Integritas Teknik Pengolahan Citra Dan Machine Learning Untuk Penilaian Kualitas Visual Biji Kopi

Adam Julian Saputra, Risky Aswi Ramadhani, Daniel Swanjaya

Abstract


Digitalisasi di sektor pertanian menjadi kebutuhan mendesak dalam menghadapi tantangan efisiensi, akurasi, dan keterbatasan tenaga kerja dalam proses penilaian mutu produk. Penilaian kualitas secara manual cenderung bersifat subjektif, memakan waktu, dan kurang konsisten, terutama pada skala produksi besar. Penelitian ini bertujuan mengembangkan sistem otomatis untuk menilai kualitas visual biji kopi dengan mengintegrasikan teknik pengolahan citra digital dan pembelajaran mesin. Metode deteksi tepi Prewitt dan thresholding Otsu digunakan untuk mengekstraksi fitur visual, sementara fitur tekstur dari Gray Level Co-occurrence Matrix (GLCM) dimanfaatkan sebagai input untuk model klasifikasi Random Forest. Sistem dilengkapi dengan antarmuka berbasis Streamlit yang memungkinkan analisis secara real-time terhadap citra biji kopi. Hasil evaluasi menunjukkan bahwa sistem mencapai akurasi klasifikasi sebesar 99,58%, dengan presisi dan recall makro masing-masing 99,60%, serta mampu mengenali cacat visual dan jenis biji kopi secara efektif. Temuan ini menunjukkan bahwa pendekatan hybrid antara pengolahan citra dan machine learning berpotensi besar dalam mendukung implementasi pertanian digital yang presisi, efisien, dan adaptif terhadap kebutuhan industri.

References


P. B. Pathare, U. L. Opara, and F. A. J. Al-Said, “Colour Measurement and Analysis in Fresh and Processed Foods: A Review,” Jan. 01, 2013, Springer Science and Business Media, LLC. doi: 10.1007/s11947-012-0867-9.

“PENGOLAHAN CITRA; DASAR DAN CONTOH PENERAPANNYA.”

A. Humeau-Heurtier, “Texture feature extraction methods: A survey,” 2019, Institute of Electrical and Electronics Engineers Inc. doi: 10.1109/ACCESS.2018.2890743.

N. Liang and D. D. Kitts, “Antioxidant property of coffee components: Assessment of methods that define mechanism of action,” Nov. 19, 2014, MDPI AG. doi: 10.3390/molecules191119180.

L. Breiman, “Random Forests,” 2001.

M. Bedaso, M. Meshesha, and C. Diriba, “Grading Ethiopian Coffee Raw Quality Using Image Processing Techniques.,” Aug. 24, 2022. doi: 10.21203/rs.3.rs-1980632/v1.

A. O. Ok, O. Akar, and O. Gungor, “Evaluation of random forest method for agricultural crop classification,” Eur J Remote Sens, vol. 45, no. 1, pp. 421–432, 2012, doi: 10.5721/EuJRS20124535.

Y. Perugachi-Diaz, J. M. Tomczak, and S. Bhulai, “Deep learning for white cabbage seedling prediction,” Comput Electron Agric, vol. 184, May 2021, doi: 10.1016/j.compag.2021.106059.

K. K. Patel, A. Kar, S. N. Jha, and M. A. Khan, “Machine vision system: A tool for quality inspection of food and agricultural products,” Apr. 2012. doi: 10.1007/s13197-011-0321-4.

N. Nasution, A. Zamsuri, L. Lisnawita, and A. Wanto, “Polak-Ribiere updates analysis with binary and linear function in determining coffee exports in Indonesia,” in IOP Conference Series: Materials Science and Engineering, Institute of Physics Publishing, Oct. 2018. doi: 10.1088/1757-899X/420/1/012088.

A. Kamilaris and F. X. Prenafeta-Boldú, “Deep learning in agriculture: A survey,” Apr. 01, 2018, Elsevier B.V. doi: 10.1016/j.compag.2018.02.016.

G. Carrasco Silva et al., “Microplastics and their effect in horticultural crops: Food safety and plant stress,” Aug. 01, 2021, MDPI AG. doi: 10.3390/agronomy11081528.

J. Chen, J. Zhao, B. Kong, Q. Chen, Q. Liu, and C. Liu, “Comparative study of oxidative structural modifications of unadsorbed and adsorbed proteins in whey protein isolate‐stabilized oil‐in‐water emulsions under the stress of primary and secondary lipid oxidation products,” Foods, vol. 10, no. 3, Mar. 2021, doi: 10.3390/foods10030593.

A. Mohapatra, S. Shanmugasundaram, and R. Malmathanraj, “Grading of ripening stages of red banana using dielectric properties changes and image processing approach,” Comput Electron Agric, vol. 143, pp. 100–110, Dec. 2017, doi: 10.1016/j.compag.2017.10.010.

Z. L. Zhu, Z. Li, R. X. Zhang, C. Le Guo, and M. M. Cheng, “Designing an Illumination-Aware Network for Deep Image Relighting,” IEEE Transactions on Image Processing, vol. 31, pp. 5396–5411, 2022, doi: 10.1109/TIP.2022.3195366.

E. Karypidis, S. G. Mouslech, K. Skoulariki, and A. Gazis, “Comparison Analysis of Traditional Machine Learning and Deep Learning Techniques for Data and Image Classification,” WSEAS Trans Math, vol. 21, pp. 122–130, 2022, doi: 10.37394/23206.2022.21.19.


Refbacks

  • There are currently no refbacks.



 
PANDUAN SUBMITE ARTIKEL
 


Kantor Sekertariat:
Universitas PGRI Madiun
Jl. Auri No. 14-16  Kota Madiun 63118
Lt 3 Kantor Program Studi Teknik Informatika
email :  [email protected]
 
 

Lisensi Creative Commons
Ciptaan disebarluaskan di bawah Lisensi Creative Commons Atribusi-BerbagiSerupa 4.0 Internasional.