Investigasi Forensik Citra Penyakit Daun Bonsai dengan Fitur GLCM dan Bentuk Berbasis Deep Learning
Abstract
Identifikasi penyakit daun bonsai secara visual bersifat subjektif dan bergantung pada pengalaman pengamat. Penelitian ini bertujuan mengembangkan dan mengevaluasi sistem klasifikasi kondisi daun bonsai beringin dan serut ke dalam empat kelas, yaitu sehat, bercak, klorosis, dan nekrosis, dengan menggabungkan fitur tekstur Gray Level Co-occurrence Matrix (GLCM) dan fitur bentuk kontur pada jaringan saraf tiruan berlapis. Alur pemrosesan mengacu pada kerangka forensik digital NIST SP 800-86 dan mencakup penyeragaman citra 224×224 piksel, konversi keabuan, segmentasi Otsu, ekstraksi empat fitur GLCM (contrast, correlation, energy, homogeneity) serta empat fitur bentuk (area, perimeter, metric, eccentricity), standardisasi, dan klasifikasi dengan tiga lapisan tersembunyi (128, 64, dan 32 neuron) yang dilatih menggunakan optimizer Adam. Evaluasi pada 113 citra uji menghasilkan akurasi 93,81% (selang kepercayaan 95%: 87,8–97,0%), macro-precision 95,12%, macro-recall 93,08%, dan macro-F1 94,00%. Seluruh citra sehat terklasifikasi benar, sedangkan recall terendah terdapat pada kelas nekrosis (85,00%) karena nilai contrast dan metric kelas ini tumpang tindih dengan kelas bercak. Ketujuh kesalahan terjadi antarkelas sakit. Nilai metric yang konstan pada citra sehat mengindikasikan segmentasi global yang masih sensitif terhadap latar, sehingga diperlukan segmentasi yang lebih kuat, data yang lebih beragam, dan uji ablasi fitur. Sistem diimplementasikan sebagai aplikasi web Streamlit untuk skrining awal.
References
Ahmed, I. T., Hammad, B. T., & Jamil, N. (2021). Forgery detection algorithm based on texture features. IEEE Access, 9, 94549–94567. https://doi.org/10.1109/ACCESS.2021.3093896
Amrullah. (2026). Pendekatan forensik dokumen dalam verifikasi keaslian tanda tangan menggunakan metode Histogram of Oriented Gradients (HOG) dan Support Vector Machine (SVM). Indonesian Journal of Multidisciplinary Scientific Studies, 4(6), 440–448. https://doi.org/10.33151/ijomss.v4i6.1131
Anggiratih, E., Siswanti, S., Octaviani, S. K., & Sari, A. (2021). Klasifikasi penyakit tanaman padi menggunakan model deep learning Efficientnet B3 dengan transfer learning. Jurnal Ilmiah SINUS, 19(1). https://doi.org/10.30646/sinus.v19i1.526
Anita, A., Rodhy, R., Ningsih, S., & Solin, D. (2019). Penerapan metode forward chaining dan certainty factor untuk diagnosa penyakit pada tanaman bonsai. JGK (Jurnal Guru Kita), 3(2), 187–194. https://doi.org/10.24114/jgk.v3i2.14587
Burhanuddin, R. R. (2024). Klasifikasi penyakit padi melalui citra daun menggunakan metode Naive Bayes. Jurnal Informatika dan Teknik Elektro Terapan, 12(2). https://doi.org/10.23960/jitet.v12i2.4012
Dhiman, P., Kaur, A., Hamid, Y., Alabdulkreem, E., Elmannai, H., & Ababneh, N. (2023). Smart disease detection system for citrus fruits using deep learning with edge computing. Sustainability, 15(5), 4576. https://doi.org/10.3390/su15054576
Fi’Nawu, R. A., Salihi, I. A., Lamasigi, Z. Y., & Idris, I. S. K. (2026). Klasifikasi penyakit tanaman cabai berdasarkan seleksi fitur GLCM dan algoritma K-Nearest Neighbor. Jambura Journal of Electrical and Electronics Engineering, 8(1), 40–45. https://ejurnal.ung.ac.id/index.php/jjeee/article/download/34661/12491
Harakannanavar, S. S., Rudagi, J. M., Puranikmath, V. I., Siddiqua, A., & Pramodhini, R. (2022). Plant leaf disease detection using computer vision and machine learning algorithms. Global Transitions Proceedings, 3(1), 305–310. https://doi.org/10.1016/j.gltp.2022.03.016
