KLASIFIKASI PENYAKIT DAUN PISANG MENGGUNAKAN METODE  K-NEAREST NEIGHBOR (KNN) BERBASIS EKSTRAKSI FITUR WARNA DAN TEKSTUR

Suranto .; Martanto .; Denni Pratama; Agus Bahtiar; Riri Narasati

Authors

Suranto . STMIK IKMI Cirebon, Indonesia
Martanto . STMIK IKMI Cirebon, Indonesia
Denni Pratama STMIK IKMI Cirebon, Indonesia
Agus Bahtiar STMIK IKMI Cirebon, Indonesia
Riri Narasati STMIK IKMI Cirebon, Indonesia

Keywords:

Penyakit Daun Pisang, K-Nearest Neighbor, HSV, HOG, Klasifikasi, Pembelajaran Mesin

Abstract

Daun pisang rentan terhadap berbagai penyakit merusak seperti Black Sigatoka, Cordana, dan Pestalotiopsis yang menyebabkan penurunan hasil panen secara signifikan [1][2]. Penelitian ini mengembangkan model klasifikasi penyakit daun pisang menggunakan algoritma K-Nearest Neighbor (KNN) dengan ekstraksi fitur warna dan tekstur berbasis model warna HSV [3] dan Histogram of Oriented Gradients [4]. Dataset BananaLSD [5] digunakan sebagai dataset utama. Proses penelitian meliputi tahapan prapemrosesan seperti perubahan ukuran, penghilangan noise, segmentasi, dan augmentasi [6], ekstraksi fitur, penggabungan fitur, normalisasi, serta pelatihan model KNN dengan beberapa nilai k dan metrik jarak [7]. Hasil pengujian menunjukkan bahwa model mencapai akurasi 96,17%, presisi 94,8%, recall 95,2%, dan F1-score 95%. Kombinasi fitur HSV dan HOG dengan KNN terbukti memberikan performa klasifikasi yang tinggi dengan kebutuhan komputasi rendah, sehingga sesuai untuk sistem pertanian skala kecil dengan keterbatasan sumber daya [8].

References

A. C. Soares, J. C. Pereira, and R. S. Lima, “Impact of Black Sigatoka on photosynthetic activity and yield performance in banana plantations,” Journal of Plant Pathology, vol. 103, no. 4, 2021, doi: 10.1007/s42161-021-00850-7.

R. D. Noar and L. Da Silva, “Foliar diseases of banana and their effect on crop productivity: A comprehensive review,” Plant Disease Review, vol. 15, no. 2, 2022.

N. Ahmad, H. M. S. Asif, G. Saleem, M. U. A. U. 0-A. Younus S., and M. R. Anjum, “Leaf image‐based plant disease identification using color and texture features,” Wireless Personal Communications, vol. 121, no. 2, pp. 1139–1168, 2021, doi: 10.1007/s11277-021-09054-2.

N. Dalal and B. Triggs, “Histograms of Oriented Gradients for Human Detection,” 2005.

S. E. Arman, M. A. B. Bhuiyan, H. M. Abdullah, S. Islam, T. T. Chowdhury, and M. A. Hossain, “Banana Leaf Spot Diseases (BananaLSD): A banana leaf images dataset for classification of banana leaf diseases using machine learning,” Data in Brief, vol. 50, 2023, doi: 10.1016/j.dib.2023.109608.

L. Pérez and J. Wang, “The effectiveness of data augmentation in image classification using deep learning,” Neural Networks, vol. 95, pp. 1–10, 2017, doi: 10.1016/j.neunet.2017.08.012.

X. Zhang and J. Wang, “Improved KNN classifier for agricultural leaf disease recognition,” Applied Soft Computing, vol. 113, p. 107931, 2021, doi: 10.1016/j.asoc.2021.107931.

D. Demilie, “Hybrid HOG–CNN feature extraction for plant disease classification: A comparative study,” Frontiers in Plant Science, vol. 15, 2024, doi: 10.3389/fpls.2024.1452201.

H. Fan, X. Zhong, and P. Li, “Yield losses caused by Fusarium Wilt and Xanthomonas Wilt in tropical banana production systems,” Agricultural Systems, vol. 178, p. 102741, 2020, doi: 10.1016/j.agsy.2019.102741.

H. Lee, S. Park, and J. Lim, “Fusion of color and texture descriptors for improved plant leaf disease classification,” Expert Systems with Applications, vol. 235, p. 121156, 2024, doi: 10.1016/j.eswa.2023.121156.

X. Xu, Y. Zheng, and F. Liu, “Limitations of convolutional neural networks on small-scale agricultural image datasets,” Artificial Intelligence Review, vol. 56, 2023, doi: 10.1007/s10462-022-10234-9.

T. Cover and P. Hart, “Nearest neighbor pattern classification,” IEEE Transactions on Information Theory, vol. 13, no. 1, pp. 21–27, 1967, doi: 10.1109/TIT.1967.1053964.

A. Ioannidis, C. Georgiou, and G. Papadakis, “Performance of vision transformers and CNNs on plant disease recognition under varied field conditions,” Computers and Electronics in Agriculture, vol. 212, p. 108187, 2024, doi: 10.1016/j.compag.2024.108187.

B. Zhao, J. Hu, and G. Li, “Texture-based plant disease detection using HOG and SVM: A lightweight approach for mobile agriculture systems,” Computers and Electronics in Agriculture, vol. 193, p. 106700, 2022, doi: 10.1016/j.compag.2021.106700.

J. Görtler et al., “Neo: Generalizing confusion matrix visualization to hierarchical and multi-output labels,” ACM Transactions on Interactive Intelligent Systems, vol. 12, no. 4, p. Article 32, 2022, doi: 10.1145/3491102.3501823.