Strawberry Leaf Disease Detection using Transfer Learning Models

Authors:

Abstract
Strawberries are one of the world’s most popular and prized fruits, prized for their delicious flavor and vibrant color. Strawberry crops, like other plant species, are susceptible to a variety of diseases that can have a significant impact on their growth, yield, and overall quality. Plant disease detection in a timely and precise manner is critical for maintaining plant health and sustaining agriculture. Traditional methods, which involve expert manual inspection, are inefficient. To address this issue, the study looks into the use of Transfer Learning Models with pre-trained neural networks to detect strawberry leaf diseases. The research aims to reliably identify and classify diseases by fine-tuning models such as MobilNetV2, EfficientNetB0, and ResNet18. The models’ accuracy is 80%, 99%, and 64%, respectively, with the EfficientNetB0 achieving a fantastic 99% accuracy. This methodology, which utilizes the power of deep learning and transfer learning techniques, has the potential to revolutionize agriculture by providing an effective and scalable method for disease identification, resulting in better crops and more sustainable practices.

This publication has 18 references indexed in Scilit: