansot samples. The SVM with the Radial Basis Function (RBF) kernel achieved 93.33% cross-validation accuracy and 96.00% test accuracy, with precision, recall, and F1-score of 96.00%. The RBF kernel also performed significantly better than the Linear kernel (p = 0.0026). These findings indicate the potential of GLCM and SVM for image-based characterization and classification of crushed-stone surface texture.
References
Al-Rousan, T., Masad, E., Tutumluer, E., & Pan, T. (2007). Evaluation of image analysis techniques for quantifying aggregate shape characteristics. Construction and Building Materials, 21(5), 978–990. https://doi.org/10.1016/j.conbuildmat.2006.03.005
Bianconi, F., González, E., Fernández, A., & Saetta, S. A. (2012). Automatic classification of granite tiles through colour and texture features. Expert Systems with Applications, 39(12), 11212–11218. https://doi.org/10.1016/j.eswa.2012.03.052
Chatterjee, S. (2013). Vision-based rock-type classification of limestone using multi-class support vector machine. Applied Intelligence, 39(1), 14–27. https://doi.org/10.1007/s10489-012-0391-7
Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20, 273–297. https://doi.org/10.1007/BF00994018
Feng, P., Wang, H., Ding, H., Xiao, J., & Hassan, M. (2020). Effects of surface texture and its mineral composition on interfacial behavior between asphalt binder and coarse aggregate. Construction and Building Materials, 262, Article 120869. https://doi.org/10.1016/j.conbuildmat.2020.120869
Ghodrati, S., Gorji Kandi, S., & Mohseni, M. (2018). How accurately do different computer-based texture characterization methods predict material surface coarseness? A guideline for effective online inspection. Journal of the Optical Society of America A, 35(5), 712–725. https://doi.org/10.1364/JOSAA.35.000712
Güçlüer, K. (2020). Investigation of the effects of aggregate textural properties on compressive strength (CS) and ultrasonic pulse velocity (UPV) of concrete. Journal of Building Engineering, 27, Article 100949. https://doi.org/10.1016/j.jobe.2019.100949
Haralick, R. M., Shanmugam, K., & Dinstein, I. (1973). Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, SMC-3(6), 610–621. https://doi.org/10.1109/TSMC.1973.4309314
Liu, Z., Zhang, C., Shao, L., & Wang, J. (2021). Study on quantitative characterization of morphological characteristics and high temperature performance evaluation of coarse aggregate based on computer vision. Frontiers in Materials, 7, Article 607105. https://doi.org/10.3389/fmats.2020.607105
Naveen, M., Vidyashankara, M. S., & Kumar, G. H. (2020). Leaf classification based on GLCM texture and SVM. International Journal of Computer Applications, 177(35), 18–21. https://doi.org/10.5120/ijca2020919846
Nurzynska, K., & Iwaszenko, S. (2020). Application of texture features and machine learning methods to grain segmentation in rock material images. Image Analysis and Stereology, 39(2), 73–90. https://doi.org/10.5566/ias.2186
Ojala, T., Pietikäinen, M., & Mäenpää, T. (2002). Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(7), 971–987. https://doi.org/10.1109/TPAMI.2002.1017623
Petrounias, P., Rogkala, A., Giannakopoulou, P. P., Kalpogiannaki, M., Laskaris, N., & Lampropoulou, P. (2022). The role of the aggregate shape on the compressive strength of concrete using a new micro geo-informatics methodology. Micron, 161, Article 103333. https://doi.org/10.1016/j.micron.2022.103333
Rayhan, M. A., Manik, C. F. D., & Putra, A. P. (2026). Analyzing model stability and generalization under distribution shift in real-world machine learning applications. Dewantara Journal of Technology, 6(2), 78–89. https://doi.org/10.59563/djtech.v6i2.367
Roy, N., & Kuna, K. K. (2023). Image texture analysis to evaluate the microtexture of coarse aggregates for pavement surface courses. International Journal of Pavement Engineering, 24(2), Article 2099854. https://doi.org/10.1080/10298436.2022.2099854
Sarkar, M. R. (2024). Deep learning methods for chest X-ray imaging-based COVID-19 pneumonia detection. Journal Artificial: Informatika dan Sistem Informasi, 2(1), 1–9. https://doi.org/10.54065/artificial.487
Singh, A., Armstrong, R. T., Regenauer-Lieb, K., & Mostaghimi, P. (2019). Rock characterization using gray-level co-occurrence matrix: An objective perspective of digital rock statistics. Water Resources Research, 55(3), 1912–1927. https://doi.org/10.1029/2018WR023342
Tafesse, S., Robison Fernlund, J. M., Sun, W., & Bergholm, F. (2013). Evaluation of image analysis methods used for quantification of particle angularity. Sedimentology, 60(4), 1100–1110. https://doi.org/10.1111/j.1365-3091.2012.01367.x
Wafda, A. (2025). Transfer learning advancements: A comprehensive literature review on text analysis, image processing, and health data analytics. Journal Artificial: Informatika dan Sistem Informasi, 3(1), 1–10. https://doi.org/10.54065/artificial.544
Wang, Y., & Sun, S. (2022). A rock fabric classification method based on the grey level co-occurrence matrix and the Gaussian mixture model. Journal of Natural Gas Science and Engineering, 104, Article 104627. https://doi.org/10.1016/j.jngse.2022.104627
Zhang, S., Li, R., & Pei, J. (2019). Evaluation methods and indexes of morphological characteristics of coarse aggregates for road materials: A comprehensive review. Journal of Traffic and Transportation Engineering (English Edition), 6(3), 256–272. https://doi.org/10.1016/j.jtte.2019.01.003
Zhang, X., Huang, T.-N., Chung, S.-L., Maulana, A., Mawaleda, M., Tien, C.-Y., Lee, H.-Y., & Liu, P.-P. (2022). Late Eocene subduction initiation of the Indian Ocean in the North Sulawesi Arc, Indonesia, induced by abrupt Australian plate acceleration. Lithos, 422–423, Article 106742. https://doi.org/10.1016/j.lithos.2022.106742
Zhou, X., Xie, Y., Long, G., & Li, J. (2021). Effect of surface characteristics of aggregates on the compressive damage of high-strength concrete based on 3D discrete element method. Construction and Building Materials, 301, Article 124101. https://doi.org/10.1016/j.conbuildmat.2021.124101
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Pasquila V. Jade, Luther A. Latumakulita, Siska Ayu Widiana, Winsy Ch. D. Weku, Edwin Tenda, Rillya Arundaa
This work is licensed under a Creative Commons Attribution 4.0 International License.
License and Copyright Agreement
- Authors retain copyright and other proprietary rights related to the article.
- Authors retain the right and are permitted to use the substance of the article in their own future works, including lectures and books.
- Authors grant the journal the right of first publication with the work simultaneously licensed under Creative Commons Attribution License (CC BY 4.0) that allows others to share the work with an acknowledgment 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 acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post or self-archive 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.
