Analysis of Color Space Transformations on MobileNetV2 Performance for Image Classification

Sherlyn Vironica, Sugiyarto Surono, Aris Thobirin

Abstract


This study analyzes the effect of color space transformation on the performance of MobileNetV2 for rice leaf disease classification using RGB, HSV, CIELab, and their combinations. The RGB color space is used as the baseline representation, while HSV and CIELab are applied to provide alternative representations of color information. In addition, a dual-stream architecture is employed to combine different color spaces for feature extraction. The results show that the choice of color space influences classification performance. In the single color-space scenario, RGB achieves the highest accuracy of 91.42%, while in the combined scenario, the RGB+CIELab model achieves the best performance with an accuracy of 97.00%. These findings suggest that the use of multiple color spaces can provide richer feature representations and may improve classification performance. Furthermore, the results indicate that optimizing input representation plays an important role in improving model performance, particularly when using lightweight architectures such as MobileNetV2. This study shows that color space transformation can improve classification performance in the rice leaf disease dataset used in this study.


Keywords


MobileNetV2, RGB, HSV, CIELab, Deep Learning, Rice Disease

Full Text:

PDF

References


[1] Alzubaidi, Laith, Jinglan Zhang, et al. "Review of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions." Journal of Big Data 8(1) (2021). doi: 10.1186/s40537-021-00444-8.

[2] Putri, N. I., and Z. Munawar. "Deep Learning and Big Data Technology for IoT Security." J. Inform. – Comput. 7(1) (2020), 48–73.

[3] Esmaeili, F., et al. "Utilizing Deep Learning Algorithms for Signal Processing in Electrochemical Biosensors: From Data Augmentation to Detection and Quantification of Chemicals of Interest." Bioengineering 10(12) (2023), 1348. doi: 10.3390/bioengineering10121348.

[4] She, W. "A Review of Deep Learning-Based Text Sentiment Analysis." (2023). doi: 10.54254/2755-2721/32/20230204.

[5] Kong, X., et al. "Deep Learning for Time Series Forecasting: A Survey." Springer (2025). doi: 10.1007/s13042-025-02560-w.

[6] Younesi, A., et al. "A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends." IEEE Access (2024). doi: 10.1109/ACCESS.2024.3376441.

[7] Azmi, K., S. Defit, and S. Sumijan. "Implementasi Convolutional Neural Network (CNN) Untuk Klasifikasi Batik Tanah Liat Sumatera Barat." J. Unitek (2023). doi: 10.52072/unitek.v16i1.504.

[8] Suhendar, S., et al. "Deteksi Penyakit Pada Daun Tanaman Ubi Jalar Menggunakan Metode Convolutional Neural Network." J. Ilm. Inform. Glob. (2023). doi: 10.36982/jiig.v14i3.3478.

[9] Ibrahim, Media Ali, et al. "Deep Learning in Medical Image Analysis Article Review Media." Indonesian Journal of Computer Science 13(2) (2024), 2293–2311.

[10] Hütten, N., et al. "Deep Learning for Automated Visual Inspection in Manufacturing and Maintenance: A Survey of Open-Access Papers." Applied System Innovation 7(1) (2024), 11. doi: 10.3390/asi7010011.

[11] Luo, C., et al. Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices. arXiv preprint arXiv:2005.05085. 2020. http://arxiv.org/abs/2005.05085.

[12] Younesi, A., et al. "A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends." IEEE Access 12 (2024).

[13] Shahriar, T. Comparative Analysis of Lightweight Deep Learning Models for Memory-Constrained Devices. arXiv preprint arXiv:2505.03303. 2025. http://arxiv.org/abs/2505.03303.

[14] Putra, O. V., M. Z. Mustaqim, and D. Muriatmoko. "Transfer Learning untuk Klasifikasi Penyakit dan Hama Padi Menggunakan MobileNetV2." Techno.Com 22(3) (2023), 562–575. doi: 10.33633/tc.v22i3.8516.

