ADAPTIVE HYBRID FRAMEWORK FOR ROBUST APPLE LEAF DISEASE DETECTION USING AHE AND GMM
DOI:
https://doi.org/10.34218/IJCET_16_04_010Keywords:
Machine Learning, Deep Learning, GMM, Agriculture, AHE, CNN, SVM, RFAbstract
Apple leaf diseases pose a significant threat to global apple production, demanding accurate and efficient diagnostic frameworks. This study proposes a hybrid model integrating advanced pre-processing techniques, feature extraction, and robust classification methodologies to enhance disease detection accuracy. Pre-processing techniques such as Adaptive Histogram Equalization (AHE) and Gaussian Mixture Models (GMM) were employed to improve image quality and segment disease regions effectively. Feature extraction was performed using a pre-trained ResNet-50 model, followed by classification using a CNN-SVM hybrid model, enhanced with an ensemble Random Forest classifier for robustness. Evaluated on the Plant Village dataset, the proposed model achieved a mean accuracy of 97.76%, outperforming existing methods. This study underscores the importance of advanced pre-processing and hybrid modelling in precision agriculture, offering a scalable and accurate solution for early disease detection and sustainable apple farming practices.
References
Zhang, J., Wang, X., & Huang, Z. (2020). Deep learning-based plant disease identification: A review of challenges and opportunities. Journal of Plant Science and Technology, 5(3), 123–134.
Wang, Y., Li, P., & Zhao, L. (2021). Application of convolutional neural networks in apple leaf disease classification. Computers in Agriculture, 19(2), 45–57.
Bowen, J. K., Mesarich, C. H., & Bus, V. G. (2020). Pathogenicity and control of Venturia inaequalis: The causal agent of apple scab. Plant Pathology Journal, 36(3), 123-135.
Ellis, M. A., Madden, L. V., & Lalancette, N. (2019). The epidemiology of powdery mildew in apple trees. Horticultural Reviews, 45, 89-115.
Beckerman, J. (2021). Cedar apple rust: Biology and management in apple orchards. Plant Disease Journal, 65(4), 245-250.
Jones, A. L., & Aldwinckle, H. S. (2018). Compendium of Apple and Pear Diseases. APS Press, 2nd edition.
Parks, C., Brown, S., & Fenn, M. (2017). Alternaria leaf blotch and its impact on apple production. Journal of Horticultural Science, 12(5), 334-340.
Detection of Apple Leaf Diseases Using VGG16. IEEE Xplore.
Coordination Attention EfficientNet for Plant Disease Identification. Frontiers in Plant Science, 2021.
YOLO-Based Real-Time Apple Leaf Disease Detection. Nature Scientific Reports, 2024.
Lightweight Deep Learning Models for Plant Disease Detection. PubMed Central.
Ensemble Learning for Multi-Class Plant Disease Detection. ArXiv Preprint, 2022.
EfficientNetV2S for Plant Disease Classification with Runtime Data Augmentation. ArXiv Preprint, 2023.
Dong, C., et al. (2016). Image Super-Resolution Using Deep Convolutional Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(2), 295-307.
Zhu, Y., et al. (2021). Adaptive Histogram Equalization for Agricultural Image Enhancement. Precision Agriculture Journal, 22(4), 567-589.
Zivkovic, Z. (2004). Improved Adaptive Gaussian Mixture Model for Background Subtraction. Pattern Recognition Letters, 27(5), 773-780.
Abdi, H., & Williams, L. J. (2010). Principal Component Analysis. Wiley Interdisciplinary Reviews: Computational Statistics, 2(4), 433-459.
Isola, P., et al. (2017). Image-to-Image Translation with Conditional Adversarial Networks. CVPR 2017.
Zhang, X., et al. (2014). "Image processing for detecting apple scab and powdery mildew using support vector machines." Journal of Plant Pathology.
Wang, F., et al. (2015). "Hyperspectral imaging and machine learning for fire blight detection." Computers and Electronics in Agriculture.
Liu, J., et al. (2016). "A deep learning approach for detecting apple diseases using CNN." Sensors.
Gupta, P., et al. (2017). "UAV-based detection of apple diseases using random forests." Agricultural Robotics and Automation.
Liu, Z., et al. (2018). "Multispectral imaging and CNN for apple disease classification." Journal of Agricultural and Food Chemistry.
Akram, M., et al. (2019). "IoT-based early warning system for apple plant diseases." Sensors and Actuators A: Physical.
Khusainov, R., et al. (2020). "Data fusion for apple disease detection using RGB, hyperspectral, and thermal images." Remote Sensing.
Zhang, Y., et al. (2021). "Transfer learning and CNNs for small dataset disease detection in apples." Computers in Biology and Medicine.
Zhang, X., et al. (2022). "Using UAV and deep learning for disease detection in apple orchards." Precision Agriculture.
Xu, Y., et al. (2023). "3D imaging and deep learning for apple canker detection." International Journal of Agricultural Technology.
Lee, J., et al. (2024). "Hybrid model combining IoT and deep learning for apple disease detection." Agricultural Systems.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Nidhi Agrawal, Dr. Sanjay Singh Bhadoriya, Dr. Rajesh Kumar Nagar (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
