Transfer Learning Implementation with MobileNetV2 for Cassava Leaf Disease Detection

Muhammad Fathir Aulia; M. Khalil Gibran; Nur Shafwa Aulia Sitorus; Agung Nugroho; Nayla Faiza; Hervilla Amanda R. Siregar

doi:10.36378/jtos.v8i1.4442

Muhammad Fathir Aulia Universitas Islam Negeri Sumatera Utara
M. Khalil Gibran Universitas Islam Negeri Sumatera Utara
Nur Shafwa Aulia Sitorus Universitas Islam Negeri Sumatera Utara
Agung Nugroho Universitas Islam Negeri Sumatera Utara
Nayla Faiza Universitas Islam Negeri Sumatera Utara
Hervilla Amanda R. Siregar Universitas Islam Negeri Sumatera Utara

DOI: https://doi.org/10.36378/jtos.v8i1.4442

Keywords: MobileNetV2, Transfer Learning, Cassava Leaf, Image Processing, Disease Detection

Abstract

Cassava (Manihot esculenta) is one of Indonesia’s key agricultural commodities but is vulnerable to various leaf diseases, such as Cassava Bacterial Blight (CBB) and Cassava Mosaic Disease (CMD). These diseases often exhibit similar visual symptoms, making it challenging for farmers to accurately identify them through manual observation. This study aims to develop an automatic cassava leaf disease detection system based on transfer learning, utilizing the MobileNetV2 architecture. The dataset used consists of 1,500 images, evenly distributed across three categories: CBB, CMD, and healthy leaves. The data underwent preprocessing, augmentation, and model training, including fine-tuning of the last 20 layers of the MobileNetV2 model. Evaluation results indicated that the model achieved an accuracy of 67% on the test set, with the highest performance in detecting Cassava Mosaic Disease, reflected by an F1-score of 0.75. These results demonstrate the potential of MobileNetV2 as a lightweight and efficient solution for detecting cassava leaf diseases, particularly when supported by a larger and more diverse dataset. This research serves as a foundation for developing mobile-based diagnostic tools to help farmers make faster and more accurate decisions in the field.

Downloads

Download data is not yet available.

References

A. E. Nugraha, S. Rizal, and N. K. C. Pratiwi, “Klasifikasi Penyakit Pada Tanaman Singkong Menggunakan Arsitektur VGGNET Berbasis Deep Learning,” e-Proceeding Eng., vol. 8, no. 6, pp. 3240–3246, 2022.

A. Ramcharan, K. Baranowski, P. McCloskey, B. Ahmed, J. Legg, and D. P. Hughes, “Deep learning for image-based cassava disease detection,” Front. Plant Sci., vol. 8, no. October, pp. 1–7, 2017, doi: 10.3389/fpls.2017.01852.

Y. A. and S. A. M. D. Fida Zubair, Moutaz Saleh, “A Robust Ensemble Model for Plant Disease Detection Using Deep Learning Architectures,” AgriEngineering is an Int., vol. 7, no. 159, p. 25, 2025.

S. M. Hassan, A. K. Maji, M. Jasiński, Z. Leonowicz, and E. Jasińska, “Identification of plant-leaf diseases using cnn and transfer-learning approach,” Electron., vol. 10, no. 12, 2021, doi: 10.3390/electronics10121388.

I. G. D. Dwijayana and I. G. A. Wibawa, “Implementasi Transfer Learning Dalam Klasifikasi Penyakit Pada Daun Teh Menggunakan MobileNetV2,” J. Nas. Teknol. Inf. dan Apl., vol. 1, no. 1, pp. 379–387, 2022.

A. Saleh, A. Ridwan, and M. K. Gibran, “Machine Learning and Fuzzy C-Means Clustering for the Identification of Tomato Diseases,” Indones. J. Comput. Sci., vol. 12, no. 5, pp. 2401–2413, 2023, doi: 10.33022/ijcs.v12i5.3379.

F. S. Anam, M. R. Muttaqin, and Y. R. Ramadhan, “Klasifikasi Penyakit Pada Daun dan Buah Jambu Menggunakan Convolutional Neural Network,” JOINTECS (Journal Inf. Technol. Comput. Sci., vol. 8, no. 3, p. 115, 2023, doi: 10.31328/jointecs.v8i3.4823.

J. Yao, S. N. Tran, S. Sawyer, and S. Garg, Machine learning for leaf disease classification: data, techniques and applications, vol. 56, no. s3. Springer Netherlands, 2023. doi: 10.1007/s10462-023-10610-4.

J. Fathur Rahman, Irfansyah, Rivaldi Dwi Andhika, “WhatsApp Chat Fraud Analysis Using Support Vector Machine Method,” J. Teknol. DAN OPEN SOURCE, vol. 4, no. 2, pp. 174–179, 2021, doi: 10.36378/jtos.v4i2.1791.

A. F. Ridwan Dwi Irawan, “Application of Deep Learning Algorithm to Detect Fraud in Online Transaction Networks Ridwan,” J. Teknol. DAN OPEN SOURCE, vol. 7, no. 2, pp. 167–177, 2024, doi: 10.36378/jtos.v7i2.3890.

