Robusta Coffee Leaf Disease Classifications Using SVM Method and GLCM Feature Extraction
Abstract
Many farmers in Indonesia derive their income from coffee plants, which also play a crucial role in the country’s foreign exchange earnings. However, coffee plant production may decrease due to pests and disease attacks. Leaf diseases, such as leaf spot (Cercospora coffeicola) and leaf rust (Hemileia vastatrix), are among the most common diseases to occur in coffee plants. This research seeks to identify leaf diseases in robusta coffee leaves and determine the classification. The application of machine learning-based image processing using the support vector machine (SVM) classification method based on the gray-level co-occurrence matrix (GLCM) feature extraction can be the proposed solution. The preprocessing must precede the processing stage for easier analysis of the image’s quality. Then, the k-means clustering segmentation process was conducted to distinguish leaf parts affected by leaf spot and rust from those unaffected. The GLCM method was employed as the feature extraction based on the angular second moment (ASM) or energy features, contrasts, correlations, inverse different moment (IDM) or homogeneities, and entropy with angles of 0°, 45°, 90°, and 135°, as well as inter-pixel distances of 1 until 3. The classification was done with the SVM method using the linear, polynomial, and radial basis function (RBF) Gaussian kernels. This research used leaf spot and rust images, with training and test data of 320 and 80 images, respectively. The RBF Gaussian achieved the best test results with the best accuracy of 97.5%, precision of 95.24%, recall of 100%, and F1-score of 97.56%.
References
M. Rizwan, Budidaya Kopi. West Pasaman, West Sumatra: CV. Azka Pustaka, 2022.
Y. Defitri, “Pengamatan Beberapa Penyakit yang Menyerang Tanaman Kopi (Coffea Sp) di Desa Mekar Jaya Kecamatan Betara Kabupaten Tanjung Jabung Barat,” J. Media Pertan., Vol. 1, No. 2, pp. 78–84, Oct. 2016, doi: 10.33087/jagro.v1i2.19.
I. Fibriani, Widjonarko, C.S. Sarwono, and F. Dwika, “Deteksi Penyakit Brown Eye Spot pada Daun Kopi Menggunakan Metode Euclidean Distance dan Hough Transform,” J. JEETech, Vol. 1, No. 1, pp. 44–49, May 2020, doi: 10.48056/jeetech.v1i2.120.
A.S. Franca and L.S. Oliveira, “Coffee,” in Integrated Processing Technologies for Food and Agricultural By-Products, Z. Pan, R. Zhang, dan S. Zicari, Eds., Cambridge, MA, USA: Academic Press, 2019, pp. 413–438, doi: 10.1016/B978-0-12-814138-0.00017-4
International Coffee Organization, “Total Production by All Exporting Countries.” Distributed by International Coffee Organization, https://www.ico.org/historical/1990%20onwards/PDF/1a-total-production.pdf
R. Harni et al., Teknologi Pengendalian Hama dan Penyakit Tanaman Kopi, ed. 2. Jakarta, Indonesia: IAARD Press, 2018.
U.D. Rosiani, C. Rahmad, M.A. Rahmawati, and F. Tupamahu, “Segmentasi Berbasis K-Means pada Deteksi Citra Penyakit Daun Tanaman Jagung,” J. Inform. Polinema, Vol. 6, No. 3, pp. 37–42, May 2020, doi: 10.33795/jip.v6i3.331.
E.P. Ramdan et al., Penyakit Tanaman dan Pengendaliannya. Medan, Sumatera Utara: Yayasan Kita Menulis, 2021.
N.E.T. Castillo et al., “Impact of Climate Change and Early Development of Coffee Rust – An Overview of Control Strategies to Preserve Organic Cultivars in Mexico,” Sci. Total Environ., Vol. 738, pp. 1–14, Oct. 2020, doi: 10.1016/j.scitotenv.2020.140225.
W. Li et al., “Intelligent Metasurface System for Automatic Tracking of Moving Targets and Wireless Communications Based on Computer Vision,” Nat. Commun., Vol. 14, pp. 1–10, Feb. 2023, doi: 10.1038/s41467-023-36645-3.
A.Y.P. Putri, “Pemodelan Sistem Pakar Diagnosa Penyakit Tanaman Kopi Arabika Dengan Metode Fuzzy K-Nearest Neighbor (FK-NN),” Skripsi, Universitas Brawijaya, Malang, Indonesia, 2015.
F.R. Lumbanraja, S. Rosdiana, H. Sudarsono, and A. Junaidi, “Sistem Pakar Diagnosis Hama dan Penyakit Tanaman Kopi Menggunkan Metode Breadth First Search (Bfs) Berbasis Web,” Explore J. Sist. Inf., Telemat., Vol. 11, No. 1, pp. 1–9, Jun. 2020, doi: 10.36448/jsit.v11i1.1452.
T.S. Prihartini and P.N. Andono, “Deteksi Tepi dengan Metode Laplacian of Gaussian pada Citra Daun Tanaman Kopi,” Skripsi, Universitas Dian Nuswantoro, Semarang, Indonesia, 2015.
W.A. Nugraha, M. Lestari, M. Yasin, and D. Suhartono, “Perancangan Sistem Pakar Pendeteksi Penyakit pada Tanaman Kopi dengan Layanan Berbasis Lokasi,” Access date: 20-Jun-2023, [Online], https://socs.binus.ac.id/2014/07/18/perancangan-sistem-pakar-pendeteksi-penyakit-pada-tanaman-kopi-dengan-layanan-berbasis-lokasi/
P.U. Rakhmawati, Y.M. Pranoto, and E. Setyati, “Klasifikasi Penyakit Daun Kentang Berdasarkan Fitur Tekstur dan Fitur Warna Menggunakan Support Vector Machine,” Seminar Nas. Teknol., Rekayasa (SENTRA) 2018, 2018, pp. 1–8, doi: 10.22219/sentra.v0i4.2127.
