Implementasi Deep Learning Berbasis MobileNetV2 untuk Deteksi Real-Time Bacterial Spot dengan Pendekatan Arsitektur Lightweight
- Ahmad Nabilul As'ad Universitas Dian Nuswantoro, Semarang, Indonesia
-
Elkaf Rahmawan Pramudya
*
Universitas Dian Nuswantoro, Semarang,
Indonesia
(*) Corresponding Author
Abstract
Bacterial spot caused by Xanthomonas campestris pv. vesicatoria is a critical disease in bell peppers that can reduce productivity by up to 50%. This study implements MobileNetV2 with two-stage transfer learning for real-time bacterial spot detection using lightweight architecture approach, with ResNet50 as baseline comparison. PlantVillage dataset (2,475 images) was used for training and in-domain evaluation, while India dataset (132 images) for domain shift assessment. Results demonstrate MobileNetV2 achieves 98.66% accuracy on PlantVillage test set, outperforming ResNet50 (89.78%) by 8.88 percentage points despite being 9.2× lighter (2.7 MB vs 24.3 MB TFLite) and 2.0× faster (22.4 ms vs 45.8 ms inference time). MobileNetV2 efficiency advantage is also evident in its inference memory footprint of only 107 MB RAM, significantly 2.3x lower than ResNet50(242 MB RAM), making it highly suitable for deployment on mid-range smartphones with limited RAM. External dataset evaluation reveals MobileNetV2 maintains superior robustness with 65.3% retention rate versus ResNet50's 52.3%. Trade-off analysis positions MobileNetV2 on the Pareto frontier, achieving optimal accuracy-efficiency sweet spot for plant disease detection applications. This research contributes empirical evidence for lightweight architecture superiority, comprehensive efficiency-oriented evaluation framework, ULTRA-LIGHT training strategy for addressing inverse overfitting, and realistic generalization assessment using tropical external dataset.
Downloads
References
A. Yuliana Sianipar, F. Paulus Ginting, and E. Sembiring, “Pengenalan Paprika Hijau (Capsicum annuum L.) Yang Mengandung Vitamin C Sebagai Antioksidan,” Jurnal Abdimas Mutiara, vol. 3, no. 2, pp. 436–438, Aug. 2022, Accessed: Feb. 05, 2026. [Online]. Available: https://e-journal.sari-mutiara.ac.id/index.php/JAM/article/view/4035
J. Khatib Sulaiman, V. Salim, A. Abdullah, and P. Yuli Utami, “Klasifikasi Citra Penyakit Tanaman Pada Daun Paprika Dengan Metode Transfer Learning Menggunakan DenseNet-201,” Indonesian Journal of Computer Science Attribution, vol. 13, no. 2, pp. 3001–3014, Jun. 2024, doi: https://doi.org/10.33022/ijcs.v13i2.3746.
V. Yamaçli and K. Yildirim, “Plant Disease Detection by Using Mobilentv2 and Xception on Filtered and Enhanced Images,” Engineering and Technology Journal, vol. 09, no. 01, pp. 3266–3270, Jan. 2024, doi: 10.47191/etj/v9i01.02.
N. Ilham, N. Elizabeth Mustamu, B. Ainy Dalimunthe, and S. Hartati Yusida Saragih, “Aplikasi Pemberian Abu Sekam Padi dan Pupuk Organik Cair (POC) Terhadap Produksi Tanaman Cabai Merah (Capsicum annum L.),” Jurnal Mahasiswa Agroteknologi (JMATEK), vol. 4, no. 2, pp. 56–63, Aug. 2023, Accessed: Feb. 05, 2026. [Online]. Available: https://jurnal.ulb.ac.id/index.php/JMATEK/article/view/4995
M. Poudel, S. McDuffee, G. V. Minsavage, S. F. Hutton, A. Sharma, and J. B. Jones, “Pyramiding Recessive Resistance Genes Enhances Bacterial Leaf Spot Resistance in Peppers by Suppressing In Planta Bacterial Growth,” Plants, vol. 14, no. 16, p. 2559, Aug. 2025, doi: 10.3390/plants14162559.
H.-T. Vo, L.-D. Quach, and H. Tran Ngoc, “Ensemble of Deep Learning Models for Multi-plant Disease Classification in Smart Farming,” (IJACSA) International Journal of Advanced Computer Science and Applications, vol. 14, no. 5, pp. 1045–1054, 2023, doi: 10.14569/IJACSA.2023.01405108.
N. Anggraini, B. A. Kusuma, P. Subarkah, F. S. Utomo, and N. Hermanto, “Classification of Rice Plant Disease Image Using Convolutional Neural Network (CNN) Algorithm based on Amazon Web Service (AWS),” Building of Informatics, Technology and Science (BITS), vol. 6, no. 3, pp. 1293–1300, Dec. 2024, doi: 10.47065/bits.v6i3.5883.
S. B. Imanulloh, A. R. Muslikh, and D. R. I. M. Setiadi, “Plant Diseases Classification based Leaves Image using Convolutional Neural Network,” Journal of Computing Theories and Applications, vol. 1, no. 1, pp. 1–10, Aug. 2023, doi: 10.33633/jcta.v1i1.8877.
R. A. Setyadi, S. Rahman, D. Manurung, M. Hasanah, and A. Indrawati, “Implementasi Transfer Learning U ntuk Klasifikasi Penyakit Pada Daun Cabai Menggunakan CNN,” Jurnal Teknologi Informasi, vol. 5, no. 2, pp. 304–315, Aug. 2024, doi: 10.46576/djtechno.
