Klasifikasi Tekstur Kayu Jati dan Mahoni Menggunakan Ekstraksi Fitur GLCM dan Convolutional Neural Network (CNN)
DOI:
https://doi.org/10.33005/santika.v5i1.752Keywords:
Klasifikasi Kayu, Tekstur Kayu, CNN, GLCM, Ekstraksi FiturAbstract
Identifikasi jenis kayu secara manual membutuhkan keahlian dan waktu, serta rentan subjektivitas. Penelitian ini mengusulkan sistem klasifikasi otomatis untuk tekstur kayu jati dan mahoni menggunakan kombinasi Convolutional Neural Network (CNN) untuk ekstraksi fitur visual dan Gray Level Co- occurrence Matrix (GLCM) untuk ekstraksi fitur tekstur. Dataset terdiri dari 220 citra (110 jati, 110 mahoni) yang melalui tahap pra-pemrosesan termasuk augmentasi data. Model yang dibangun memiliki dua input (citra dan fitur GLCM) yang digabungkan sebelum lapisan klasifikasi. Model dilatih selama 20 epoch dan dievaluasi menggunakan metrik akurasi, precision, recall, F1-score, serta confusion matrix. Hasil evaluasi menunjukkan performa yang baik dengan akurasi keseluruhan mencapai 93%. Model mampu mengklasifikasikan kayu Jati dengan recall 100% dan Mahoni dengan recall 86%. Penggabungan CNN dan GLCM terbukti efektif meningkatkan akurasi klasifikasi tekstur kayu.
References
S. Ilahiyah dan A. Nilogiri, "Implementasi deep learning pada identifikasi jenis tumbuhan berdasarkan citra daun menggunakan convolutional neural network," Justindo (Jurnal Sistem & Teknologi Informasi Indonesia), vol. 3, no. 2, hlm. 49-56, 2018.
E. Christopher R. and E. M. Sipayung, "Klasifikasi Image Jenis Kayu pada Furnitur dengan Convolutional Neural Network," Jurnal Telematika, vol. 18, no. 2, pp. 82-87, 2023.
N. F. Mustamin, Y. Sari, dan H. Khatimi, "Klasifikasi kualitas kayu kelapa menggunakan arsitektur CNN," Kumpulan Jurnal Ilmu Komputer (KLIK), vol. 8, no. 1, hlm. 49-59, 2021.
T. Riantiarni, "Deteksi Cacat pada Permukaan Kayu Menggunakan Model Convolutional Neural Network Yolovs," Skripsi, Telkom University, Bandung, 2022.
B. Konara, M. Krishnapillai, and L. Galagedara, “Recent Trends and Advances in Utilizing Digital Image Processing for Crop Nitrogen Management,” Remote Sensing, vol. 16, no. 23, p. 4514, Dec. 2024, doi: 10.3390/rs16234514.
K. Li, H. Yu, Y. Xu, and X. Luo, “Detection of oil spills based on gray level co-occurrence matrix and support vector machine,” Frontiers in Environmental Science, vol. 10, Dec. 2022, doi: 10.3389/fenvs.2022.1049880.
O. Elezabi, S. Guesney-Bodet, and J.-B. Thomas, “Impact of
Exposure and Illumination on Texture Classification Based on Raw Spectral
Filter Array Images,” Sensors, vol. 23, no. 12, p. 5443, Jun. 2023, doi:
3390/s23125443.
S. Barburiceanu, R. Terebes, and S. Meza, “3D Texture Feature Extraction and Classification Using GLCM and LBP-Based Descriptors,” Applied Sciences, vol. 11, no. 5, p. 2332, Mar. 2021, doi: 10.3390/app11052332.
N. Iqbal, R. Mumtaz, U. Shafi, and S. M. H. Zaidi, “Gray level co-occurrence matrix (GLCM) texture based crop classification using low altitude remote sensing platforms,” PeerJ Computer Science, vol. 7, p. e536, May 2021, doi: 10.7717/peerj-cs.536.
J. Liu et al., “Optimizing window size and directional parameters of GLCM texture features for estimating rice AGB based on UAVs multispectral imagery,” Frontiers in Plant Science, vol. 14, Dec. 2023, doi: 10.3389/fpls.2023.1284235.
F. A. Mohammed, K. K. Tune, B. G. Assefa, M. Jett, and S. Muhie, “Medical Image Classifications Using Convolutional Neural Networks: A Survey of Current Methods and Statistical Modeling of the Literature,” Machine Learning and Knowledge Extraction, vol. 6, no. 1, pp. 699–736, Mar. 2024, doi: 10.3390/make6010033.
L. Alzubaidi et al., “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,” Journal of Big Data, vol. 8, no. 1, p. 53, Mar. 2021, doi: 10.1186/s40537-021-00444-8.
[1]K. Kanwal et al., “Efficient CNN architecture with image sensing and algorithmic channeling for dataset harmonization,” Scientific Reports, vol. 15, no. 1, p. 7552, Mar. 2025, doi: 10.1038/s41598-025-90616-
w.
A. S. Sagayaraj and T. K. Devi, “Combination of gray level features with deep transfer learning for copra classification using machine learning and neural networks,” Scientific Reports, vol. 15, no. 1, p. 1579, Jan. 2025, doi: 10.1038/s41598-025-85490-5.
Y. Liu et al., “Textured-Based Deep Learning in Prostate Cancer Classification with 3T Multiparametric MRI: Comparison with PI-RADS- Based Classification,” Diagnostics, vol. 11, no. 10, p. 1785, Sep. 2021, doi: 10.3390/diagnostics11101785.
[1]K. Sudhakar et al., “Optimised feature selection-driven convolutional neural network using gray level co-occurrence matrix for detection of cervical cancer,” Open Life Sciences, vol. 18, no. 1, Nov. 2023, doi: 10.1515/biol-2022-0770.
