An Efficient Deep Learning Approach for Jute Pest Classification Using Transfer Learning

Jute is considered as one of the most vital crops in the world. For some countries jute is the principal source of earnings and GDP. One of the primary elements influencing jute yield is jute pests. Accurate pest identification makes it possible to take prompt preventative action to minimize financial losses. Considering the fact, to classify jute pests, the study suggests different jute pest classification models, which are based on transfer learning. The best model offers high performance and resilience. A VCI-validated dataset comprising 7235 images has been utilized in the analysis. The dataset encompasses images classified into 17 distinct jute pest classes. The dataset is already divided into three categories train, test and validation. To increase the dataset size, data augmentation is applied to the training set. To improve performance, all the models were integrated with the transfer learning model. VGG 16, ResNetl0l, DenseNet201, InceptionV3, Xception, and MobileN etV2 were used to train the parameters on the publicly available ImageN et dataset followed by some customized dense layers. The models were assessed using different types of metrics, including confusion matrix, F1 score, precision, and recall. Compared to other models DenseNet201 outclassed other models, acquiring 97% accuracy. The fundamental information and technical support for jute pest classification are provided by this study.