Classification of Tomato Fruit Image Ripeness Based on Color Feature Extraction Using the K-NN Method
DOI:
https://doi.org/10.33379/gtech.v8i3.4539Keywords:
K-Nearest Neighbor, Maturity Classification, Color Feature ExtractionAbstract
Tomatoes are a vegetable commodity that has high economic value and is widely consumed by the public. Tomato ripeness plays an important role in determining the quality and durability of tomato products. The process of ripening tomatoes only takes a short time. To overcome this problem, researchers used the K-NN method to classify tomato fruit ripeness based on color feature extraction. In the process of classifying the maturity level of tomatoes, 150 datasets from 3 different maturity classes are used, namely 50 ripe, 50 ripe and 50 unripe. The 150 datasets were divided into 90 training data and 60 test data. The classification results using K-NN show the optimal value, namely k=5 with an accuracy of 98.33%.
References
Amalia, R. (2021). Pelengkap Makanan, Kenali 9 Jenis Tomat Ini, Yuk! Diakses dari https://www.idntimes.com/food/diet/regina-amalia/pelengkap-makanan-kenali-9-jenis-tomat-ini-yuk-c1c2?page=all
Arsy, L., Nurhayati, O. D., & Martono, K. T. (2016). Aplikasi Pengolahan Citra Digital Meat Detection Dengan Metode Segmentasi K-Mean Clustering Berbasis OpenCV Dan Eclipse. Jurnal Teknologi Dan Sistem Komputer, 4(2), 322. https://doi.org/10.14710/jtsiskom.4.2.2016.322-332
Fernando Ade Pratama, E., Khairil, & Jumadi, J. (2022). Implementasi Metode K-Means ClusteringPada Segmentasi Citra Digital. Jurnal Media Infotama, 18(2), 291–301.
Ghazali, M. I. N., Subha, E. K., Galuh, M., & Burhannudin, M. (2018). Aplikasi Kematangan Tomat Berdasarkan Warna dengan Metode Linear Discriminant Analysis (LDA). Jurnal Informatika.
Id, I. D. (2021). MACHINE LEARNING : Teori, Studi Kasus dan Implementasi Menggunakan Python (Edisi 1). UR PRESS. https://www.google.co.id/books/edition/_/JvBPEAAAQBAJ?hl=id&gbpv=1&pg=PA133&dq=teori+knn
Johan, T. M., & Rifna, I. (2022). Identifikasi Kematangan Buah Tomat Berdasarkan Warna Menggunakan Metode Jaringan Syaraf Tiruan (Jst) Backpropagation. Jurnal TIKA, 7(3), 309–315. https://doi.org/10.51179/tika.v7i3.1647
Maulana Alfaruq, B., Erwanto, D., & Yanuartanti, I. (2023). Klasifikasi Kematangan Buah Tomat Dengan Metode Support Vector Machine. Generation Journal, 7(3), 64–72. https://doi.org/10.29407/gj.v7i3.21092
Muhammad, D. I., Ermatita, E., & Falih, N. (2021). Penggunaan K-Nearest Neighbor (KNN) untuk Mengklasifikasi Citra Belimbing Berdasarkan Fitur Warna. Informatik : Jurnal Ilmu Komputer, 17(1), 9. https://doi.org/10.52958/iftk.v17i1.2132
Neighhbor, M. K., & Aprilisa, S. (2019). Klasifikasi Tingkat Kematangan Buah Tomat Berdasarkan Fitur Warna. Prosiding Annual Research Seminar 2019, 5(1), 978–979.
Riska, S. Y. (2015). Klasifikasi Level Kematangan Tomat Berdasarkan Perbedaan Perbaikan Citra Menggunakan Rata-Rata RGB Dan Index Pixel. Jurnal Ilmiah Teknologi Informasi Asia, 9(2), 18–26.
Riska, S. Y., & Subekti, P. (2016). Klasifikasi Level Kematangan Buah Tomat Berdasarkan Fitur Warna Menggunakan Multi-Svm. Jurnal Ilmiah Informatika, 1(1), 39–45. https://doi.org/10.35316/jimi.v1i1.442
Rizky, T. P. (2015). Klasifikasi Mutu Telur Berdasarkan Kebersihan. October, 241–245.
Safrizal, S. (2019). Pengenalan Karakter Jawi Tulisan Tangan Menggunakan Fitur Sudut. VOCATECH: Vocational Education and Technology Journal, 1. https://doi.org/10.38038/vocatech.v1i0.1
Sari, P., Muflikah, L., & Wihandika, R. C. (2018). Klasifikasi Kualitas Susu Sapi Menggunakan Metode Support Vector Machine ( SVM ). Jurnal Pengembangan Teknologi Informasi Dan Ilmu Komputer (J-PTIIK), 2(3), 1204–1211.
Sinaga, A. S. R. (2017). Implementasi Teknik Threshoding Pada Segmentasi Citra Digital. Jurnal Mantik Penusa, 1(2), 48–51.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Ahmad Badri Maulana Widat, Achmad Baijuri, Farihin Lazim
This work is licensed under a Creative Commons Attribution 4.0 International License.
