Analisis Citra Digital untuk Klasifikasi Kematangan Kelapa Menggunakan K-Nearest Neighbor

Paisal Hamid  Marpaung; Editha Dewi  Purnamasari; Hikma Gustina  Rambe; Elisa Elisa; Indah  Lestari

doi:10.55338/jumin.v6i4.6783

Authors

Paisal Hamid Marpaung, Universitas Muhammadiyah Tapanuli Selatan, Indonesia
Editha Dewi Purnamasari, Unversitas Muhammadiyah Tapanuli Selatan, Indonesia
Hikma Gustina Rambe, Unversitas Cendekia Abditama, Indonesia
Elisa Elisa, Unversitas Muhammadiyah Tapanuli Selatan, Indonesia
Indah Lestari, Unversitas Muhammadiyah Tapanuli Selatan, Indonesia

DOI:

https://doi.org/10.55338/jumin.v6i4.6783

Keywords:

Klasifikasi kelapa, Pengolahan citra digital, K-Nearest Neighbors, Kematangan buah, Ruang warna RGB

Abstract

Penelitian ini membahas pengembangan sistem klasifikasi tingkat kematangan kelapa berbasis pengolahan citra digital dengan algoritma K-Nearest Neighbors (KNN). Tujuannya adalah menyediakan metode penilaian kualitas kelapa yang lebih objektif, konsisten, dan efisien dibandingkan metode manual. Dataset citra kelapa diperoleh melalui proses akuisisi terkontrol, diikuti tahapan pra-pemrosesan, konversi ruang warna RGB ke HSV, dan ekstraksi fitur warna. Model KNN dioptimalkan melalui validasi silang untuk menentukan nilai k terbaik, yaitu k = 3. Evaluasi dilakukan menggunakan metrik akurasi, presisi, recall, F1-score, serta analisis Receiver Operating Characteristic (ROC) dan Area Under Curve (AUC). Hasil menunjukkan akurasi rata-rata 92%, dengan nilai AUC di atas 0,90 untuk semua kelas (Muda, Setengah Matang, Matang), mengindikasikan kinerja model yang sangat baik. Kesalahan klasifikasi paling sering terjadi pada kelas Setengah Matang dan Matang karena kemiripan warna. Temuan ini menegaskan potensi KNN untuk klasifikasi kualitas kelapa berbasis warna, meskipun peningkatan dapat dilakukan melalui fitur tekstur, augmentasi data, dan pengujian pada kondisi pencahayaan yang bervariasi. Sistem ini diharapkan dapat mendukung otomasi sortasi kelapa di tingkat petani maupun industri.

Downloads

Download data is not yet available.

References

A. S. Nurdin, “Produksi dan Nilai Ekonomi Kelapa di Indonesia,” Jurnal Pertanian Tropis, vol. 8, no. 2, pp. 101–108, 2020.

S. R. Rahman et al., “The Maturity Classification of Coconut using Machine Vision,” International Journal of Agricultural Technology, vol. 14, no. 3, pp. 491–502, 2018.

I. Kartika and H. Santosa, “Identifikasi Kemapanan Buah Kelapa Berdasarkan Karakteristik Warna,” Jurnal Teknologi dan Industri Pangan, vol. 6, no. 1, pp. 30–35, 2019.

J. A. Aguilera and D. Ibarz, “Food color measurement: principles and practice,” Trends in Food Science & Technology, vol. 18, no. 7, pp. 401–408, 2007.

M. A. Hossain et al., “Fruit quality detection using color and shape features,” Computers and Electronics in Agriculture, vol. 162, pp. 600–608, 2019.

W. S. Nugroho et al., “Aplikasi Pengolahan Citra Digital untuk Klasifikasi Kematangan Buah,” Jurnal Teknik Informatika, vol. 10, no. 1, pp. 15–20, 2022.

A. E. Rachman and L. P. Putra, “Ekstraksi Warna RGB dan HSV pada Pengolahan Citra Buah,” Jurnal Ilmu Komputer dan Informatika, vol. 5, no. 3, pp. 45–52, 2021.

Y. Li, “Analysis of Color Space Conversion for Fruit Classification,” IEEE Access, vol. 7, pp. 14299–14307, 2019.

N. A. Fauzi and M. I. Fadlillah, “Analisis RGB dan HSV untuk Deteksi Warna Objek,” Jurnal Pengolahan Citra, vol. 3, no. 2, pp. 67–74, 2020.

Y. Zhang et al., “Comparative Study of Machine Learning Algorithms for Fruit Classification,” International Journal of Advanced Computer Science and Applications, vol. 11, no. 2, pp. 112–118, 2020.

S. P. Dewi et al., “Klasifikasi Kematangan Buah Pisang Menggunakan Metode KNN,” Jurnal Teknologi dan Sistem Komputer, vol. 8, no. 1, pp. 44–49, 2020.

H. B. Santosa et al., “Pengenalan Kematangan Mangga Berdasarkan Citra Digital,” Jurnal Informatika, vol. 16, no. 2, pp. 93–100, 2019.

