Klasifikasi Citra Kualitas Beras Akurasi Tinggi Menggunakan Transfer Learning Arsitektur Mobilenetv2

Muhammad Febrian Haekal; Tomi Tri Sujaka; Fahry Fahry

doi:10.31004/riggs.v5i2.12829

Authors

Muhammad Febrian Haekal Universitas Bumigora
Tomi Tri Sujaka Universitas Bumigora
Fahry Fahry Universitas Bumigora

DOI:

https://doi.org/10.31004/riggs.v5i2.12829

Keywords:

Klasifikasi Mutu Beras, Antarmuka Web, MobileNetV2, Akurasi Superior

Abstract

Penilaian mutu beras secara konvensional yang mengandalkan inspeksi visual kerap menghasilkan evaluasi subjektif, inkonsisten, serta memakan waktu lama. Untuk mengatasi kendala tersebut, penelitian ini bertujuan mengembangkan model komputasi cerdas berbasis web guna mengklasifikasikan kualitas beras secara otomatis dan praktis. Dataset yang digunakan dalam eksperimen terdiri atas 926 citra beras publik yang diekstraksi dari Roboflow Universe. Pendekatan penelitian memanfaatkan algoritma Convolutional Neural Network (CNN) berarsitektur MobileNetV2 yang dioptimasi menggunakan metode Transfer Learning dan Fine-Tuning. Tahapan utama pengembangan mencakup prapemrosesan citra, pelatihan model dengan differential learning rates, hingga integrasi sistem menggunakan kerangka kerja backend asinkron FastAPI. Hasil implementasi menunjukkan bahwa sistem sukses berjalan pada antarmuka web interaktif untuk membedakan kategori beras premium, medium, dan tidak layak tanpa kendala latensi komputasi. Pengujian model mencatatkan performa sangat superior dengan nilai akurasi dan metrik Weighted F1-Score yang mencapai 98,92%. Kesimpulannya, pemanfaatan arsitektur ringan MobileNetV2 terbukti efisien secara komputasi serta mumpuni memberikan solusi praktis bagi pelaku industri untuk melakukan kontrol kualitas beras secara objektif tanpa harus mengandalkan keahlian pakar.

Downloads

Download data is not yet available.

References

1. Chelsya Dwi Marnelius, Koredianto Usman, & Nor Kumalasari Caecar Pratiwi. (2023). Klasifikasi Jenis Beras Berbasis Citra Dengan Menggunakan Deep Learning.

2. Din, N. M. U., Assad, A., Dar, R. A., Rasool, M., Sabha, S. U., Majeed, T., Islam, Z. U., Gulzar, W., & Yaseen, A. (2024). RiceNet: A deep convolutional neural network approach for classification of rice varieties. Expert Systems with Applications, 235, 121214. https://doi.org/10.1016/J.ESWA.2023.121214

3. Hastari, N. P., Rohana, T., Masruriyah, A. F. N., & Wahiddin, D. (2024). CLASSIFICATION OF RICE ELIGIBILITY BASED ON INTACT AND NON-INTACT RICE SHAPES USING YOLO V8-BASED CNN ALGORITHM. Jurnal Teknik Informatika (Jutif), 5(5), 1309–1318. https://doi.org/10.52436/1.jutif.2024.5.5.2413

4. Helmiyah, S., Pramestiawan, R., Studi Pendidikan Informatika, P., & Tinggi Keguruan dan Ilmu Pendidikan Rosalia Lampung, S. (2025). Analisis Komparatif Algoritma Machine Learning dengan Metrik Akurasi, Presisi, Recall, dan F1-Score pada Dataset Kacang Kering. 6(3), 152–159. https://doi.org/10.35960/ikomti.v6i3.2031

5. Khatib Sulaiman, J., Muhammad, F., Murni Arimurthy, A., Chahyati, D., & Artikel Abstrak, I. (n.d.). Transfer Learning dengan Metode Fine Tuning pada Model Network VGG16 dan ResNet50. Indonesian Journal of Computer Science Attribution, 12(1), 361.

6. Noprisson, H. (2022). Fine-Tuning Model Transfer Learning VGG16 Untuk Klasifikasi Citra Penyakit Tanaman Padi. JSAI: Journal Scientific and Applied Informatics, 5(3). https://doi.org/10.36085

7. Purwono, Ma’arif, A., Rahmaniar, W., Fathurrahman, H. I. K., Frisky, A. Z. K., & Haq, Q. M. U. (2022). Understanding of Convolutional Neural Network (CNN): A Review. International Journal of Robotics and Control Systems, 2(4), 739–748. https://doi.org/10.31763/ijrcs.v2i4.888

8. Suminar1, R., Hidayat2, B., & Atmaja3, R. D. (n.d.). KLASIFIKASI KUALITAS BERAS BERDASARKAN CIRI FISIK BERBASIS PENGOLAHAN CITRA DIGITAL. Retrieved www.tcpdf.org

9. Wayan Ruspendi Junaedi, O. I., Wayan Damayana, I., Waruwu, D., Nyoman Wiratanaya, G., Stevan Eka Putra, P., & Dhyana Pura, U. (n.d.). MODEL PEMBERDAYAAN EKONOMI UMKM MASYARKAT ADAT PAPUA DALAM PENANGANAN RISIKO OPERASIONAL MELALUI PEMASARAN BERAS. Retrieved http://ejurnal.binawakya.or.id/index.php/MBI