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
Hassan, S. M., & Maji, A. K. (2022). Plant disease identification using a novel convolutional neural network. IEEE Access, 10, 5390–5401. https://doi.org/10.1109/ACCESS.2022.3141371
Kabir, M., Unal, F., Akinci, T. C., Martinez-Morales, A. A., & Ekici, S. (2024). Revealing GLCM metric variations across a plant disease dataset: A comprehensive examination and future prospects for enhanced deep learning applications. Electronics, 13(12), 2299. https://doi.org/10.3390/electronics13122299
Kent, K., Chevalier, S., Grance, T., & Dang, H. (2006). Guide to integrating forensic techniques into incident response (NIST Special Publication 800-86). National Institute of Standards and Technology. https://doi.org/10.6028/NIST.SP.800-86
Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015). https://doi.org/10.48550/arXiv.1412.6980
Kuncoro, S. T., & Syahra, Y. (2026). Deteksi tepi citra pupuk menggunakan algoritma Canny untuk analisis bentuk dan tekstur produk. Indonesian Journal of Multidisciplinary Scientific Studies, 4(6), 609–622. https://doi.org/10.33151/ijomss.v4i6.1155
Leiva, F., Abdelghafour, F., Alsheikh, M., Nagy, N. E., Davik, J., & Chawade, A. (2024). ScabyNet, a user-friendly application for detecting common scab in potato tubers using deep learning and morphological traits. Scientific Reports, 14, 1277. https://doi.org/10.1038/s41598-023-51074-4
Luque, A., Carrasco, A., Martín, A., & de las Heras, A. (2019). The impact of class imbalance in classification performance metrics based on the binary confusion matrix. Pattern Recognition, 91, 216–231. https://doi.org/10.1016/j.patcog.2019.02.023
Matondang, D. F., & Tanjung, M. A. P. (2026). Deteksi dini karies dan karang gigi berbasis Android menggunakan CNN MobileNetV2 dan transfer learning. Indonesian Journal of Multidisciplinary Scientific Studies, 4(6), 574–582. https://doi.org/10.33151/ijomss.v4i6.1149
Orchi, H., Sadik, M., Khaldoun, M., & Sabir, E. (2023). Automation of crop disease detection through conventional machine learning and deep transfer learning approaches. Agriculture, 13(2), 352. https://doi.org/10.3390/agriculture13020352
Oryza Sativa, R. D., & Serdani, A. D. (2022). Bonsai beringin dan serut sebagai alternatif pendapatan petani milenial di masa pandemi Covid 19. VIABEL: Jurnal Ilmiah Ilmu-Ilmu Pertanian, 16(1), 21–28. https://doi.org/10.35457/viabel.v16i1.1800
Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1), 62–66. https://doi.org/10.1109/TSMC.1979.4310076
Shoaib, M., Shah, B., EI-Sappagh, S., Ali, A., Ullah, A., Alenezi, F., Gechev, T., Hussain, T., & Ali, F. (2023). An advanced deep learning models-based plant disease detection: A review of recent research. Frontiers in Plant Science, 14, 1158933. https://doi.org/10.3389/fpls.2023.1158933
Simhadri, C. G., & Kondaveeti, H. K. (2023). Automatic recognition of rice leaf diseases using transfer learning. Agronomy, 13(4), 961. https://doi.org/10.3390/agronomy13040961
Singh, A. K., Sreenivasu, S. V. N., Mahalaxmi, U. S. B. K., Sharma, H., Patil, D. D., & Asenso, E. (2022). Hybrid feature-based disease detection in plant leaf using convolutional neural network, Bayesian optimized SVM, and random forest classifier. Journal of Food Quality, 2022, 2845320. https://doi.org/10.1155/2022/2845320
Sun, X., Li, G., Qu, P., Xie, X., Pan, X., & Zhang, W. (2022). Research on plant disease identification based on CNN. Cognitive Robotics, 2, 155–163. https://doi.org/10.1016/j.cogr.2022.07.001
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
