Klasifikasi Kualitas Beras Menggunakan Convolutional Neural Network Berbasis Citra Digital
DOI:
https://doi.org/10.29407/tb2rb846Keywords:
Convolutional Neural Network, Klasifikasi Citra, Kualitas Beras, Pengolahan Citra DigitalAbstract
Kualitas beras merupakan faktor penting yang memengaruhi nilai jual dan kepuasan konsumen. Penilaian kualitas beras secara manual cenderung subjektif dan memerlukan waktu yang relatif lama, sehingga diperlukan metode otomatis yang lebih efisien dan objektif. Penelitian ini bertujuan untuk mengembangkan sistem klasifikasi kualitas beras berbasis pengolahan citra digital menggunakan metode Convolutional Neural Network (CNN) berbasis transfer learning dengan arsitektur MobileNetV2. Dataset yang digunakan terdiri dari citra beras yang dikelompokkan ke dalam tiga kelas, yaitu beras baik, beras sedang, dan beras rusak. Data dibagi menjadi data latih dan data uji dengan perbandingan 80% dan 20%. MobileNetV2 digunakan sebagai feature extractor, sedangkan lapisan klasifikasi terdiri dari fully connected layer dan fungsi aktivasi softmax. Hasil pengujian menunjukkan bahwa model yang diusulkan mampu mengklasifikasikan kualitas beras dengan tingkat akurasi sebesar 78% pada data uji, sehingga metode CNN berbasis MobileNetV2 dinilai cukup efektif untuk diterapkan pada sistem klasifikasi kualitas beras dengan jumlah dataset yang terbatas.
Downloads
References
[1] M. Köklü, İ. A. Özkan, and M. Sert, “Classification of rice varieties with deep learning methods,” Computers and Electronics in Agriculture, vol. 187, 2021, doi: 10.1016/j.compag.2021.106285.
[2] Simamora and T. Tanti, “Rice quality classification model using machine learning technique,” Journal of Artificial Intelligence and Engineering Applications, vol. 5, no. 1, pp. 1–10, 2025.
[3] Sharma, R. Patel, and S. Verma, “Intelligent rice quality assessment using hybrid CNN-clustering approach,” Discover Applied Sciences, vol. 7, no. 90, 2025, doi: 10.1007/s42452-025-07790-9.
[4] Rahman, M. Hossain, and N. Islam, “Exploring convolutional neural networks for rice grain classification,” arXiv preprint, 2025.
[5] S. Kumar and P. Singh, “An overall real-time mechanism for classification and quality evaluation of rice using deep learning,” arXiv preprint, 2025.
[6] L. Putra, “Rice quality mobile-based classification using convolutional neural network,” J-Icon: Jurnal Informatika dan Komputasi, vol. 9, no. 2, pp. 45–52, 2025.
[7] M. S. Ramadhan and D. Kurniawan, “Klasifikasi tekstur citra beras menggunakan convolutional neural network,” Techno Nusa Mandiri, vol. 22, no. 1, pp. 12–19, 2025.
[8] G. Budiono and R. Wirawan, “Classification of rice texture based on rice image using the convolutional neural network method,” Techno Nusa Mandiri, vol. 20, no. 2, pp. 102–107, 2023.
[9] Hermawan, M. Agustin, and D. Arnaldy, “Rice seedling image classification using light convolutional neural network,”
[10] Khazanah Informatika: Jurnal Ilmu Komputer dan Informatika, 2025.
[11] F. Elfaladonna et al., “Implementasi convolutional neural network untuk klasifikasi citra tiga jenis beras,” Journal of Science and Social Research, vol. 8, no. 3, 2025.
[12] Abdiansyah, Baharuddin, and M. S. Said, “Klasifikasi jenis beras menggunakan convolutional neural network pada arsitektur MobileNet,” Simtek: Jurnal Sistem Informasi dan Teknik Komputer, vol. 9, no. 2, 2025.
[13] R. Muzhaffar and I. Suharjo, “Penerapan convolutional neural network berbasis arsitektur ResNet-50 untuk klasifikasi citra beras organik dan non-organik,” Jurnal Pustaka Data, vol. 5, no. 2, 2025.
[14] Bhattacharjee et al., “A comparative study on rice grain classification using convolutional neural network and other machine learning techniques,” International Journal of Intelligent Systems and Applications in Engineering, 2025.
[15] W. Xia et al., “An overall real-time mechanism for classification and quality evaluation of rice,” arXiv preprint, 2025.
[16] Sharma et al., “A twin CNN-based framework for optimized rice leaf disease classification with feature fusion,” Journal of Big Data, vol. 12, no. 89, 2025, doi: 10.1186/s40537-025-01148-z.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Onkky Sandyka Mahendra, Ardan Putra Ramadhan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
