A Novel Salp Swarm Algorithm With Attention-Densenet Enabled Plant Leaf Disease Detection And Classification In Precision Agriculture

Abstract

Recent technological advancements enable precision agriculture to improve crop productivity and quality. Since plant diseases mainly affect crop production and reduce profit, necessary tools are needed to detect plant diseases at an earlier stage. Automatic detection of plant diseases becomes essential to identify the occurrence of plant diseases and take remedial actions. The latest advancements of computer vision and artificial intelligence techniques can be used to design effective plant leaf disease detection models. This paper presents a novel salp swarm algorithm with attention-DenseNet enabled plant leaf disease detection and classification (SSADN-PLDDC) technique for precision agriculture. The major intention of the SSADN-PLDDC technique is to recognize the presence of plant leaf diseases using computer vision and image processing methods. The SSADN-PLDDC technique initially employs Gabor filtering to pre-process the input images. In addition, SSA with extreme learning machine (ELM) model is utilized as an image classification technique where the parametersinvolved in the ELM are optimally adjusted by using SSA. The experimental result analysis of the SSADN-PLDDC technique is validated using benchmark dataset and the experimental results reported the enhanced outcomes of the SSADN-PLDDC technique over the recent approaches.