Implementation of Papaya Fruit Ripeness Detection System Using RGB Method

Authors

  • Krista Bella Dwi Rahayu Nur Widyasari POLITEKNIK NEGERI MALANG
  • Ulla Delfana Rosiani Politeknik Negeri Malang
  • Agung Nugroho Pramudhita Politeknik Negeri Malang

DOI:

https://doi.org/10.32664/smatika.v11i01.536

Keywords:

Benefit of Papaya Fruit, RGB Method, Image Processing

Abstract

To date, agriculture in Indonesia still uses a manual method to detect the ripeness of papaya fruits. Based on its characteristics, the source of the degree of fruit maturity is obtained from the raw, half ripe and ripe papaya fruit obtained from the farmer. Here after performing the implementation on the basis of the information obtained. To measure the logic for detecting the degree of fruit maturity, the RGB method here will be used. In accordance with what is needed, the results of the implementation itself should function well. Based on the calculation of the accuracy obtained on the system that was made it reached 50%.

References

J. F. Fauzi, H. Tolle dan R. K. Dewi, “Implementasi Metode RGB To HSV pada Aplikasi Pengenalan Mata Uang Kertas Berbasis Android untuk Tuna Netra,†Jurnal Pengembangan Teknologi dan Informasi dan Ilmu Komputer, pp. 2319-2325, 2018.

R.Kusumanto dan A. N. Tompunu, “Pengolahan Citra Digital Untuk Mendeteksi Obyek Menggunakan Pengolahan Warna Model Normalisasi RGB,†dalam Seminar Nasional Teknologi Informasi & Komunikasi Terapan, 2011.

I. dan M. , “Deteksi Kematangan Buah Pisang Berdasarkan Fitur Warna Citra Kulit Pisang Menggunakan Metode Transformaso Ruang Warna HIS,†JUITA, pp. 2086-9398;, 2017.

M. dan E. Nurraharjo, “Sistem Deteksi Kematangan Buah Alpukat Menggunakan Metode Pengolah Citra,†Dinamika Informatika, pp. 2086-9398;, 2019.

S. Jatmika dan D. Purnamasari, “Rancang Bangun Alat Pendeteksi Kematangan Buah Apel Dengan Menggunakan Metode Image Processing Berdasarkan Komposisi Warna,†Jurnal Ilmiah Teknologi dan Informasi ASIA, 2014.

E. F. Saraswita dan Sukemi, “Akurasi Klasifikasi Citra Digital Scenes RGB Menggunakan Model K-Nearest Neighbor dan Naive Bayes,†dalam ARS2019, Palembang, 2019.

Published

2021-06-30