Early Detection and Classification of Apple Leaf Diseases by utilizing IFPA Genetic Algorithm with MC-SVM, SVI and Deep Learning Methods

Objectives: To propose a new model for early detection and classification of apple leaf diseases by means genetic algorithms advanced deep learning methods in order to minimize plant degradation maximize accuracy. Methods: A feature selection extraction task is carried out using an Improvised Flower Pollination Technique (IFPA) based algorithm. Deep techniques such as Multi Class Support Vector Machine (MC-SVM) Spectral Vegetation Indices (SVI) are used classify detect disease. The Region Growing Algorithm (RGA) the Stochastic Gradient Descent Method (SGDM) colour segments identify disease at stage on shape, texture, features. IFPA-GA with MC-SVM SVI extracts features from dataset (collected Apple Experiment Station Northwest A&F University, China) then selects appropriate function perform occurrence improve accuracy level. demonstrate efficiency proposed algorithm, MATLAB implementation. performance results evaluated compared existing models Faster R-CNN, R-SSD, INARSSD. Findings: Early achieved 94.09% level, 93.07% Speed, 94.01% sensitivity, 93.38% specificity, 95.01% precision, 93.17% recall, 190 True Positive, 110 Negative, 92.07% F-Score it optimized manner, which high versions. Novelty: According findings comprehensive study, method SVM-SVI outperforms INAR-SSD terms speed classifying robust manner. Keywords: Leaf Disease Detection; SVM; Genetic Algorithm; Learning; Image Processing