Deep Learning algorithm has recently encountered a lot of success especially in the field of computer vision. The current paper aims to describe a new classification method applied to synthetic aperture radar (SAR), We used transfer learning followed by fine tuning methods in such a classification schematic; Pre-trained architectures on ImageNet database was used; VGG 16 was indeed used as a feature extractor and a new classifier was trained based on extracted features; the last three convolutional blocks of the VGG16 were then fine tuned; Dataset used is the Moving and Stationary Traget Acquisition and recognition (MSTAR) data; We’ve reached a final accuracy of 97.91% on Ten (10) different classes.
CITATION STYLE
Anas, H., Majdoulayne, H., Chaimae, A., & Nabil, S. M. (2020). Deep learning for SAR image classification. In Advances in Intelligent Systems and Computing (Vol. 1037, pp. 890–898). Springer Verlag. https://doi.org/10.1007/978-3-030-29516-5_67
Mendeley helps you to discover research relevant for your work.