Klasifikasi Cacat Permukaan Keramik Menggunakan Logistic Regression dan SVM Berbasis CNN

Authors

  • Inggrid Nindia Aprila Palupi Universitas Airlangga, Surabaya, Indonesia
  • Budiyan Mariyadi Universitas Muhammadiyah Bandung, Bandung, Indonesia
  • Imam Yuadi Univeristas Airlangga, Surabaya, Indonesia
  • Taufik Roni Sahroni Binus University, Jakarta, Indonesia

DOI:

https://doi.org/10.38035/jemsi.v7i4.7551

Keywords:

Klasifikasi, Logistic Regression, Support Vector Machine, Cacat permukaan Keramik, Akurasi, Presisi

Abstract

Klasifikasi dalam mendeteksi cacat permukaan pada ubin keramik merupakan langkah penting dalam memastikan kualitas produk di industri manufaktur. Klasifikasi yang akurat sangat diperlukan untuk meningkatkan kualitas hasil produksi dan mengurangi kesalahan faktor manusia. Penelitian ini bertujuan untuk deteksi dan klasifikasi secara akurat pada jenis cacat baik yang bertekstur 2D dan 3D. Metode yang diusulkan dengan menggunakan Logistic Regression dan dibandingkan dengan Support Vector Machine. Dalam Penelitian ini menggunakan 133 data jenis cacat yang diambil menggunakan kamera smartphone dengan sudut 45˚. Proses pelatihan menggunakan 66% data yang dilatih dengan model Inception V3, VGG-16 dan VGG-19 kemudian 34% data jenis cacat untuk pengujian. Logistic Regression dan Support Vector Machine dengan Inception V3 memberikan hasil klasifikasi terbaik dengan akurasi dan presisi 0,99 dengan kemampuan untuk klasifikasi 100% jenis cacat seperti gompal, lubang, terkelupas, retak dengan tekstur 2D. Sedangkan VGG-19 dapat melakukan klasifikasi 100% pada jenis cacat gelembung dengan tekstur 3D. Waktu pelatihan dan pengujian Logistic Regression dengan Inception V3 6,9 dan 2,1 detik dan VGG-19 membutuhkan waktu pelatihan dan pengujian 53,8 dan 5,36 detik. Sedangkan Support Vector Machine dengan Inception V3 membutuhkana waktu pelatihan dan pengujian 6,6 dan 4,7 detik, sedangkan VGG-19 membutuhkan waktu pelatihan dan pengujian 10,1 dan 4,7 detik.

References

Bai, J., Wu, D., Shelley, T., Schubel, P., Twine, D., Russell, J., Zeng, X., & Zhang, J. (2024). A Comprehensive Survey on Machine Learning Driven Material Defect Detection: Challenges, Solutions, and Future Prospects. http://arxiv.org/abs/2406.07880

Baldomero-Naranjo, M., Martínez-Merino, L. I., & Rodríguez-Chía, A. M. (2021). A robust SVM-based approach with feature selection and outliers detection for classification problems. Expert Systems with Applications, 178(1995), 1–38. https://doi.org/10.1016/j.eswa.2021.115017

Caba, A. B. (2023). Mathematical Approach in Image Classification using Regression. 732–733. https://doi.org/10.1186/cc2401.

Chen, J., Xiong, H., Zhou, S., Wang, X., Lou, B., Ning, L., Hu, Q., Tang, Y., & Gu, G. (2025). A Hybrid Deep Learning and Improved SVM Framework for Real-Time Railroad Construction Personnel Detection with Multi-Scale Feature Optimization. Sensors, 25(7). https://doi.org/10.3390/s25072061

Cumbajin, E., Rodrigues, N., Costa, P., Miragaia, R., Frazão, L., Costa, N., Fernández-caballero, A., Carneiro, J., Buruberri, L. H., & Pereira, A. (2023). A Systematic Review on Deep Learning with CNNs Applied to Surface Defect Detection. 1–29.