X. Zhang et al., "Deep learning-based image classification: A survey," Pattern Recognition, vol. 110, 2021.

J. Han et al., Data Mining: Concepts and Techniques, 4th ed., Elsevier, 2022.

M. H. Rashid et al., "Maturity detection of coconut using machine learning," Computers and Electronics in Agriculture, vol. 190, 2021.

T. Cover and P. Hart, "Nearest neighbor pattern classification," IEEE Trans. Inf. Theory, vol. 13, no. 1, pp. 21–27, 1967.

S. Dasarathy, "Nearest neighbor (NN) norms: NN pattern classification techniques," IEEE CS Press, 1991.

R. O. Duda et al., Pattern Classification, 2nd ed., Wiley, 2001.

L. Rokach and O. Maimon, Data Mining with Decision Trees: Theory and Applications, 2nd ed., World Scientific, 2015.

A. Beygelzimer et al., "Cover trees for nearest neighbor," ICML, 2006.

S. Arya et al., "An optimal algorithm for approximate nearest neighbor searching," J. ACM, vol. 45, no. 6, pp. 891–923, 1998.

R. Bellman, Adaptive Control Processes: A Guided Tour, Princeton, 1961.

K. Q. Weinberger et al., "Distance metric learning for large margin nearest neighbor classification," NIPS, 2005.

I. Jolliffe, Principal Component Analysis, Springer, 2002.

C. Zhang et al., "Weighted kNN for imbalanced data," Pattern Recognition, vol. 75, pp. 407–419, 2018.

R. Polikar, "Ensemble based systems in decision making," IEEE Circuits Syst. Mag., vol. 6, no. 3, pp. 21–45, 2006.

M. Hossain et al., "Feature extraction techniques for image recognition," IJCSIT, vol. 6, no. 1, 2015.

M. Rahman et al., "Mango maturity classification using machine vision," Biosystems Engineering, vol. 172, 2018.

A. Prasetyo et al., "Coffee bean quality classification using KNN," Procedia Computer Science, vol. 157, 2019.

E. Setiawan et al., "Coconut maturity classification using KNN," ICoICT, 2020.

C. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.

S. A. T. Al-Antari et al., "Breast cancer detection using deep learning and KNN," Computers in Biology and Medicine, vol. 98, 2018.

Y. Liu et al., "Anomaly detection with nearest neighbor approaches," ACM Computing Surveys, vol. 55, no. 2, 2022

M. S. Rakhman and D. S. Putra, “Desain Sistem Akuisisi Citra untuk Klasifikasi Buah,” Jurnal Teknologi, vol. 10, no. 2, pp. 78–85, 2021.

D. S. Nugraha and E. W. Prasetyo, “Optimasi Resolusi Citra untuk Deteksi Objek Pertanian,” Jurnal Informatika Pertanian, vol. 5, no. 3, pp. 54–60, 2022.

H. C. Yeo et al., “Image Acquisition Techniques for Fruit Ripeness Classification,” Agricultural Engineering International: CIGR Journal, vol. 22, no. 4, pp. 112–121, 2020.

G. Gonzales and R. Woods, Digital Image Processing, 4th ed. Pearson, 2018.

M. Kusuma et al., “Segmentasi Buah Berdasarkan Warna HSV Menggunakan Threshold dan Morphology,” Jurnal Pengolahan Citra Digital, vol. 4, no. 2, pp. 65–71, 2021.

A. Permata and I. Syarif, “Evaluasi Akurasi Segmentasi Objek Buah Berdasarkan Warna,” Jurnal Ilmiah Teknologi Informasi Asia, vol. 12, no. 1, pp. 23–30, 2022.

S. P. Dewi et al., “Ekstraksi Fitur Warna untuk Pengenalan Kematangan Buah,” Jurnal Teknik Komputer, vol. 10, no. 1, pp. 55–62, 2020.

Y. Li, “Comparative Study of RGB and HSV Features for Fruit Classification,” IEEE Access, vol. 7, pp. 22980–22989, 2019.

A. Hamdani and T. Yuliana, “Efek Normalisasi pada Model Klasifikasi KNN Berbasis Warna,” Jurnal Teknologi Informasi dan Komputer, vol. 6, no. 2, pp. 89–95, 2022.

T. Cover and P. Hart, “Nearest Neighbor Pattern Classification,” IEEE Transactions on Information Theory, vol. 13, no. 1, pp. 21–27, 1967.

F. Pedregosa et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.

S. Harjoko et al., “Evaluasi Algoritma KNN dan SVM untuk Klasifikasi Buah Berdasarkan Warna dan Tekstur,” Jurnal Ilmiah Komputer dan Informatika, vol. 11, no. 3, pp. 45–52, 2020.

Analisis Citra Digital untuk Klasifikasi Kematangan Kelapa Menggunakan K-Nearest Neighbor

Authors

DOI:

Keywords:

Abstract

Downloads

References

Downloads

Published

How to Cite

Issue

Section

License