Analisis Komparasi Kinerja Arsitektur MobileNetV3 dan EfficientNet-Lite untuk Klasifikasi Penyakit Padi pada Citra Resolusi Rendah

Dading Oktaviadi Resmiranta

doi:10.30591/jpit.v11i2.10098

Analisis Komparasi Kinerja Arsitektur MobileNetV3 dan EfficientNet-Lite untuk Klasifikasi Penyakit Padi pada Citra Resolusi Rendah

Dading Oktaviadi Resmiranta

Abstract

National food security relies heavily on rapid and accurate control of rice plant diseases. However, the implementation of automatic detection technology at the farmer level is often hampered by low image quality due to the use of low-spec mobile phone cameras and data compression in areas with poor signal. This study aims to evaluate the performance of two lightweight Deep Learning architectures, MobileNetV3-Small and EfficientNet-Lite, in classifying rice diseases under low-resolution image conditions. The research method applies a simulation of resolution degradation to 128x128 pixels on a dataset consisting of four classes: Blast, Blight, Brown Spot, and Healthy. Empirical test results show that EfficientNet-Lite is significantly superior in diagnostic accuracy with an accuracy of 95.67%, a precision of 95.65%, and a recall of 95.33%. In contrast, MobileNetV3-Small achieved an accuracy of 89.00%, yet offered superior computational efficiency: a model size of only 11.97 MB (73% smaller than EfficientNet-Lite's 45.48 MB) and an inference speed of 4.67 milliseconds per image, equivalent to 214 frames per second (FPS). The study concluded that EfficientNet-Lite is recommended for high-precision diagnostic systems, while MobileNetV3-Small is the most adaptive solution for real-time applications on storage-constrained mobile devices.

Keywords

Deep Learning; EfficientNet-Lite; Low Resolution; MobileNetV3; Rice Diseases

References

Food and Agriculture Organization (FAO), “Crops and livestock products: Rice production quantity,” FAOSTAT. Accessed: Jan. 01, 2026. [Online]. Available: https://www.fao.org/faostat

I. R. R. I. (IRRI), “Rice Knowledge Bank: Rice Doctor,” RRI. Accessed: Jan. 01, 2026. [Online]. Available: http://www.knowledgebank.irri.org

E. Said Mohamed, A. Belal, S. Kotb Abd-Elmabod, M. A. El-Shirbeny, A. Gad, and M. B. Zahran, “Smart farming for improving agricultural management,” Egypt. J. Remote Sens. Sp. Sci., vol. 24, no. 3, pp. 971–981, Dec. 2021, doi: 10.1016/j.ejrs.2021.08.007.

S. Sheila, I. Permata Sari, A. Bagas Saputra, M. Kharil Anwar, and F. Restu Pujianto, “Deteksi Penyakit Pada Daun Padi Berbasis Pengolahan Citra Menggunakan Metode Convolutional Neural Network (CNN),” MULTINETICS, vol. 9, no. 1, pp. 27–34, Apr. 2023, doi: 10.32722/multinetics.v9i1.5255.

M. Shoaib et al., “An advanced deep learning models-based plant disease detection: A review of recent research,” Front. Plant Sci., vol. 14, Mar. 2023, doi: 10.3389/fpls.2023.1158933.

B. Ramana Reddy, G. Kalnoor, M. Devashish, and P. Sai Karthik Reddy, “Deep Learning Based Mobile Application for Automated Plant Disease Detection,” IEEE Access, vol. 13, pp. 107917–107925, 2025, doi: 10.1109/ACCESS.2025.3581099.

K. N, L. V. Narasimha Prasad, C. S. Pavan Kumar, B. Subedi, H. B. Abraha, and S. V E, “Rice leaf diseases prediction using deep neural networks with transfer learning,” Environ. Res., vol. 198, p. 111275, Jul. 2021, doi: 10.1016/j.envres.2021.111275.

A. Dheeraj and S. Chand, “LWDN: lightweight DenseNet model for plant disease diagnosis,” J. Plant Dis. Prot., vol. 131, no. 3, pp. 1043–1059, Jun. 2024, doi: 10.1007/s41348-024-00915-z.

I. C. Sari, “Integrasi Model Deep Learning Efficientnet-B0 Untuk Deteksi Penyakit Daun Tomat Pada Aplikasi Seluler Berbasis Flutter,” Djtechno J. Teknol. Inf., vol. 5, no. 2, pp. 332–346, 2024, doi: 10.46576/djtechno.v5i2.4651.

Mas Nurul Achmadiah, Novendra Setiawan, and A. D. Risdhayanti, “Perbandingan Efisiensi Vision Transformer dan MobileNet untuk Optimasi Deteksi Objek di Edge Device,” J. Elektron. dan Otomasi Ind., vol. 12, no. 2, pp. 346–353, 2025, doi: 10.33795/elkolind.v12i2.8730.

M. T. Roseno, S. Oktarina, Y. Nearti, H. Syaputra, and N. Jayanti, “Comparing CNN Models for Rice Disease Detection: ResNet50, VGG16, and MobileNetV3-Small,” J. Inf. Syst. Informatics, vol. 6, no. 3, pp. 2099–2109, Sep. 2024, doi: 10.51519/journalisi.v6i3.865.

J. Padhi, K. Mishra, A. K. Ratha, S. K. Behera, P. K. Sethy, and A. Nanthaamornphong, “Enhancing paddy leaf disease diagnosis -a hybrid CNN model using simulated thermal imaging,” Smart Agric. Technol., vol. 10, p. 100814, Mar. 2025, doi: 10.1016/j.atech.2025.100814.

Mohammad Haydir Awaludin Waskito, Andreas Nugroho Sihananto, and Achmad Junaidi, “Klasifikasi Penyakit Kronis Melalui Mata Menggunakan Algoritma Convolutional Neural Network Dengan Model MobileNet-V3,” Uranus J. Ilm. Tek. Elektro, Sains dan Inform., vol. 2, no. 2, pp. 48–60, 2024, doi: 10.61132/uranus.v2i2.120.

B. Khomkham and Y. Pankaseam, “Lightweight Convolutional Neural Network Model Based on Modified MobileNetV3 for Plant Disease Classification,” SN Comput. Sci., vol. 6, no. 8, p. 1028, Dec. 2025, doi: 10.1007/s42979-025-04607-9.

M. Aboh, “Benchmarking EfficientNet, MobileNet and ResNet Architectures for Cassava Disease Detection in Agricultural Robotics,” J. Eng. Res. Reports, vol. 27, no. 10, pp. 380–387, Oct. 2025, doi: 10.9734/jerr/2025/v27i101680.

Y. Gu, “Lightweight CNN Architectures for Low-Cost Smart Cameras : A,” vol. 23, no. 6, 2025.

Harsanto, A. I. Pradana, and B. Wahyu Pamekas, “Optimalisasi Akurasi Model Identifikasi Penyakit Pada Daun Padi Dengan Fine-Tuning YOLOv11 Untuk Ketahanan Pangan Berkelanjutan,” J. Algoritm., vol. 22, no. 2, Nov. 2025, doi: 10.33364/algoritma/v.22-2.2945.

D. O. Resmiranta, B. Krismono, and K. Hidjah, “Facial image recognition using hybrid filtering models and convolutional neural networks ( CNNs ),” pp. 61–73, 2025.

DOI: https://doi.org/10.30591/jpit.v11i2.10098