[15] Huong, P. T., et al. "Enhancing Deep Convolutional Neural Network Models for Orange Quality Classification Using MobileNetV2 and Data Augmentation Techniques." Journal of Algorithms and Computational Technology 19 (2025). doi: 10.1177/17483026241309070.

[16] Wardhana, S. F. D., and A. Nugroho. "Perbandingan Arsitektur MobileNetV2 dan MobileNetV3 Dalam Klasifikasi Jenis Jeruk." Journal of Computing Science and Business 16(1) (2025), 25–34. doi: 10.47927/jikb.v16i1.916.

[17] Lu, J., L. Tan, and H. Jiang. "Review on Convolutional Neural Network (CNN) Applied to Plant Leaf Disease Classification." Agriculture 11(8) (2021). doi: 10.3390/agriculture11080707.

[18] Toda, Y., and F. Okura. "How Convolutional Neural Networks Diagnose Plant Disease." Plant Phenomics 2019 (2019). doi: 10.34133/2019/9237136.

[19] Verma, D., D. Bordoloi, and V. Tripathi. "Plant Leaf Disease Detection Using MobilenetV2." Webology 18(5) (2021), 3241–3246. doi: 10.29121/WEB/V18I5/60.

[20] Chen, H., et al. "Classification and Identification of Agricultural Products Based on Improved MobileNetV2." Scientific Reports 14(1) (2024). doi: 10.1038/s41598-024-53349-w.

[21] Hassan, H. M., et al. A Survey on Different Plant Diseases Detection Using Machine Learning Techniques. 2022.

[22] Johari, P. F., et al. "Corn Leaf Diseases Classification Using CNN with GLCM, HSV, and L*a*b* Features." Jurnal Teknik Informatika 6(2) (2025), 709–722. doi: 10.52436/1.jutif.2025.6.2.4345.

[23] Ikhsan, M., and M. Rahardi. "Image-Based Classification of Indonesian Traditional Houses Using a Hybrid CNN-SVM Algorithm." Journal of Computer Science 9(5) (2025), 2303–2309. doi: 10.30871/jaic.v9i5.10864.

[24] Giuliani, D. "Metaheuristic Algorithms Applied to Color Image Segmentation on HSV Space." Journal of Imaging 8(1) (2022). doi: 10.3390/jimaging8010006.

[25] Imawati, I. A. P. F., et al. "A Study of Lab Color Space and Its Visualization." In: ICAMSAC 2023. Atlantis Press, 2024. doi: 10.2991/978-94-6463-413-6_3.

[26] N, M. B., et al. "Plant Leaf Disease Detection Using MobileNetV2." (2025). doi: 10.1051/itmconf/20257901021.

[27] Aryanta, M. S., C. A. Sari, and E. H. Rachmawanto. "A Banana Disease Detection Using MobileNetV2 Model Based on Adam Optimizer." 9(4) (2025), 1207–1218. doi: 10.30871/jaic.v9i4.9870.

[28] Morris, G., et al. "Classification of Diabetic Wounds Using Transfer Learning Model: EfficientNetB1 and ResNet50." 11(1) (2025), 207–217. doi: 10.31154/cogito.v11i1.1001.207-217.

[29] Bushara, A. R. "Efficient Net-Based Deep Learning Model for Accurate Plant Disease Classification and Diagnosis." 14(1) (2025), 1264–1270. doi: 10.30574/ijsra.2025.14.1.0170.




DOI: https://doi.org/10.18860/cauchy.v11i1.41353

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Sherlyn Vironica, Sugiyarto Surono, Aris Thobirin

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Editorial Office
Mathematics Department,
Universitas Islam Negeri Maulana Malik Ibrahim Malang
Gajayana Street 50 Malang, East Java, Indonesia 65144
Faximile (+62) 341 558933
e-mail: cauchy@uin-malang.ac.id

Creative Commons License
CAUCHY: Jurnal Matematika Murni dan Aplikasi is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.