OPTIMIZING MULTI-CHANNEL RESNET50 FOR CITRUS LEAF CLASSIFICATION USING COLOR ENHANCEMENT AND EDGE DETECTION METHOD
DOI:
https://doi.org/10.33480/jitk.v11i1.6782Keywords:
citrus leaf, gamma correction , aplacian , multi-scale retinex , resnet50Abstract
Conventional methods face limitations due to the high similarity in color and morphology among citrus leaves classification. To address this challenge, deep learning approaches combined with advanced image preprocessing techniques offer a promising solution. This study employed transfer learning using the ResNet50 architecture integrated with image preprocessing methods including contrast enhancement and edge detection. The experiment was implemented in Python 3.13.2 with TensorFlow on an HP OMEN laptop equipped with Intel® Core™ i7-12700F and NVIDIA® GeForce RTX™ 3060 Ti GPU. A dataset of 250 images across five citrus species was captured using a Samsung M54 camera. To enhance dataset diversity, augmentation techniques such as zoom scaling (80–120%), random rotation (±15° to +30°), and horizontal/vertical translation (10–20%) were applied, expanding the dataset to 2,500 images. Data were divided into training (70%), validation (15%), and testing (15%). Four model scenarios were evaluated: MSR-ResNet50 (RGB), GC-ResNet50 (RGB), LF-ResNet50 (GS), and GC-MSR-LF MC-ResNet50 (RGB+GS). Among the evaluated models, GC-MSR-LF MC-ResNet50 achieved the best performance, recording accuracies of 93.7% for training, 91.0% for validation, and 90.2% for the test set. These results indicate a significant improvement in distinguishing citrus leaves with high morphological similarity. The findings confirm that integrating image preprocessing methods with transfer learning enhances the accuracy of citrus leaf classification. The proposed GC-MSR-LF MC-ResNet50 model demonstrates robust generalization across datasets, highlighting its potential application in precision agriculture for automated species identification and crop monitoring.
Downloads
References
R. C. Traband et al., “Exploring the phylogenetic relationship among Citrus through leaf shape traits: A morphological study on Citrus leaves,” Horticulturae, vol. 9, no. 7, p. 793, 2023.
P. C. Palangasinghe et al., “Reviews on Asian citrus species: Exploring traditional uses, biochemistry, conservation, and disease resistance,” Ecol. Genet. Genomics, p. 100269, 2024.
M. Groppo, L. F. Afonso, and J. R. Pirani, “A review of systematics studies in the Citrus family (Rutaceae, Sapindales), with emphasis on American groups,” Brazilian J. Bot., vol. 45, no. 1, pp. 181–200, 2022.
S. Jain, H. Singh, D. S. Kore, S. Mishra, and R. Sharma, “A Comprehensive Review on Post Harvest Physiological Disorders in Citrus Fruit Crops (Citrus spp.),” Int. J. Environ. Clim. Chang., vol. 13, no. 10, pp. 2863–2873, 2023.
S. Hamid, K. Sharma, K. Kumar, and A. Thakur, “Types and cultivation of citrus fruits,” in Citrus Fruits and Juice: Processing and Quality Profiling, Springer, 2024, pp. 17–43.
R. Richa et al., “Citrus fruit: Classification, value addition, nutritional and medicinal values, and relation with pandemic and hidden hunger,” J. Agric. Food Res., vol. 14, p. 100718, 2023.
V. Ayumi, E. Ermatita, A. Abdiansah, H. Noprisson, M. Purba, and M. Utami, “A Study on Medicinal Plant Leaf Recognition Using Artificial Intelligence,” in 2021 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS, 2021, pp. 40–45.
V. Ayumi et al., “Transfer Learning for Medicinal Plant Leaves Recognition: A Comparison with and without a Fine-Tuning Strategy,” Int. J. Adv. Comput. Sci. Appl., vol. 13, no. 9, 2022.
P. Dhiman, A. Kaur, and V. Kukreja, “Citrus fruit disease detection techniques: a survey and comparative analysis of relevant approaches,” Int. J. Comput. Digit. Syst., vol. 14, no. 1, pp. 10127–10148, 2023.