S.I. Novichasari and Y.S. Sipayung, “PSO-SVM untuk Klasifikasi Daun Cengkeh Berdasarkan Morfologi Bentuk Ciri, Warna dan Tekstur GLCM Permukaan Daun,” J. Multimatrix, Vol. 1, No. 1, pp. 18–21, Dec. 2018.
F. Jiang et al., “Image Recognition of Four Rice Leaf Diseases Based on Deep Learning and Support Vector Machine,” Comput., Electron. Agriculture, Vol. 179, pp. 1–9, Dec. 2020, doi: 10.1016/j.compag.2020.105824.
Trivusi (2022) “Data Splitting: Pengertian, Metode, dan Kegunaannya,” [Online], https://www.trivusi.web.id/2022/08/data-splitting.html, access date: 20-Jun-2023.
L. Hussain et al., “Lung Cancer Prediction Using Robust Machine Learning and Image Enhancement Methods on Extracted Gray‐Level Co‐occurrence Matrix Features,” Appl. Sci., Vol. 12, No. 13, pp. 1–20, Jun. 2022, doi: 10.3390/app12136517.
I.M.O. Widyantara, N.M.A.E.D Wirastuti, and I.B.P. Adnyana, “Metode Contrast Stretching untuk Perbaikan Kualitas Citra pada Proses Segmentasi Video,” Maj. Ilm. Teknol. Elekt., Vol. 16, No. 2, pp. 1–6, May–Aug. 2017, doi: 10.24843/MITE.2017.vl6i02p01.
H. Armagan, “K-Means Kümeleme Algoritması ile Renk Tabanlı Segmantasyon ve Renk Uzaylarının Görüntü Niceliklerine Etkisinin Sayısal Analizi,” El-Cezerî J. Sci., Eng., Vol. 9, No. 4, pp. 1506–1517, Dec. 2022, doi: 10.31202/ecjse.1141148.
N. Mourya, Vidyashanakara, and G.H. Kumar, “Leaf Classification Based on GLCM Texture and SVM,” Int. J. Comput. Appl., Vol. 4, No. 3, pp. 156–159, Mar. 2018, doi: 10.5120/ijca2020919846.
E. Alvansga, “Pengenalan Tekstur Menggunakan Metode GLCM serta Modul Nirkabel,” Undergraduate thesis, Universitas Sanata Dharma, Yogyakarta, Indonesia, 2019.
M. Furqan, S. Sriani, and L.S. Harahap, “Klasifikasi Daun Bugenvil Menggunakan Gray Level Co-Occurrence Matrix dan K-Nearest Neighbor,” J. CoreIT, Vol. 6, No. 1, pp. 22–29, Jun. 2020, doi: 10.24014/coreit.v6i1.9296.
R. Suganya, S. Rajaram, and A.S. Abdullah, Big Data in Medical Image Processing, ed. 1. Florida, AS: CRC Press, 2018, doi: 10.1201/b22456.
M.F.T. Putra, “Penerapan Gray Level Co-Occurrence Matrix (GLCM) dan Learning Vector Quantization (LVQ) untuk Klasifikasi Penyakit Retina Mata,” Final Project, Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru, Indonesia, 2021.
J. Webel, J. Gola, D. Britz, and F. Mücklich, “A New Analysis Approach Based on Haralick Texture Features for the Characterization of Microstructure on the Example of Low-Alloy Steels,” Mater. Charact., Vol. 144, pp. 584–596, Oct. 2018, doi: 10.1016/j.matchar.2018.08.009.
Y.M. Oo and N.C. Htun, “Plant Leaf Disease Detection and Classification Using Image Processing,” Int. J. Res., Eng., Vol. 5, No. 9, pp. 516–523, Sep.–Oct. 2018, doi: 10.21276/ijre.2018.5.9.4.
E. Prasetyo, Data Minning: Mengolah Data Menjadi Informasi Menggunakan Matlab, ed. 1. Yogyakarta, Indonesia: Andi, 2014.
F. Hilmiyah, “Prediksi Kinerja Mahasiswa Menggunakan Support Vector Machine untuk Pengelola Program Studi di Perguruan Tinggi (Studi Kasus: Program Studi Magister Statistika ITS),” Master’s thesis, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia, 2017.
Y.F. Khan, B. Kaushik, C.L. Chowdhary, and G. Srivastava, “Ensemble Model for Diagnostic Classification of Alzheimer’s Disease Based on Brain Anatomical Magnetic Resonance Imaging,” Diagnostics, Vol. 12, No. 12, pp. 1–27, Dec. 2022, doi: 10.3390/diagnostics12123193.
S. Adinugroho and Y.A. Sari, Implementasi Data Mining Menggunakan Weka, ed. 1. Malang, Indonesia: UB Press, 2018.
A.N. Rais, W. Warjiono, W. Kurniawan, and R. Ardianto “Analisa Akurasi dan F1 Score pada Algoritma Smote dan Naïve Bayes pada Dataset Bank Direct Marketing,” Speed-Sentra Penelit. Eng., Edukasi, Vol. 11, No. 4, pp. 1–7, Oct. 2019, doi: 10.55181/speed.v11i4.620.
© Jurnal Nasional Teknik Elektro dan Teknologi Informasi, under the terms of the Creative Commons Attribution-ShareAlike 4.0 International License.
1.png)
