Mitigating Imbalanced Citrus Disease Image Datasets with Oversampling

Arya Gunawan; Nana  Suarna; Agus Bahtiar; Indra Wiguna Marthanu; Kaslani

doi:10.59934/jaiea.v5i2.1862

Authors

Arya Gunawan STMIK IKMI CIREBON
Nana Suarna
Agus Bahtiar
Indra Wiguna Marthanu
Kaslani

DOI:

https://doi.org/10.59934/jaiea.v5i2.1862

Keywords:

image classification; data augmentation; MobileNetV2; citrus leaf disease; oversampling

Abstract

Dataset imbalance is a critical challenge in plant disease image classification because it causes bias towards the majority class. This study evaluates the effectiveness of augmentation-based oversampling techniques on the classification performance of citrus leaf images using the MobileNetV2 architecture. The four leaf disease classes classified include Greening, Fresh, Canker, and Blackspot. The dataset was obtained from a public repository and processed through preprocessing (resize, normalization) and augmentation (rotation, flipping, zoom) stages. The model was trained and tested in two scenarios: baseline (unbalanced data) and mitigation (data balanced through augmentation). The experimental results show that the mitigation approach was able to increase accuracy from 91.92% to 93.94%. The F1-score, precision, and recall values also increased significantly, especially in the minority class. Evaluation using a confusion matrix reinforced the finding that augmentation-based oversampling is effective in reducing classification errors. This study shows that the integration of augmentation techniques and MobileNetV2-based transfer learning can significantly improve classification performance and contribute to the development of early detection systems for plant diseases in precision agriculture.

Downloads

Download data is not yet available.

References

J. Han et al., “Classifying Neovascular Age-Related Macular Degeneration With a Deep Convolutional Neural Network Based on Optical Coherence Tomography Images,” Sci. Rep., vol. 12, no. 1, 2022, doi: 10.1038/s41598-022-05903-7.

H. Zhang, H. Sun, and T. Yuan, “Network Art Image Classification and Print Propagation Extraction Based on Depth Algorithm,” Wirel. Commun. Mob. Comput., vol. 2022, no. 1, 2022, doi: 10.1155/2022/2546015.

Q. Lv, W. Feng, Y. Quan, G. Dauphin, L. Gao, and M. Xing, “Enhanced-Random-Feature-Subspace-Based Ensemble CNN for the Imbalanced Hyperspectral Image Classification,” Ieee J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 14, pp. 3988–3999, 2021, doi: 10.1109/jstars.2021.3069013.

M. H. Aabidi, A. E. Makrani, B. Jabir, and I. Zaimi, “A Model Proposal for Enhancing Leaf Disease Detection Using Convolutional Neural Networks (CNN),” Int. J. Online Biomed. Eng., vol. 19, no. 12, pp. 127–143, 2023, doi: 10.3991/ijoe.v19i12.40329.

O. Abayomi‐Alli, R. Damaševičius, S. Misra, and R. Maskeliūnas, “Cassava Disease Recognition From low‐quality Images Using Enhanced Data Augmentation Model and Deep Learning,” Expert Syst., vol. 38, no. 7, 2021, doi: 10.1111/exsy.12746.

A. Ayub and H. Kim, “GAN-Based Data Augmentation With Vehicle Color Changes to Train a Vehicle Detection CNN,” Electronics, vol. 13, no. 7, p. 1231, 2024, doi: 10.3390/electronics13071231.

B. d. O. Maciel et al., “Artificial Intelligence Tools: A Practice Report From the International Center for Software Technology,” Rev. Contemp., vol. 4, no. 12, p. e6973, 2024, doi: 10.56083/rcv4n12-156.

A. Pirmatov, B. A. Azimov, and S. Kamalov, “Artificial Intelligence Using Python: Technologies and Applications,” Bull. Sci. Pract., vol. 9, no. 11, pp. 288–295, 2023, doi: 10.33619/2414-2948/96/37.

