Application of Computer Vision for Digital Encyclopedia of Chili Varieties (Capsicum spp.)

Muhammad Viqih Zamzami; Zilvanhisna Emka Fitri; Abdul Madjid; Arizal Mujibtamana Nanda Imron

doi:10.36526/jeee.v3i1.3831

Muhammad Viqih Zamzami Politeknik Negeri Jember
Zilvanhisna Emka Fitri Politeknik Negeri Jember https://orcid.org/0000-0002-5156-3677
Abdul Madjid Politeknik Negeri Jember
Arizal Mujibtamana Nanda Imron Universitas Jember https://orcid.org/0000-0002-1048-8607

DOI: https://doi.org/10.36526/jeee.v3i1.3831

Keywords: Chilli, Computer Vision, Naive Bayes

Abstract

Chili is a vegetable commodity that has high economic value so that its production always increases every year. Several types of chilies are cultivated in Indonesia, namely cayenne pepper (Capsicum frutescens), curly red chili (Capsicum annuum L. var. longum), large red chili (Capsicum annuum L.) and paprika (Capsicum annuum var. grossum). Indonesia is a country that continues to develop innovation to produce many superior varieties, especially chilli plants. The problem arises that variations of other superior chili varieties can only be accessed through the official website of the ministry of agriculture, however, the data that can be accessed is limited (in the form of descriptions of chili varieties without physical appearance such as photos) so that it is quite difficult for the community and farmers to cultivate or utilize these varieties. This made researchers develop a digital encyclopedia of chili types using computer vision. This study uses a combination of digital image processing and intelligent systems. The image processing used is preprocessing such as cropping and splitting of RGB components, image segmentation and shape feature extraction. The features used are area, perimeter, major axis length, minor axis length and eccentricity. This feature is the input of the Naïve Bayes method which produces a system accuracy rate of 92%.

