Classification of Orange Peel Conditions Using Transfer Learning MobileNetV2 with K-Fold Cross Validation

Mu'az Khalik Lubis; Hermawan SyahPutra

doi:10.59934/jaiea.v5i1.1778

Authors

Mu'az Khalik Lubis Universitas Negeri Medan
Hermawan SyahPutra Universitas Negeri Medan

DOI:

https://doi.org/10.59934/jaiea.v5i1.1778

Keywords:

MobileNetv2, Transfer Learning, K-Fold Cross Validation, Image Classification, Orange Peel

Abstract

The quality of orange peel is one of the main indicators in determining the ripeness level, overall fruit quality, and market value. Manual assessment of orange peel conditions tends to be subjective, inconsistent, and time-consuming, especially when applied to large-scale sorting processes. This study aims to classify orange peel conditions into two categories healthy and damaged using a deep learning approach based on the MobileNetV2 architecture with the transfer learning method. The model was trained and evaluated using the 10-Fold Cross Validation technique to ensure robust and reliable results. The dataset used in this study was obtained from Kaggle, consisting of high-resolution images of orange peels categorized by physical condition. Each image was converted into RGB format, resized to 224×224 pixels, and normalized before training. The experimental results show that the proposed model achieved an average accuracy of 95.74%, with precision, recall, and F1-score of 95.73% each. The results demonstrate that MobileNetV2, when combined with transfer learning, can effectively detect damaged orange peels and can potentially be implemented in automated fruit quality inspection systems.

Downloads

Download data is not yet available.

References

N. Haryanti, D. Agungtio, R. S. Alsada, M. S. Suryani, and C. N. Harun, “Quality of orange (Cirtus sp) fruit from five districts in South Sumatera,” 2024.

A. W. Dari, A. C. Narsa, and N. M. Zamruddin, “Literature Review: Aktivitas Kulit Jeruk dalam Bidang Farmasi,” Proceeding of Mulawarman Pharmaceuticals Conferences, vol. 12, pp. 125–151, Dec. 2020, doi: 10.25026/mpc.v12i1.417.

E. M. Damayanti et al., “INFEKSI CPSV (Citrus Psorosis Virus) TERHADAP TANAMAN CITRUS DI KABUPATEN GORONTALO,” Seminar Nasional Teknologi, 2022.

E. B. Ferreira, C. C. de Oliveira, K. B. Ferreira, J. L. da Silva, and A. M. S. Vieira, “Industrial reuse of orange peel: A review of current applications,” in Frontiers of Knowledge: Multidisciplinary Approaches in Academic Research, Seven Editora, 2024. doi: 10.56238/sevened2024.026-060.

A. Aghababaei, F. Aghababaei, M. Pignitter, and M. Hadidi, “Artificial Intelligence in Agro-Food Systems: From Farm to Fork,” Feb. 01, 2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/foods14030411.

H. Pathak, C. Igathinathane, K. Howatt, and Z. Zhang, “Machine learning and handcrafted image processing methods for classifying common weeds in corn field,” Smart Agricultural Technology, vol. 5, Oct. 2023, doi: 10.1016/j.atech.2023.100249.

Z. Huang et al., “ORD-YOLO: A Ripeness Recognition Method for Citrus Fruits in Complex Environments,” Agriculture (Switzerland), vol. 15, no. 15, Aug. 2025, doi: 10.3390/agriculture15151711.

S. Castillo-Girones, S. Munera, M. Martínez-Sober, J. Blasco, S. Cubero, and J. Gómez-Sanchis, “Artificial Neural Networks in Agriculture, the core of artificial intelligence: What, When, and Why,” Mar. 01, 2025, Elsevier B.V. doi: 10.1016/j.compag.2025.109938.

H. Uyar, I. Karvelas, S. Rizou, and S. Fountas, “Data value creation in agriculture: A review,” Comput Electron Agric, vol. 227, Dec. 2024, doi: 10.1016/j.compag.2024.109602.

A. AM, M. I. Mardin, and H. Saleh, “DISEASE DETECTION SYSTEM IN COFFEE PRUNS USING MOBILENET ALGORITHM,” Jurnal Kesehatan dan Teknologi, vol. 1, no. 1, pp. 30–35, Sep. 2024, doi: 10.64879/jkestek.v1i1.33.

B. S. Acarya, A. Muhaimin, and K. M. Hindrayani, “Identifikasi Penyakit Daun Jeruk Siam Menggunakan Convolutional Neural Network (CNN) dengan Arsitektur EfficientNet,” G-Tech: Jurnal Teknologi Terapan, vol. 8, no. 2, pp. 1040–1048, Apr. 2024, doi: 10.33379/gtech.v8i2.4120.

A. Dwi Rizkika, A. Yudo Husodo, and R. Dwiyansaputra, “IMPLEMENTASI METODE CONVOLUTIONAL NEURAL NETWORK DALAM KLASIFIKASI TAHAPAN KEMATANGAN BUAH MANGGIS (Implementation Of Convolutional Neural Network Method In Classification Of Maturity Stages Of Mangosteen Fruit),” 2024.

M. Mesárošová, O. Mihálik, and M. Jirgl, “CNN Architecture for Posture Classification on Small Data,” in IFAC-PapersOnLine, Elsevier B.V., Jun. 2024, pp. 299–304. doi: 10.1016/j.ifacol.2024.07.413.

K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” Apr. 2015, [Online]. Available: http://arxiv.org/abs/1409.1556

K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” 2016. [Online]. Available: http://image-net.org/challenges/LSVRC/2015/

M. Tan and Q. V Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” 2019.

V. Bischoff, K. Farias, J. P. Menzen, and G. Pessin, “Technological support for detection and prediction of plant diseases: A systematic mapping study,” Comput Electron Agric, vol. 181, p. 105922, Feb. 2021, doi: 10.1016/J.COMPAG.2020.105922.

K. Bykov, K.-R. Müller, and M. M.-C. Höhne, “Mark My Words: Dangers of Watermarked Images in ImageNet,” Mar. 2023, [Online]. Available: http://arxiv.org/abs/2303.05498

K. P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,” Comput Electron Agric, vol. 145, pp. 311–318, Feb. 2018, doi: 10.1016/J.COMPAG.2018.01.009.

Y. Li, J. Nie, and X. Chao, “Do we really need deep CNN for plant diseases identification?,” Comput Electron Agric, vol. 178, p. 105803, Nov. 2020, doi: 10.1016/J.COMPAG.2020.105803.

M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” 2018.

S. Khandelwal, A. Raut, H. Vyawahare, D. Theng, and S. Dhande, “Optimizing Performance in Mango Plant Leaf Disease Classification through Advanced Machine Learning Techniques,” Engineering, Technology and Applied Science Research, vol. 14, no. 6, pp. 18476–18480, Dec. 2024, doi: 10.48084/etasr.8220.

Z. Du, X. Zeng, X. Li, X. Ding, J. Cao, and W. Jiang, “Recent advances in imaging techniques for bruise detection in fruits and vegetables,” Trends Food Sci Technol, vol. 99, pp. 133–141, May 2020, doi: 10.1016/J.TIFS.2020.02.024.

D. Abriha, P. K. Srivastava, and S. Szabó, “Smaller is better? Unduly nice accuracy assessments in roof detection using remote sensing data with machine learning and k-fold cross-validation,” Heliyon, vol. 9, no. 3, p. e14045, Mar. 2023, doi: 10.1016/J.HELIYON.2023.E14045.

C. Mahlich, T. Vente, and J. Beel, “From Theory to Practice: Implementing and Evaluating e-Fold Cross-Validation,” 2024.