N. Ashari and D. Avianto, “Klasifikasi Penyakit Pada Daun Kopi Robusta Menggunakan Arsitektur AlexNet dan Xception dengan Metode Convolutional Neural Network,” Building of Informatics, Technology and Science (BITS), vol. 6, no. 3, pp. 1393–1402, Dec. 2024, doi: 10.47065/bits.v6i3.6109.
Devvret Verma, Vikas Tripathi, and Dibyahash Bordoloi, “Plant Leaf Disease Detection Using Mobilenetv2,” Webology, vol. 18, no. 5, pp. 3241–3246, 2021, doi: 10.29121/web/v18i5/60.
M. Ilhamsyah and U. Enri, “Identification of Bacterial Spot Disease on Paprika Leaves Using CNN and Transfer Learning,” Jurnal Pilar Nusa Mandiri, vol. 18, no. 1, pp. 17–24, Mar. 2022, doi: 10.33480/pilar.v18i1.2755.
M. Dai et al., “Pepper leaf disease recognition based on enhanced lightweight convolutional neural networks,” Front. Plant Sci., vol. 14, p. 1230886, Aug. 2023, doi: 10.3389/fpls.2023.1230886.
L. Raheem Ali Al-khazraji, “Pepper Leaf Disease Detection Using Deep Learning Techniques,” AlKadhim Journal for Computer Science, vol. 3, no. 3, pp. 45–54, Sep. 2025, doi: 10.61710/kjcs.v3i3.118.
A. Maulana, P. Harsani, and M. I. Suriansyah, “Rancang Bangun Alat Pendeteksi Penyakit Daun Tanaman Cabai Merah (Capsicum Annum) Menggunakan Metode Histogram Equalization,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 13, no. 2, pp. 454–466, Apr. 2025, doi: 10.23960/jitet.v13i2.6234.
A. A. Devi Putri et al., “Analisis Penggunaan Pra-proses pada Metode Transfer Learning untuk Mendeteksi Penyakit Daun Singkong,” Techno.COM, vol. 22, no. 2, pp. 336–347, May 2023, doi: https://doi.org/10.33633/tc.v22i2.7769.
S. Lee and S. Lee, “Efficient Data Augmentation Methods for Crop Disease Recognition in Sustainable Environmental Systems,” Big Data and Cognitive Computing, vol. 9, no. 1, p. 8, Jan. 2025, doi: 10.3390/bdcc9010008.
J. Sharma et al., “Deep learning based ensemble model for accurate tomato leaf disease classification by leveraging ResNet50 and MobileNetV2 architectures,” Sci. Rep., vol. 15, no. 1, p. 98015, Dec. 2025, doi: 10.1038/s41598-025-98015-x.
M. Syifa Aryanta, C. A. Sari, and H. Rachmawanto, “A Banana Disease Detection Using MobileNetV2 Model Based on Adam Optimizer,” Journal of Applied Informatics and Computing (JAIC), vol. 9, no. 4, pp. 1207–1218, Aug. 2025, doi: 10.30871/jaic.v9i4.9870.
M. F. Aulia, M. K. Gibran, N. S. A. Sitorus, A. Nugroho, N. Faiza, and H. A. R. Siregar, “Transfer Learning Implementation with MobileNetV2 for Cassava Leaf Disease Detection,” JURNAL TEKNOLOGI DAN OPEN SOURCE, vol. 8, no. 1, pp. 352–361, Jun. 2025, doi: 10.36378/jtos.v8i1.4442.
G. S. Hukkeri, B. C. Soundarya, H. L. Gururaj, and V. Ravi, “Classification of Various Plant Leaf Disease Using Pretrained Convolutional Neural Network On Imagenet,” Open Agric. J., vol. 18, p. e18743315305194, May 2024, doi: 10.2174/0118743315305194240408034912.
S. Yousef and F. Qudaisat, “The Impact of ResNet50 on Image Recognition Accuracy Compared to Prior Convolutional Neural Networks,” Journal of Information Systems Engineering and Management, vol. 10, no. 57s, pp. 155–162, Jul. 2025, Accessed: Feb. 08, 2026. [Online]. Available: https://jisem-journal.com/index.php/journal/article/view/12143
Arjun Tejaswi, “Plant Village,” Kaggle. Accessed: Oct. 16, 2025. [Online]. Available: https://www.kaggle.com/datasets/arjuntejaswi/plant-village
Pratikkayal, “PlantDoc-Dataset,” Github. Accessed: Nov. 25, 2025. [Online]. Available: https://github.com/pratikkayal/PlantDoc-Dataset
M. Pidwirny, Glossary of Terms for Physical Geography and Earth Science. 1999.
S. G. Brucal et al., “Development of Tomato Leaf Disease Detection using Single Shot Detector (SSD) Mobilenet V2,” International Journal of Computing Sciences Research, vol. 7, pp. 1857–1869, Mar. 2023, doi: 10.25147/ijcsr.2017.001.1.136.
C. Li, Q. Wang, X. Liu, and B. Hu, “An Attention-Based CoT-ResNet With Channel Shuffle Mechanism for Classification of Alzheimer’s Disease Levels,” Front. Aging Neurosci., vol. 14, p. 930584, Jul. 2022, doi: 10.3389/fnagi.2022.930584.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Implementasi Deep Learning Berbasis MobileNetV2 untuk Deteksi Real-Time Bacterial Spot dengan Pendekatan Arsitektur Lightweight
Pages: 2286-2299
Copyright (c) 2026 Ahmad Nabilul As'ad, Elkaf Rahmawan Pramudya
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International 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 (Refer to The Effect of Open Access).
