Enhanced Segmentation and Ensemble Classification for Accurate Plant Disease Detection

Enhanced Segmentation and Ensemble Classification for Accurate Plant Disease Detection P. Santhosh Kumar Department of Computer Science and Engineering VELS University Chennai Tamil Nadu India https://orcid.org/0000-0003-3680-6615 K. Kalaivani Department of Computer Science and Engineering VELS University Chennai Tamil Nadu India R. Balakrishna Department of Artificial intelligence and Data Science VELS University Chennai Tamil Nadu India ABSTRACT

The majority of the crops are wasted owing to deficiency of transport, plant diseases and lack of storage facilities. Above 15% of crops are worn out in India owing to diseases and therefore it has turned out to be a main concern to be solved. This study introduces an advanced framework for plant disease detection by integrating enhanced image segmentation techniques with robust ensemble classification models. Our methodology begins with the pre‐processing of plant leaf images using median filtering and Wiener denoising to reduce noise and enhance image quality. As the next step, the Improved Region Growing Algorithm (IRGA) is deployed for the segmentation of images. Then, features together with ‘Scale Invariant Feature Transform (SIFT), improved Binary Gabor Pattern (IBGP), Haralick features, color features like RGB Color Histogram, disease area and higher order statistical features (Entropy, Skewness, variance and kurtosis)’ are extracted. The improved independent component analysis (IICA) model is then used to choose the best attributes. Lastly, detection takes place using Ensemble classifiers (EC) including Neural Network (NN), modified effective squeeze and excitation block‐based deep convolutional neural network (M‐ESE‐DCNN) and bi‐directional gated recurrent unit (BI‐GRU). Further, the DCNN weights are optimised via the Colliding Archimedes and Teamwork Algorithm (CA‐TWA) model. For the best case with dataset 1, EC + CA‐TWA got a high accuracy of 0.94, while EC + BOA, EC + DOX, EC + SSO, EC + TOA and EC + ArOA had lower accuracy. Furthermore, for all schemes, dataset 1 displays superior outputs to dataset 2 and dataset 3. Finally, an evaluation is done to validate this work.
12 10 2024 11 2024 e13426 10.1111/jph.13426 2 10.1002/crossmark_policy onlinelibrary.wiley.com true 2024-04-11 2024-10-18 2024-12-10 http://onlinelibrary.wiley.com/termsAndConditions#vor 10.1111/jph.13426 https://onlinelibrary.wiley.com/doi/10.1111/jph.13426 https://onlinelibrary.wiley.com/doi/pdf/10.1111/jph.13426 10.1016/j.compag.2021.106279 Energy Aborisade D. 239 2 10 2014 Comparative Analysis of Textural Features Derived From GLCM for Ultrasound Liver Image Classification 10.1109/ACCESS.2021.3119655 10.1109/LISAT.2015.7160191 10.1109/JSTARS.2017.2788426 10.1016/j.matpr.2021.05.584 10.1016/j.aiia.2021.05.002 10.1016/j.suscom.2020.100415 10.1109/JIOT.2019.2947624 10.21203/rs.3.rs-2373358/v1 David B. andR.Gomathi.2023.“Improved Segmentation With Optimization Based Multilevel Thresholding and K‐Means Clustering for Plant Disease Identification.” 10.3390/s21134567 10.1109/JIOT.2021.3097379 10.1109/JSEN.2021.3064060 10.1007/s10489-020-01893-z 10.3389/fpls.2023.1280671 10.1016/j.asoc.2020.106597 10.1016/j.jhydrol.2017.02.021 10.1109/ACCESS.2020.3011685 10.1109/ACCESS.2019.2908061 10.1109/ACCESS.2019.2914929 Kaur N. andV.Devendran. n.d. “Optimize Segmentation and Law Mask Feature Extraction With SVM Classifier.” 10.1109/ACCESS.2019.2908040 10.1109/JSEN.2020.3046295 10.1109/ACCESS.2021.3073929 10.1016/j.cam.2017.12.026 10.1109/ACCESS.2021.3069646 10.1016/j.petrol.2021.109309 10.1016/j.chemolab.2020.104129 10.1109/ACCESS.2020.2980310 10.1109/IECBES.2016.7843459 10.1109/ACCESS.2019.2954845 International Research Journal of Modernization in Engineering Technology and Science Pallavi R. 65 5 2023 A Hybrid Ensemble Approach For Plant Disease Detection And Classification 10.1109/JSEN.2021.3089722 10.1007/s11042-023-17830-4 10.1109/ICSC45622.2019.8938371 SIFT Feature. Accessed: 17 2021.https://medium.com/data‐breach/introduction‐to‐sift‐scale‐invariant‐feature‐transform‐65d7f3a72d40. 10.1109/ACCESS.2019.2907383 IEEE Access Sunil C. K. 789 10 2021 Cardamom Plant Disease Detection Approach Using EfficientNetV2 10.1109/ACCESS.2021.3098307 10.1016/j.ecoinf.2021.101289 10.1109/JSEN.2020.3032438 10.1016/j.mlwa.2023.100502 10.1109/ACCESS.2020.3039345 10.1016/j.matpr.2021.03.700 10.1109/ACCESS.2021.3052769 10.1109/ACCESS.2020.3025196 10.1109/ICIP.2012.6466800 10.1109/TCBB.2021.3056683 10.1109/ACCESS.2019.2943454 10.1016/j.phpro.2012.03.133