Deep Learning-Based Citrus Disease Detection Using Hybrid Feature Extraction
Keywords:
Citrus disease detection, CNN, Feature extraction, MobileNet, ResNet, VGG16Abstract
Early detection of fungal infections in citrus crops is vital to prevent disease spread, minimize losses, and maintain agricultural productivity. Deep learning has enhanced plant disease diagnosis, improving fruit quality and yield. This study evaluates multiple convolutional neural network (CNN) architectures for citrus disease identification. Six pre-trained models VGG16, InceptionNet, ResNet, NasNet, MobileNet, and a custom CNN were tested on 1,500 images of healthy and diseased citrus leaves. MobileNet achieved the highest accuracy at 96%. Further analysis incorporated advanced feature extraction using a comprehensive citrus disease dataset. Deep features were generated with AlexNet, followed by data augmentation and extraction of color and texture attributes using color moments, gray-level co-occurrence matrix (GLCM), and Gabor wavelets. A hybrid feature set was created by combining deep features with extracted attributes, optimized using neighbourhood component analysis (NCA). Classification models were assessed using random forest and a Bayesian-optimized approach. The highest classification accuracy of 95.07% was achieved, validating the effectiveness of the proposed citrus disease detection framework.
References
J. Boulent, S. Foucher, J. Theau, and P. L. St-Charles, “Convolutional neural networks for the automatic identification of plant diseases,” Frontiers in Plant Science, vol. 10, p. 941, 2019. Available: https://doi.org/10.3389/fpls.2019.00941
S. P. Mohanty, D. P. Hughes, and M. Salathé, “Using deep learning for image-based plant disease detection,” Frontiers in Plant Science, vol. 7, p. 1419, 2016. Available: https://doi.org/10.3389/fpls.2016.01419
S. Zhang, S. Zhang, C. Zhang, X. Wang, and Y. Shi, “Cucumber leaf disease identification with global pooling dilated convolutional neural network,” Computers and Electronics in Agriculture, vol. 162, pp. 422–430, 2019. Available: https://doi.org/10.1016/j.compag.2019.04.018
K. P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,” Computers and Electronics in Agriculture, vol. 145, pp. 311–318, 2018. Available: https://doi.org/10.1016/j.compag.2018.01.009
E. C. Too, L. Yujian, S. Njuki, and L. Yingchun, “A comparative study of fine-tuning deep learning models for plant disease identification,” Computers and Electronics in Agriculture, vol. 161, pp. 272–279, 2019. Available: https://doi.org/10.1016/j.compag.2018.03.032
J. G. A. Barbedo, “Plant disease identification from individual lesions and spots using deep learning,” Biosystems Engineering, vol. 180, pp. 96–107, 2019. Available: https://doi.org/10.1016/j.biosystemseng.2019.02.002
J. Ma et al., “A segmentation method for overlapping fruits based on deep learning and watershed transformation,” Computers and Electronics in Agriculture, vol. 185, p. 106135, 2021. Available: https://doi.org/10.1016/j.compag.2021.106135
J. Chen et al., “Using deep transfer learning for image-based plant disease identification,” Computers and Electronics in Agriculture, vol. 173, p. 105393, 2020. Available: https://doi.org/10.1016/j.compag.2020.105393
R. Wang, S. Min, X. Ma, and B. Li, “Recognition of citrus diseases based on deep learning using an improved convolutional neural network model,” Agronomy, vol. 11, no. 2, p. 343, 2021. Available: https://doi.org/10.3390/agronomy11020343
J. Zhang, Y. Xie, Y. Li, Y. Wang, and E. Xia, “Recognition of citrus leaf diseases based on deep learning model,” IEEE Access, vol. 8, pp. 139491–139497, 2020. Available: https://doi.org/10.1109/ACCESS.2020.3012431
J. Amara, B. Bouaziz, and A. Algergawy, “A deep learning-based approach for banana leaf disease classification,” in Lecture Notes in Computer Science, vol. 10882, pp. 79–88, 2018. Available: https://doi.org/10.1007/978-3-319-93034-3_9
R. Dhingra and N. Kumar, “An improved deep learning-based framework for plant disease classification using hybrid features,” Expert Systems with Applications, vol. 200, p. 116923, 2022. Available: https://doi.org/10.1016/j.eswa.2022.116923
A. Ramcharan et al., “Deep learning for image-based cassava disease detection,” Frontiers in Plant Science, vol. 10, p. 221, 2019. Available: https://doi.org/10.3389/fpls.2019.00221
W. Xie, Y. Ma, Y. Wang, and L. Wang, “Citrus disease detection using attention-based convolutional neural networks,” Agricultural Research, vol. 11, pp. 723–731, 2021. Available: https://doi.org/10.1007/s40003-021-00544-w
A. Fuentes, S. Yoon, J. Lee, and D. S. Park, “Deep learning-based morphological feature extraction for plant disease diagnosis,” Agricultural and Forest Meteorology, vol. 263, pp. 45–56, 2018. Available: https://doi.org/10.1016/j.agrformet.2018.08.012
M. G. Selvaraj et al., “AI-powered plant disease detection using UAV-based multispectral imaging,” Remote Sensing, vol. 11, no. 20, p. 2445, 2019. Available: https://doi.org/10.3390/rs11202445
H. Durmus, E. O. Güneş, and M. Kirci, "Disease detection on the leaves of tomato plants using deep learning,” Agriculture, vol. 9, no. 6, p. 115, 2019. Available: https://doi.org/10.3390/agriculture9060115
A. Picon, M. Galar, I. Irigoien, and L. Magdalena, “Deep convolutional neural networks for mobile capture device-based crop disease classification in heterogeneous environments,” Computers and Electronics in Agriculture, vol. 161, pp. 280–290, 2019. Available: https://doi.org/10.1016/j.compag.2018.12.012
A. K. Rangarajan, R. Purushothaman, and A. Ramesh, “Tomato crop disease classification using a pre-trained deep learning algorithm,” Procedia Computer Science, vol. 133, pp. 1040–1047, 2018. Available: https://doi.org/10.1016/j.procs.2018.07.070
M. H. Saleem, J. Potgieter, and K. M. Arif, “Plant disease detection and classification by deep learning,” Plants, vol. 10, no. 6, p. 1216, 2021. Available: https://doi.org/10.3390/plants10061216
L. Ma, Y. Liu, H. Zhang, and D. Chen, “Lightweight deep learning-based citrus disease identification using attention mechanisms,” Neural Computing and Applications, vol. 34, pp. 18979–18992, 2022. Available: https://doi.org/10.1007/s00521-022-07522-w
P. Jiang, Y. Chen, B. Liu, D. He, and C. Liang, “Real-time detection of apple leaf diseases using deep learning approach based on improved convolutional neural networks,” IEEE Access, vol. 7, pp. 59069–59080, 2019. Available: https://doi.org/10.1109/ACCESS.2019.2914929
J. Liu, X. Wang, and J. Zhang, “Explainable AI for plant disease detection using hybrid CNN and Vision Transformers,” Expert Systems with Applications, vol. 193, p. 116372, 2022. Available: https://doi.org/10.1016/j.eswa.2021.116372
R. Dhingra and N. Kumar, “An optimized deep learning framework for citrus disease detection using attention-based convolutional neural networks,” Applied Soft Computing, vol. 132, p. 109802, 2023. Available: https://doi.org/10.1016/j.asoc.2023.109802
