Automated Plant Leaf Disease Classification using Artificial Algae Algorithm with Deep Learning Model

Agriculture is the primary occupation in India and owing to plant diseases, annually it loses 35% of its crops. Early detection of plant disease is a challenging task due to its expert knowledge and improper laboratory facilities. Automatic plant leaf disease detection methods can be beneficial for decreasing the laborious work of monitoring huge crop farms and for early recognizing disease symptoms, i.e., once they emerge on plant leaf. Latest developments in deep learning (DL) and computer vision techniques have shown the value of developing automated plant leaf disease detection model based on visible symptoms on plant leaves. The study introduces an Automatic Plant Leaf Disease Classification using Artificial Algae Algorithm with Deep Learning (PLDC-AAADL) Model. The PLDC-AAADL technique intends to differentiate the diseased and healthy plant leaf images. In the initial stage, the PLDC-AAADL technique makes use of densely connected networks (DenseNet-121) model for feature vector generation with Artificial Algae Algorithm (AAA) as a hyperparameter optimizer. Kernel extreme learning machine (KELM) model is applied for plant leaf disease detection purposes. In this study, to improvise the detection rate of the KEIM model, the Adam optimizer is used. The experimental outcome of the PLDC-AAADL method can be studied on benchmark datasets and the outcomes highlighted the supremacy of the PLDC-AAADL technique over other existing approaches.