A. Li, J. P. Winebrake, and K. D. Kovacs, “Facilitating Deep Learning Through Preprocessing of Optical Coherence Tomography Images,” BMC Ophthalmol., vol. 23, no. 1, 2023, doi: 10.1186/s12886-023-02916-2.

M. Yousif, “Enhancing the Accuracy of Image Classification Using Deep Learning and Preprocessing Methods,” Artif. Intell. Robot. Dev. J., 2024, doi: 10.52098/airdj.2023348.

G. Jin, S. Oh, Y. Lee, and S. Shin, “Extracting Weld Bead Shapes From Radiographic Testing Images With U-Net,” Appl. Sci., vol. 11, no. 24, p. 12051, 2021, doi: 10.3390/app112412051.

S. Prusty, S. Patnaik, and S. K. Dash, “SKCV: Stratified K-Fold Cross-Validation on ML Classifiers for Predicting Cervical Cancer,” Front. Nanotechnol., vol. 4, 2022, doi: 10.3389/fnano.2022.972421.

A. F. Boy, A. Akhyar, T. Y. Arif, and S. Syahrial, “Artificial Intelligence for Dental Caries Detection: A Mixup, Fine-Tuning, and Quantization Approach on the MobileNetV2 Model,” J. Conserv. Dent. Endod., vol. 28, no. 8, pp. 764–771, 2025, doi: 10.4103/jcde.jcde_362_25.

M. Iqbal, F. Rozi, N. O. Adiwijaya, and D. I. Swasono, “Identifikasi Kinerja Arsitektur Transfer Learning VGG16 , ResNet-50 , dan Inception-V3 Dalam Pengklasifikasian Citra Penyakit Daun Tomat Identification of VGG16 , ResNet-50 , and Inception-V3 Transfer Architecture Performance in Image Classification of Tomato Leaf Diseases,” vol. 5, no. 2, pp. 145–154, 2023.

H. Bechinia, D. Benmerzoug, and N. Khlifa, “Approach Based Lightweight Custom Convolutional Neural Network and Fine-Tuned MobileNet-V2 for ECG Arrhythmia Signals Classification,” Ieee Access, vol. 12, pp. 40827–40841, 2024, doi: 10.1109/access.2024.3378730.

S. Albahli and M. Nawaz, “DCNet: DenseNet-77-based CornerNet Model for the Tomato Plant Leaf Disease Detection and Classification,” Front. Plant Sci., vol. 13, 2022, doi: 10.3389/fpls.2022.957961.

P. Sharma and P. Abrol, “Agricultural Advancements Through Machine Learning Technologies,” Environ. Ecol., vol. 42, no. 2B, pp. 775–779, 2024, doi: 10.60151/envec/krws4781.

A. H. Ali, A. Youssef, M. Abdelal, and M. A. Raja, “An ensemble of deep learning architectures for accurate plant disease classification,” Ecol. Inform., vol. 81, no. September 2023, p. 102618, 2024, doi: 10.1016/j.ecoinf.2024.102618.

G. Han, D. Kwaku, P. Asiedu, and K. Ebo, “Heliyon Plant disease detection with generative adversarial networks,” Heliyon, vol. 11, no. 7, p. e43002, 2025, doi: 10.1016/j.heliyon.2025.e43002.

S. Agustina, A. Hidayat, Satrianansyah, and R. Kurniawan, “Klasifikasi Penyakit pada Buah Jeruk Berdasarkan Citra dengan Pendekatan Transfer Learning Menggunakan Arsitektur Densenet-121,” J. Ilm. Inform., vol. 10, pp. 42–47, Jul. 2025, doi: 10.35316/jimi.v10i1.41-47.

M. H. Firdaus, E. Utami, and D. Ariatmanto, “Detection And Classification of Citrus Diseases Based on A Combination of Features Using the Densenet-169 Model,” Sinkron, vol. 8, no. 4, pp. 2592–2601, 2023, doi: 10.33395/sinkron.v8i4.12974.