Pemanfaatan Support Vector Machine dalam Mendeteksi Biji Kopi
DOI:
https://doi.org/10.29407/75j7ar20Abstract
Abstrak— Penentuan mutu biji kopi secara akurat merupakan bagian penting dalam proses pascapanen dan pengolahan industri kopi. Namun, klasifikasi manual masih bersifat subjektif dan kurang efisien. Penelitian ini bertujuan membangun sistem klasifikasi otomatis untuk membedakan biji kopi dan non-kopi menggunakan metode Support Vector Machine (SVM) yang dikombinasikan dengan ekstraksi fitur tekstur dari citra menggunakan Gray Level Co-occurrence Matrix (GLCM). Dataset terdiri dari citra tiga jenis biji kopi (green, light, dark) serta citra non-kopi (beras, leci, dan coklat). Setiap citra diolah melalui tahap grayscale, resize, ekstraksi fitur (contrast, correlation, energy, homogeneity), dan normalisasi. Model SVM dioptimasi dengan Grid Search dan 5-fold cross validation. Hasil pengujian menunjukkan model mampu mengklasifikasikan dua kelas dengan akurasi 100%. Sistem telah diimplementasikan dalam aplikasi web berbasis Python. Hasil ini menunjukkan bahwa kombinasi GLCM dan SVM efektif untuk klasifikasi visual biji kopi dan memiliki potensi aplikasi dalam proses sortir otomatis dan kontrol mutu berbasis citra digital.
Keywords:
Support Vector Machine (SVM), Klasifikasi Biji Kopi, Ekstraksi Fitur GLCM##plugins.themes.default.displayStats.downloads##
References
[1] A. Faridah, R. Santosa, dan A. Zainuddin, “Klasifikasi Kualitas Biji Kopi Menggunakan Metode Jaringan Syaraf Tiruan dan Ekstraksi Ciri Tekstur,” Jurnal Ilmiah Komputer dan Informatika (KOMPUTA), vol. 9, no. 2, 2020.
[2] R. M. Haralick, K. Shanmugam, dan I. Dinstein, “Textural Features for Image Classification,” IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-3, no. 6, pp. 610–621, 1973.
[3] Cortes, Corinna, and Vladimir Vapnik. "Support-vector networks." Machine learning 20 (1995): 273-297.
[4] Yana, Yusuf Eka, and Nur Nafi’iyah. "Klasifikasi jenis pisang berdasarkan fitur warna, tekstur, bentuk citra menggunakan SVM dan KNN." Res. J. Comput. Inf. Syst. Technol. Manag 4.1 (2021): 28. [5] Wyatt, J. C., Spiegelhalter, D. 2008. Field Trials of Medical Decision-Aids: PotentialProblems and Solutions. Proceeding of 15th Symposium on ComputerApplications in Medical Care. Washington. May 3
[5] Dong, Yiyang, et al. "A machine learning model for product fraud detection based on svm." 2021 2nd International Conference on Education, Knowledge and Information Management (ICEKIM). IEEE, 2021.
[6] Fajri, Muhamad, and Aji Primajaya. "Komparasi Teknik Hyperparameter Optimization pada SVM untuk Permasalahan Klasifikasi dengan Menggunakan Grid Search dan Random Search." Journal of Applied Informatics and Computing 7.1 (2023): 10-15. [8] Wallace, V. P., Bamber,J. C. dan Crawford, D. C. 2000. Classification of reflectance spectra from pigmented skin lesions, a comparison of multivariate discriminate analysis and artificial neural network. Journal Physical Medical Biology. No.45. Vol.3. 2859-2871.
[7] Darmawan, Zakha Maisat Eka, and Ashafidz Fauzan Dianta. "Implementasi optimasi hyperparameter GridSearchCV pada sistem prediksi serangan jantung menggunakan SVM." Teknologi: Jurnal Ilmiah Sistem Informasi 13.1 (2023): 8-15.
[8] K. Wahidah, D. Pranolo, dan I. P. Raka, “Ekstraksi Ciri Tekstur Menggunakan GLCM untuk Klasifikasi Citra Daun,” Jurnal Informatika dan Sistem Informasi (JIFSI), vol. 8, no. 1, 2022.
[9] C. Cortes dan V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, no. 3, pp. 273–297, 1995.
[10] J. Bergstra dan Y. Bengio, “Random Search for Hyper-Parameter Optimization,” Journal of Machine Learning Research, vol. 13, pp. 281–305, 2012.
[11] I. T. Umagapi, B. Umaternate, H. Hazriani, and Y. Yuyun, "Uji Kinerja K-Means Clustering Menggunakan Davies Bouldin Index Pada Pengelompokan Data Prestasi Siswa," Prosiding SISFOTEK, vol. 7, no. 1, pp. 303-308, 2023.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Muhammad Nur Ichsan, Made Ayu Dusea Widyadara, Umi Mahdiyah
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License 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 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.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