Diao, J., Wei, H., Zhou, Y., & Diao, Z. (2025). A Deep Learning-Based Algorithm for Ceramic Product Defect Detection. Applied Sciences (Switzerland), 15(12), 1–19. https://doi.org/10.3390/app15126641

Hussain, T., Hong, J., & Seok, J. (2024). A Hybrid Deep Learning and Machine Learning-Based Approach to Classify Defects in Hot Rolled Steel Strips for Smart Manufacturing. 1–21. https://doi.org/10.32604/cmc.2024.050884

Jha, S. B., & Babiceanu, R. F. (2023). Deep CNN-based visual defect detection: Survey of current literature. Computers in Industry, 148, 103911. https://doi.org/10.1016/j.compind.2023.103911

Kareem, I., Ali, S. F., Bilal, M., & Hanif, M. S. (2024). Exploiting the features of deep residual network with SVM classifier for human posture recognition. PLoS ONE, 19(12 December), 1–26. https://doi.org/10.1371/journal.pone.0314959

Karimi, N., Mishra, M., & Lourenço, P. B. (2024). Deep learning-based automated tile defect detection system for Portuguese cultural heritage buildings. Journal of Cultural Heritage, 68, 86–98. https://doi.org/10.1016/j.culher.2024.05.009

Kaur, S., Gupta, S., Gupta, D., Juneja, S., Nauman, A., Khan, M., Husain, I., Islam, A., & Mallik, S. (2025). High-accuracy lung disease classification via logistic regression and advanced feature extraction techniques. Egyptian Informatics Journal, 29(December 2024), 100596. https://doi.org/10.1016/j.eij.2024.100596

Kazemi, M. (2024). Support vector machine in ultrahigh-dimensional feature space. Journal of Statistical Computation and Simulation, 94(3), 517–535. https://doi.org/10.1080/00949655.2023.2263128

Kilci, O., & Koklu, M. (2025). 4 th International Conference on Trends in Advanced MACHINE LEARNING-BASED DETECTION OF SOLAR PANEL SURFACE DEFECTS USING DEEP FEATURES FROM. July.

Laveda-Martínez, A., García-de-la-Puente, N. P., García-Torres, F., Israelsen, N. M., Bang, O., Brouczek, D., Benson, N., Colomer, A., & Naranjo, V. (2025). Defect Segmentation in OCT scans of ceramic parts for non-destructive inspection using deep learning. http://arxiv.org/abs/2510.00745

Mariyadi, B., Fitriyani, N., & Sahroni, T. R. (2021). 2D Detection Model of Defect on the Surface of Ceramic Tile by an Artificial Neural Network. Journal of Physics: Conference Series, 1764(1). https://doi.org/10.1088/1742-6596/1764/1/012176

Mat Jizat, J. A., P.P. Abdul Majeed, A., Ahmad, A. F., Taha, Z., & Yuen, E. (2021). Evaluation of the machine learning classifier in wafer defects classification. ICT Express, 7(4), 535–539. https://doi.org/10.1016/j.icte.2021.04.007

Ohemu, M. F. (2021). DEVELOPMENT OF AUTOMATED CERAMIC TILES SURFACE DEFECT DETECTION AND CLASSIFICATION SYSTEM. 8(8), 200–208.

Pardo, C. N., Sabri, L. M., & Awwaluddin, M. (2019). No Title. Jurnal Geodesi Undip; Volume 9, Nomor 1, Tahun 2020. https://doi.org/10.14710/jgundip.2020.26181

Sun, Z. (2026). Parts Surface Defect Detection Algorithm Based on Improved YOLOv8s. https://doi.org/10.1002/eng2.70569

Tahirovi, E. (2023). Interpretability and Explainability of Logistic Regression Model for Breast Cancer Detection. 3(Icaart), 161–168. https://doi.org/10.5220/0011627600003393

Wang, B. S., & Zhang, L. (2025). Deep Learning for Ceramic Surface Defect Inspection : A State-of-the-Art Survey. 14, 1–14. https://doi.org/10.4416/JCST2025-00011

Zhang, P., Wang, R., & Xiu, N. (2022). Neurocomputing Multinomial logistic regression classifier via l q ; 0 -proximal Newton algorithm. Neurocomputing, 468, 148–164. https://doi.org/10.1016/j.neucom.2021.10.005

Downloads

Published

2026-03-18

How to Cite

Inggrid Nindia Aprila Palupi, Budiyan Mariyadi, Imam Yuadi, & Taufik Roni Sahroni. (2026). Klasifikasi Cacat Permukaan Keramik Menggunakan Logistic Regression dan SVM Berbasis CNN. Jurnal Ekonomi Manajemen Sistem Informasi, 7(4), 3259–3273. https://doi.org/10.38035/jemsi.v7i4.7551