Date of Publication :2nd September 2024

Abstract:Deep learning techniques applied for classification and detection of plant diseases. Using convolutional neural networks (CNNs) and other deep learning architectures, researchers have made major strides toward automating the identification of numerous plant diseases. Deep learning improves classification efficiency and accuracy by automatically extracting complicated characteristics from digital pictures, hence eliminating the need for manual feature engineering. Deep Crop management and food security in agriculture, even in the face of obstacles like model interpretability and the need for annotated training data. The review also looks at the use of the cutting-edge deep learning architecture Efficient Net for plant leaf disease classification, emphasizing how effective and scalable it is for automating tasks related to illness identification. Additionally, the review highlights CNNs' remarkable success in correctly identifying plant illnesses and compares the efficacy of deep learning to traditional machine learning techniques. The article also looks at the potential of deep transfer learning for identifying plant diseases, showing how it might enhance detection accuracy by tailoring trained models to particular disease datasets. In order to highlight the potential of deep learning to improve agricultural management practices and guarantee food security, the review concludes by examining the factors influencing the adoption of deep learning for plant disease identification, such as dataset availability, computational resources, and model interpretability.

Reference :