Approach of Transfer Learning in Remote Sensing Image Classification

One of the primary uses of digital image processing is image classification, which has applications in the medical industry as well as in the categorization of plant diseases and land use in geospatial pictures. A VGG 16 deep neural network model was used in the proposed work to classify remote sensing images. Here, the classification process uses a transfer learning strategy with a pre-trained network. The Sentinel-2 satellite's EuroSat Dataset, which has ten distinct classifications, was utilized. A 20 epoch pre-trained VGG16 network was used to achieve 92.14 percent accuracy. Transfer learning makes it possible for us to do better in less time.