10. Yusuf, M., Ruimassa, R., Tawainella, A. I., & Maharani, D. (2024). KLASIFIKASI KUALITAS BERAS MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK BERBASIS ANDROID. Jurnal Komputer Dan Informatika, 12(2), 186–192. https://doi.org/10.35508/jicon.v12i2.18004

11. Aznan, A., Gonzalez Viejo, C., Pang, A., & Fuentes, S. (2021). Computer vision and machine learning analysis of commercial rice grains: A potential digital approach for consumer perception studies. Sensors, 21(19), 6354. https://doi.org/10.3390/s21196354

12. de Oliveira Carneiro, L., Coradi, P. C., Rodrigues, D. M., Lima, R. E., Teodoro, L. P. R., Santos de Moraes, R., Teodoro, P. E., Nunes, M. T., Leal, M. M., Lopes, L. R., Vendrusculo, T. A., Robattini, J. C., Soares, A. H., & dos Santos Bilhalva, N. (2023). Characterizing and predicting the quality of milled rice grains using machine learning models. AgriEngineering, 5(3), 1196-1215. https://doi.org/10.3390/agriengineering5030076

13. Díaz-Martínez, V., Orozco-Sandoval, J., Manian, V., Dhatt, B. K., & Walia, H. (2023). A deep learning framework for processing and classification of hyperspectral rice seed images grown under high day and night temperatures. Sensors, 23(9), 4370. https://doi.org/10.3390/s23094370

14. Farahnakian, F., Sheikh, J., Farahnakian, F., & Heikkonen, J. (2024). A comparative study of state-of-the-art deep learning architectures for rice grain classification. Journal of Agriculture and Food Research, 15, 100890. https://doi.org/10.1016/j.jafr.2023.100890

15. Fatima, M., Khan, M. A., Sharif, M., Alhaisoni, M., Alqahtani, A., Tariqe, U., Kim, Y. J., & Chang, B. (2022). Two-stage intelligent DarkNet-SqueezeNet architecture-based framework for multiclass rice grain variety identification. Computational Intelligence and Neuroscience, 2022, 1339469. https://doi.org/10.1155/2022/1339469

16. Huang, S., Lu, Z., Shi, Y., Dong, J., Hu, L., Yang, W., & Huang, C. (2023). A novel method for filled/unfilled grain classification based on structured light imaging and improved PointNet++. Sensors, 23(14), 6331. https://doi.org/10.3390/s23146331

17. Iqbal, M. J., Aasem, M., Ahmad, I., Alassafi, M. O., Bakhsh, S. T., Noreen, N., & Alhomoud, A. (2023). On application of lightweight models for rice variety classification and their potential in edge computing. Foods, 12(21), 3993. https://doi.org/10.3390/foods12213993

18. Jeyaraj, P. R., Asokan, S. P., & Samuel Nadar, E. R. (2022). Computer-assisted real-time rice variety learning using deep learning network. Rice Science, 29(5), 489-498. https://doi.org/10.1016/j.rsci.2022.02.003

19. Jin, C., Zhou, X., He, M., Li, C., Cai, Z., Zhou, L., Qi, H., & Zhang, C. (2024). A novel method combining deep learning with the Kennard-Stone algorithm for training dataset selection for image-based rice seed variety identification. Journal of the Science of Food and Agriculture, 104(13), 8332-8342. https://doi.org/10.1002/jsfa.13668

20. Koklu, M., Cinar, I., & Taspinar, Y. S. (2021). Classification of rice varieties with deep learning methods. Computers and Electronics in Agriculture, 187, 106285. https://doi.org/10.1016/j.compag.2021.106285

21. Liang, Z., Xu, X., Yang, D., & Liu, Y. (2025). The development of a lightweight DE-YOLO model for detecting impurities and broken rice grains. Agriculture, 15(8), 848. https://doi.org/10.3390/agriculture15080848

22. Razavi, M., Mavaddati, S., & Koohi, H. (2024). ResNet deep models and transfer learning technique for classification and quality detection of rice cultivars. Expert Systems with Applications, 247, 123276. https://doi.org/10.1016/j.eswa.2024.123276

23. Ruslan, R., Khairunniza-Bejo, S., Jahari, M., & Ibrahim, M. F. (2022). Weedy rice classification using image processing and a machine learning approach. Agriculture, 12(5), 645. https://doi.org/10.3390/agriculture12050645

24. Sun, K., Zhang, Y.-J., Tong, S.-Y., Tang, M.-D., & Wang, C.-B. (2022). Study on rice grain mildewed region recognition based on microscopic computer vision and YOLO-v5 model. Foods, 11(24), 4031. https://doi.org/10.3390/foods11244031

25. Wang, C., Caragea, D., Kodadinne Narayana, N., Hein, N. T., Bheemanahalli, R., Somayanda, I. M., & Jagadish, S. V. K. (2022). Deep learning based high-throughput phenotyping of chalkiness in rice exposed to high night temperature. Plant Methods, 18, 9. https://doi.org/10.1186/s13007-022-00839-5

26. Wu, Z., Zhang, Y., Zhang, Z., Shen, F., Li, L., He, X., Zhong, H., & Zhou, Y. (2025). An improved YOLOv8n-based method for detecting rice shelling rate and brown rice breakage rate. Agriculture, 15(15), 1595. https://doi.org/10.3390/agriculture15151595