Automated Plant Disease Detection Systems for the Smart Farming Sector

Abstract

Global agriculture is affected by plant diseases. Plant diseases have hampered agricultural productivity and development worldwide, reducing food supplies. Systemic conditions can damage leaves. Several plant diseases were on the leaves. The infestation type must be identified to treat it. Farmers' diagnostic error and disease propagation are examined in this case study. Machine learning can benefit from CV DL methods. This research evaluates the dwarf mongoose optimization algorithm with deep learning for automated plant leaf disease detection. APLDD-DMOADL shows farmers photos to boost productivity and reduce crop losses. The APLDD-DMOADL method classifies leaf diseases exactly. APLDD-DMOADL uses Inception ResNet-v2 to extract features and stacked LLSTM to classify. CSA enhanced subject-level SLSTM hyperparameters. The APLDD-DMOADL approach was extensively tested using a reference database to demonstrate its benefits. Many categories showed that the APLDD-DMOADL algorithm outperformed others.