R. Sari and R. Y. Hayuningtyas, “Particle Swarm Optimization-based Support Vector Machine Method for Sentiment Analysis in OVO Digital Payment Applications,” J. Teknol. Dan Open Source, vol. 4, no. 2, pp. 232–239, 2021, doi: 10.36378/jtos.v4i2.1776.

M. F. Siti Saniah, “Classification Of Rice Plant Diseases Using K-Nearest Neighbor Algorithm Based On Hue Saturation Value Color Extraction And Gray Level Co-Occurrence Matrix Features,” J. Teknol. DAN OPEN SOURCE, vol. 7, no. 2, pp. 212–223, 2024, doi: 10.36378/jtos.v7i2.3972.

A. D. P. Ariyanto, S. Hasanah, M. B. Subkhi, and N. Suciati, “Analisis Penggunaan Pra-proses pada Metode Transfer Learning untuk Mendeteksi Penyakit Daun Singkong,” Techno.Com, vol. 22, no. 2, pp. 336–347, 2023, doi: 10.33633/tc.v22i2.7769.

D. A. Tri Anton, Arief Setyanto, “Penerapan Transfer Learning Dengan Inception-V3 Dan Efficientnet-B4 Pada Studi Kasus Klasifikasi Penyakit Pada Daun Singkong,” J. Compr. Sci., vol. 3, no. 12, pp. 37–48, 2024.

D. Firdaus, I. Sumardi, and R. R. Aziz, “Sistem Deteksi Penyakit Daun Singkong Menggunakan Deep Learning dengan Arsitektur MobilenetV3 berbasis Android,” J. Wahana Inform., vol. 3, no. 2, pp. 71–80, 2024.

M. Faturrachman, I. Yustiana, and . S., “Sistem Pendeteksi Penyakit Pada Daun Tanaman Singkong Menggunakan Deep Learning Dan Tensorflow Berbasis Android,” IJIS - Indones. J. Inf. Syst., vol. 7, no. 2, p. 176, 2022, doi: 10.36549/ijis.v7i2.225.

W. Shafik, A. Tufail, C. De Silva Liyanage, and R. A. A. H. M. Apong, “Using transfer learning-based plant disease classification and detection for sustainable agriculture,” BMC Plant Biol., vol. 24, no. 1, pp. 1–19, 2024, doi: 10.1186/s12870-024-04825-y.

A. R. D. Muhammad Gabriel Somoal, “KOMPARASI MOBILENETV2 DENGAN KUSTOMISASI TRANSFER LEARNING DAN HYPERPARAMETER UNTUK IDENTIFIKASI TUMOR OTAK,” J. Teknol. Inf. dan Ilmu Komput., vol. 12, no. 1, pp. 229–240, 2025, doi: 10.25126/jtiik.2025129582.

M. A. and TE Ogunbiyi, AM Mustapha, EJ Eturhobore and T. Sessi, “Development of a Web-based Tomato Plant Disease Detection and Diagnosis System using Transfer Learning Techniques,” Ann. Civ. Environ. Eng., vol. 8, no. 1, pp. 76–86, 2024.

W. B. Demilie, “Plant disease detection and classification techniques: a comparative study of the performances,” J. Big Data, vol. 11, no. 1, 2024, doi: 10.1186/s40537-023-00863-9.

A. K. Fathorazi Nur Fajri, Mohammad Dzikrillah, “Digital Fish Image Segmentation Using U-Net for Shape Feature Extraction,” J. Teknol. DAN OPEN SOURCE, vol. 7, no. 2, pp. 195–201, 2024, doi: 10.36378/jtos.v7i2.3968.

P. Kaur, S. Harnal, R. Tiwari, S. Upadhyay, S. Bhatia, and A. Mashat, “Recognition of Leaf Disease Using Hybrid Convolutional,” Sensors, vol. 22, 2022.

F. A. Arafat, M. N. Ichsan, and M. F. Pramoedya, “Pemanfaatan Arsitektur MOBILENET-CNN Untuk Mendiagnosis Penyakit Pada Daun Singkong Melalui Teknologi Citra Digital,” Pros. Semin. Nas. Teknol. DAN SAINS, vol. 4, pp. 73–78, 2025.

A. Dolatabadian, T. X. Neik, M. F. Danilevicz, S. R. Upadhyaya, J. Batley, and D. Edwards, “Image-based crop disease detection using machine learning,” Plant Pathol., no. September 2024, pp. 18–38, 2024, doi: 10.1111/ppa.14006.

A. S. M. Khalil Gibran, “A Hybrid RBF Neural Network and FCM Clustering for Diabetes Prediction Dataset,” J. Comput. Sci. Inf. Technol. Telecommun. Eng., vol. 4, no. 2, pp. 395–401, 2023, doi: 10.30596/jcositte.v4i2.15573.

I. Mudzakir and T. Arifin, “Klasifikasi Penggunaan Masker dengan Convolutional Neural Network Menggunakan Arsitektur MobileNetv2,” Expert J. Manaj. Sist. Inf. dan Teknol., vol. 12, no. 1, p. 76, 2022, doi: 10.36448/expert.v12i1.2466.