S. Ghazal, W. S. Qureshi, U. S. Khan, J. Iqbal, N. Rashid, and M. I. Tiwana, “Analysis of visual features and classifiers for Fruit classification problem,” Comput. Electron. Agric., vol. 187, p. 106267, 2021.
A. Khattak et al., “Automatic detection of citrus fruit and leaves diseases using deep neural network model,” IEEE access, vol. 9, pp. 112942–112954, 2021.
C. Senthilkumar and M. Kamarasan, “An effective citrus disease detection and classification using deep learning based inception resnet V2 model,” Turkish J. Comput. Math. Educ., vol. 12, no. 12, pp. 2283–2296, 2021.
A. R. Luaibi, T. M. Salman, and A. H. Miry, “Detection of citrus leaf diseases using a deep learning technique,” Int. J. Electr. Comput. Eng., vol. 11, no. 2, p. 1719, 2021.
H. Zhu, D. Wang, Y. Wei, X. Zhang, and L. Li, “Combining Transfer Learning and Ensemble Algorithms for Improved Citrus Leaf Disease Classification,” Agriculture, vol. 14, no. 9, p. 1549, 2024.
M. F. Chowdhury, A. Nondi, S. U. Akhter, T. B. Pathan, and D. Z. Karim, “Optimizing Citrus Leaf Disease Detection: An Efficient Custom CNN Leveraging Efficient Training Parameters,” in 2024 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), 2024, pp. 579–584.
A. Goyal and K. Lakhwani, “Integrating advanced deep learning techniques for enhanced detection and classification of citrus leaf and fruit diseases,” Sci. Rep., vol. 15, no. 1, p. 12659, 2025.
L. Hodač et al., “Deep learning to capture leaf shape in plant images: Validation by geometric morphometrics,” Plant J., vol. 120, no. 4, pp. 1343–1357, 2024.
V. Naralasetti and J. D. Bodapati, “Enhancing plant leaf disease prediction through advanced deep feature representations: a transfer learning approach,” J. Inst. Eng. Ser. B, vol. 105, no. 3, pp. 469–482, 2024.
A. Upadhyay et al., “Deep learning and computer vision in plant disease detection: a comprehensive review of techniques, models, and trends in precision agriculture,” Artif. Intell. Rev., vol. 58, no. 3, pp. 1–64, 2025.
J. Lu et al., “Citrus green fruit detection via improved feature network extraction,” Front. Plant Sci., vol. 13, p. 946154, 2022.
P. Dhiman, A. Kaur, Y. Hamid, E. Alabdulkreem, H. Elmannai, and N. Ababneh, “Smart disease detection system for citrus fruits using deep learning with edge computing,” Sustainability, vol. 15, no. 5, p. 4576, 2023.
S. Ma, C. Yang, and S. Bao, “Contrast Enhancement Method Based on Multi-Scale Retinex and Adaptive Gamma Correction,” J. Adv. Comput. Intell. Intell. Informatics, vol. 26, no. 6, pp. 875–883, 2022.
L. Wang, “Natural low-illumination image enhancement based on dual-channel prior information,” Heliyon, vol. 10, no. 17, 2024.
H. Liang, A. Yu, M. Shao, and Y. Tian, “Multi-feature guided low-light image enhancement,” Appl. Sci., vol. 11, no. 11, p. 5055, 2021.
P. M. Kanjalkar, J. Kanjalkar, A. J. Zagade, and V. Talnikar, “A Novel Approach to Identify Leaf Vein Morphology Using Laplacian Filter and Deep Learning for Plant Identification,” in Recent Developments in Machine and Human Intelligence, IGI Global, 2023, pp. 13–31.
K. R. Manoj, G. Manikandan, G. R. Chalini, and V. Thiruchelvam, “Comparison of roberts edge detection and Laplacian edge detection for classification of guava leaf disease,” in AIP Conference Proceedings, 2024, vol. 3161, no. 1.
P. Muruganandam, V. Tandon, and B. Baranidharan, “Rice crop diseases and pest detection using edge detection techniques and convolution neural network,” in Computer Vision and Robotics: Proceedings of CVR 2021, Springer, 2022, pp. 49–64.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Handrie Noprisson, Mariana Purba, Pungkas Subarkah
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
