Implementation of MobileNetV2 Transfer Learning for Image-Based Classification of Cocoa Fruit Diseases
Abstract
Cocoa is one of the high-value agricultural commodities in Indonesia; however, its productivity continues to decline due to the increasing prevalence of plant diseases, particularly Black Pod Disease and attacks by Helopeltis spp. Traditional disease detection, which is generally performed manually by farmers, is often inefficient and prone to errors, thereby highlighting the need for an intelligent and technology-assisted early diagnosis system. This study aims to develop a disease classification model for cocoa plants using a Convolutional Neural Network (CNN) based on the MobileNet-V2 architecture, which is recognized for its computational efficiency and strong performance in image analysis. The dataset consisted of 300 images divided into three categories: healthy cocoa pods, Black Pod Disease, and damage caused by Helopeltis. Following the Pareto principle, 80% of the data were allocated for training and 20% for testing. The model was trained for 10 epochs with a batch size of 32 and was supported by data augmentation to improve data variability. Experimental results demonstrated a significant improvement in performance, with the highest validation accuracy of 93.75% achieved at the seventh epoch. The confusion matrix further confirmed that the model classified each category with a high level of precision. These findings indicate that MobileNet-V2 is an effective approach for automatic cocoa disease detection and has strong potential to assist farmers in improving disease management practices in the field.
Key words: Convolutional Neural Network; MobileNet-V2; Cocoa Disease Classification; Helopeltis spp.; Deep Learning
References
C. Depoorter, J. Bemelmans, and A. Marx, “The role of intermediaries in the implementation of sustainability standards. A case study of buyer-driven Rainforest Alliance certification in the Indonesian cocoa sector,” World Dev., vol. 195, no. 107128, pp.1-15, 2025, doi: 10.1016/j.worlddev.2025.107128.
W. Rumahlewang, H. R.D. Amanupunyo, and B. S. Tomia, “Kerusakan Buah Kakao Akibat Penyakit Busuk Buah (Phytopthora palmivora Butlher),” COMSERVA : Jurnal Penelitian dan Pengabdian Masyarakat, vol. 2, no. 7, pp. 956-962, Nov. 2022, doi: 10.59141/comserva.v2i7.427.
P. Liyanapathiranage et al., “Vascular Streak Dieback: A Novel Threat to Redbud and Other Woody Ornamental Production in the United States,” Plant Dis., vol. 109, no. 5, pp. 953-970, May. 2025, doi: 10.1094/PDIS-04-24-0905-FE.
F. N. Aini et al., “Effect of Weather Conditions to Vascular Streak Dieback Disease Severity on Some Cocoa Clones with Different Resistant Levels,” Research Journal of Life Science, vol. 10, no. 2, pp. 59-72, Jul. 2024, doi: 10.21776/ub.rjls.2023.010.02.2.
Y. Elfina, . I., A. Sabirunah, D. Wijayanto, A. Rizqi, and M. Mu’arif, “The Morphological Identification of Fungi Causing Cocoa Fruit Rot Disease and Inhibition Test of Bacillus spp. Against the Fungus in Vitro,” Jurnal Budidaya Pertanian, vol. 20, no. 1, pp. 83-89, Jun. 2024, doi: 10.30598/jbdp/2024.20.1.83.
K. A. Awang and Y. M. Killa, “Identifikasi jenis hama intensitas kerusakan tanaman jambu mete (Anacardium Occidentale L.) di Desa Watupuda,” in 4th Nasional Seminar of Sustainable Agriculture Technology Innovation, pp. 780-888, Agustus. 2025.
Y. B. Blikon, “Perbandinga Kinerja Pengklasifikasi Citra Buah Kakao Sakit Dan Sehat Menggunakan Support Vector Machine (SVM) Dan K-Nearest Neighbors (KNN),” Simetris: Jurnal Teknik Mesin, Elektro dan Ilmu Komputer, vol. 14, no. 1, pp. 9-16, Apr. 2023, doi: 10.24176/simet.v14i1.9012.
G. A. S. Gado and P. N. Primandari, “Sistem Klasifikasi Berbasis Android untuk Penyakit Buah Kakao Menggunakan CNN NasNet-Mobile,” Jurnal Teknologi Terpadu, vol. 11, no. 1, pp. 27-35, 2025, doi: 10.54914/jtt.v11i1.1821.
A. A. Sari, N. Arifin, and C. N. Insani, “Klasifikasi Penyakit Buah Kakao Berbasis Citra Menggunakan Transfer Learning Dengan Model MOBILENETV2,” vol. 11, no. 1, pp. 249-254, 2026.
N. Khaerani Hamzidah, “Analisis Diagnosa Penyakit Pada Tanaman Kakao Dengan Menggunakan Metode YOLOV8,” Journal of Informatics and Computer Engineering Research (JICER), vol. 2, no. 2, pp. 29-33, 2025.
J. B. Ruhland, I. Masoudian, and D. Heider, “Enhancing deep neural network training through learnable adaptive normalization,” Knowl. Based. Syst., vol. 326, pp. 1-9, 2025, doi: 10.1016/j.knosys.2025.113968.
G. Kostiuchik, L. Sharan, B. Mayer, I. Wolf, B. Preim, and S. Engelhardt, “Surgical phase and instrument recognition: how to identify appropriate dataset splits,” Int. J. Comput. Assist. Radiol. Surg., vol. 19, no. 4, pp. 699-711, Jan. 2024, doi: 10.1007/s11548-024-03063-9.
A. Akshay et al., “MLcps: machine learning cumulative performance score for classification problems,” Gigascience, vol. 12, no. 1, pp. 1-9, 2023, doi: 10.1093/gigascience/giad108.
W. Wang et al., "InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions," 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 2023, pp. 14408-14419, doi: 10.1109/CVPR52729.2023.01385.
O. Rainio, J. Teuho, and R. Klén, “Evaluation metrics and statistical tests for machine learning,” Sci. Rep., vol. 14, no. 1, pp. 1-14, Jul. 2024, doi: 10.1038/s41598-024-56706-x.
Y. Bammou et al., “Machine learning models for gully erosion susceptibility assessment in the Tensift catchment, Haouz Plain, Morocco for sustainable development,” Journal of African Earth Sciences, vol. 213, pp. 1-16, May. 2024, doi: 10.1016/j.jafrearsci.2024.105229.
O. Rainio et al., “Comparison of thresholds for a convolutional neural network classifying medical images,” Int. J. Data Sci. Anal., vol. 20, no. 3, pp. 2093-2099, Jun. 2025, doi: 10.1007/s41060-024-00584-z.
S. Roumeliotis et al., “ROC curve analysis: a useful statistic multi-tool in the research of nephrology,” vol. 56, no. 8, pp. 2651-2658, Mar. 2024. doi: 10.1007/s11255-024-04022-8.
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, Dec. 2024, doi: 10.1186/s12870-024-04825-y.
M. Alkanan and Y. Gulzar, “Enhanced corn seed disease classification: leveraging MobileNetV2 with feature augmentation and transfer learning,” Front. Appl. Math. Stat., vol. 9, pp. 1-12, Jan. 2023, doi: 10.3389/fams.2023.1320177.
How To Cite This :
Refbacks
- There are currently no refbacks.
