Analysis of the Impact of Image Brightness Normalization on the Accuracy of Apple Leaf Disease Classification
DOI:
https://doi.org/10.30871/jaic.v10i2.12537Keywords:
Deep Learning, Image Classification, MobileNetV2, Brightness Normalization, Apple Leaf DiseaseAbstract
Apple crops represent an economically important horticultural sector, yet it faces vulnerabilities from various leaf diseases, including Apple Scab, Cedar Rust, and Black Rot. Translate . Variations in illumination during image acquisition can lead to inconsistencies in color and contrast, adversely affecting the performance of Convolutional Neural Network (CNN)–based classification systems. This study aims to explore how brightness normalization techniques can enhance the accuracy of apple leaf disease classification. The dataset utilized in this research consists of 480 images of apple leaves, categorized into three disease classifications. To facilitate an objective evaluation of the model, the dataset was partitioned into 70% training set, 15% validation set, and 15% test set. Eight different brightness normalization methods were applied during preprocessing, including no normalization, min-max scaling, z-score normalization, gamma correction, histogram equalization, CLAHE, logarithmic transformation, and square root transformation. For this study, the MobileNetV2 architecture was selected as the primary model due to its efficiency in parameters and strong performance in image recognition tasks. Experimental results reveal that the Min-Max normalization technique yielded the highest accuracy at 95.83%, followed by Histogram Equalization at 94.44% and Gamma Correction at 83.33%. In contrast, the baseline model without any normalization only achieved an accuracy of 38.89%. These findings underscore the significant role that brightness normalization plays in enhancing the resilience of CNN models against variations in illumination, thereby improving the automated classification of apple leaf diseases.
Downloads
References
[1] M. U. Ali, M. Khalid, M. Farrash, H. F. M. Lahza, A. Zafar, and S. H. Kim, “AppleLeafNet: a lightweight and efficient deep learning framework for diagnosing apple leaf diseases,” Front. Plant Sci., vol. 15, 2024, doi: 10.3389/fpls.2024.1502314.
[2] A. S. Abade, P. A. Ferreira, and F. de B. Vidal, “Plant Diseases recognition on images using Convolutional Neural Networks: A Systematic Review,” Sep. 2020, [Online]. Available: http://arxiv.org/abs/2009.04365
[3] Md. R. Ahmed, A. F. Ashrafi, R. U. Ahmed, and T. Ahmed, “MCFFA-Net: Multi-Contextual Feature Fusion and Attention Guided Network for Apple Foliar Disease Classification,” Nov. 2022, doi: 10.1109/ICCIT57492.2022.10055790.
[4] Y. Jiao et al., “LCAMNet: a lightweight model for apple leaf disease classification in natural environments,” Front. Plant Sci., vol. 16, 2025, doi: 10.3389/fpls.2025.1626569.
[5] L. Fu, S. Li, Y. Sun, Y. Mu, T. Hu, and H. Gong, “Lightweight-Convolutional Neural Network for Apple Leaf Disease Identification,” Front. Plant Sci., vol. 13, May 2022, doi: 10.3389/fpls.2022.831219.
[6] B. M. Usman, S. K. Johl, and P. A. Khan, “Enhancing energy sector sustainability through robust green governance mechanisms for carbon neutrality,” Dec. 01, 2025, Springer Nature. doi: 10.1007/s43621-025-01064-5.
[7] C. O. Artizzu, G. Allibert, and C. Demonceaux, “OMNI-CONV: Generalization of the Omnidirectional Distortion-Aware Convolutions,” J. Imaging, vol. 9, no. 2, Feb. 2023, doi: 10.3390/jimaging9020029.
[8] J. P. Schwarz Schuler, S. Romani, M. Abdel-Nasser, H. Rashwan, and D. Puig, “Reliable Deep Learning Plant Leaf Disease Classification Based on Light-Chroma Separated Branches,” in Frontiers in Artificial Intelligence and Applications, IOS Press BV, Oct. 2021, pp. 375–382. doi: 10.3233/FAIA210157.
[9] E. A. Taufik, A. F. Parsa, and S. A. M. Mostafa, “Efficient Leaf Disease Classification and Segmentation using Midpoint Normalization Technique and Attention Mechanism,” May 2025, [Online]. Available: http://arxiv.org/abs/2505.21316
[10] N. Sulaiya, “Enhanced Plant Leaf Disease Detection Using CLAHE-Processed Images and Custom CNN Deep Learning Architecture,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 13, no. 9, pp. 906–915, Sep. 2025, doi: 10.22214/ijraset.2025.74149.
[11] X. Niu and G. Zheng, “Research on Low Illumination Image Enhancement Algorithm Based on Convolutional Neural Network,” Academic Journal of Computing & Information Science, vol. 6, no. 9, pp. 115–121, 2023, doi: 10.25236/ajcis.2023.060917.
[12] H. Mao, W. Peng, Y. Tian, and X. Zhu, “A Novel Low-Illumination Image Enhancement Method Based on Convolutional Neural Network with Retinex Theory,” Applied Sciences (Switzerland), vol. 15, no. 22, pp. 1–14, 2025, doi: 10.3390/app152212324.
[13] G. Restu Baihaqi, S. Reditha Shalsadilla, A. Maya Nur Maulidiya, and L. Muflikhah, “Enhancing DenseNet Accuracy in Retinal Disease Classification with Contrast Limited Adaptive Histogram Equalization,” Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI), vol. 10, no. 4, pp. 858–869, 2024, doi: 10.26555/jiteki.v10i4.30327.
[14] Z. Bi et al., “Apple leaf disease severity grading based on deep learning and the DRL-Watershed algorithm,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-15246-8.
[15] V. S. Babu and N. V. Ram, “Deep Residual CNN with Contrast Limited Adaptive Histogram Equalization for Weed Detection in Soybean Crops,” Traitement du Signal, vol. 39, no. 2, pp. 717–722, 2022, doi: 10.18280/ts.390236.
[16] V. Rajpoot et al., “Mango Plant Disease Detection System Using Hybrid BBHE and CNN Approach,” Traitement du Signal, vol. 39, no. 3, pp. 1071–1078, 2022, doi: 10.18280/ts.390334.
[17] C. Kaeser-Chen, F. Pathology, - Maggie, and S. Dane, “Plant Pathology 2020 - FGVC7,” Kaggle. Accessed: Dec. 09, 2025. [Online]. Available: https://www.kaggle.com/competitions/plant-pathology-2020-fgvc7
[18] M. T. Ahad, Y. Li, B. Song, and T. Bhuiyan, “Comparison of CNN-based deep learning architectures for rice diseases classification,” Artificial Intelligence in Agriculture, vol. 9, pp. 22–35, Sep. 2023, doi: 10.1016/j.aiia.2023.07.001.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Nurlina Ambon, Yufis Azhar
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