Author Biographies

Muhammad Viqih Zamzami, Politeknik Negeri Jember

Department of Informatic Technology

Abdul Madjid, Politeknik Negeri Jember

Department of Agriculture Production

Arizal Mujibtamana Nanda Imron, Universitas Jember

Department of Electrical Engineering

References

[1] P. Tripodi dan S. Kumar, “The Capsicum Crop: An Introduction,” dalam The Capsicum Genome, N. Ramchiary dan C. Kole, Ed., New Delhi: Springer, 2019, hlm. 1–8. [Daring]. Tersedia pada: http://www.springer.com/series/11805
[2] M. Syukur, R. Yunianti, dan R. Dermawan, Budidaya Cabai Panen Setiap Hari. Penebar Swadaya Grup, 2012.
[3] BPS Indonesia, “Statistik Hortikultura 2021,” Jakarta, Jun 2022.
[4] Z. E. Fitri, R. Aprilia, A. Madjid, dan A. M. N. Imron, “Ensiklopedia Digital Berdasarkan Klasifikasi Varietas Buah Mangga (Mangifera spp.) Menggunakan Algoritma Backpropagation,” Komputika : Jurnal Sistem Komputer, vol. 11, no. 2, hlm. 113–120, Feb 2022, doi: 10.34010/komputika.v11i2.5513.
[5] N. T. Anggraeni dan A. Fadlil, “Sistem Identifikasi Citra Jenis Cabai (Capsicum Annum L.) Menggunakan Metode Klasifikasi City Block Distance,” Jurnal Sarjana Teknik Informatika, vol. 1, no. 2, hlm. 409–418, 2013.
[6] M. A. Aldiansyah, “PEMROSESAN CITRA DIGITAL UNTUK KLASIFIKASI TANAMAN CABAI MENGGUNAKAN JARINGAN SARAF TIRUAN BACKPROPOGATION,” Jurnal Teknologi Informasi dan Terapan, vol. 5, no. 1, hlm. 31–36, Apr 2019, doi: 10.25047/jtit.v5i1.76.
[7] I. Perlindungan dan Risnawati, “PENGENALAN TANAMAN CABAI DENGAN TEKNIK KLASIFIKASI MENGGUNAKAN METODE CNN,” dalam Seminar Nasional Mahasiswa Ilmu Komputer dan Aplikasinya (SENAMIKA), Jakarta, Agu 2020, hlm. 15–22.
[8] D. Suryani, W. I. Sabilla, dan H. L. Wicaksono, “Identifikasi Kualitas Cabai Berdasarkan Warna dan Tekstur Dengan Menggunakan Metode K-Nearest Neighbor,” dalam Seminar Informatika Aplikatif Polinema (SIAP), 2020, hlm. 438–443.
[9] Khairullah dan E. D. Putra, “Identifikasi Kematangan Cabai Menggunakan Operasi Morfologi (Opening dan Closing) dan Metode Backpropagation,” Jurnal Sistem Informasi (SISTEMASI), vol. 10, no. 1, hlm. 96–105, 2021, [Daring]. Tersedia pada: http://sistemasi.ftik.unisi.ac.id
[10] S. Suhirman, A. D. Kalifia, S. Sumarsono, dan M. S. Aslam, “Identifikasi Penyakit Tanaman Cabai Menggunakan Teorema Bayes,” Jurnal Teknologi Informasi dan Komunikasi (FIKI), vol. XII, no. 1, hlm. 1–8, 2022, [Daring]. Tersedia pada: http://jurnal.unnur.ac.id/index.php/jurnalfiki
[11] Z. E. Fitri, M. Silvia, A. Madjid, A. M. N. Imron, dan L. N. Sahenda, “Red Dragon Fruit (Hylocereus costaricensis) Ripeness Color Classification by Naive Bayes Algorithm,” Applied Technology and Computing Science Journal, vol. 5, no. 1, hlm. 21–28, Jun 2022.
[12] Z. E. Fitri, A. Baskara, A. Madjid, dan A. M. N. Imron, “Comparison of Classification for Grading Red Dragon Fruit (Hylocereus Costaricensis),” Jurnal Nasional Teknik Elektro, vol. 11, no. 1, hlm. 43–49, 2022, doi: 10.25077/jnte.v11n1.899.2022.

[13] Abd. Ghofur, “Implementasi Metode Klasifikasi Naive Bayes Untuk Memprediksi Kualitas Cabai,” Jurnal Ilmiah Informatika, vol. 1, no. 1, hlm. 32–38, 2016, doi: 10.35316/jimi.v1i1.441.
[14] A. Dekebo, Capsicum. United Kingdom: IntechOpen, 2020.
[15] A. R. Firdaus, M. Lutfi, dan M. F. Amrulloh, “Klasifikasi Jenis Tanaman Kelengkeng Berdasarkan Ciri Tekstur Daun Menggunakan Metode Adaptive Neuro Fuzzy Inference System (AFIS),” EXPLORE IT, vol. 14, no. 1, hlm. 29–38, 2022, doi: 10.35891/explorit.
[16] B. Adi Prasetya dkk., “Ensiklopedia Digital Varietas Ubi Jalar Berdasarkan Klasifikasi Citra Daun Menggunakan K-Nearest Neighbor,” Elektrika, vol. 14, no. 1, hlm. 1–6, 2022.
[17] Z. E. Fitri, A. Baskara, A. Madjid, dan A. M. N. Imron, “Comparison of Classification for Grading Red Dragon Fruit (Hylocereus Costaricensis),” JURNAL NASIONAL TEKNIK ELEKTRO, vol. 11, no. 1, hlm. 43–49, Mar 2022, doi: 10.25077/jnte.v11n1.899.2022.
[18] U. Hasna, A. Cendekia Siregar, dan B. C. Octariadi, “Klasifikasi Bentuk Daun Tanaman Begonia (Begoniaceae) Menggunakan Metode K-Nearest Neigbhor,” DIGITAL INTELLIGENT, vol. 3, no. 1, hlm. 57–64, 2022, doi: 10.29406/diligent.v3i1.4809.