Jeongwhan Choi, Journal of Internet Computing and Services, Vol. 19, No. 4, pp. 35-44, Aug. 2018
10.7472/jksii.2018.19.4.35, Full Text:
Keywords: Convolutional Neural Network, Deep Learning, Transfer Learning, Pooling Layer, Adam Optimizer, data augmentation

Abstract

Monitoring through Synthesis Aperture Radar (SAR) is responsible for marine safety from floating icebergs. However, there are limits to distinguishing between icebergs and ships in SAR images. Convolutional Neural Network (CNN) is used to distinguish the iceberg from the ship. The goal of this paper is to increase the accuracy of identifying icebergs from SAR images. The metrics for performance evaluation uses the log loss. The two-layer CNN model proposed in research of C.Bentes et al.[1] is used as a benchmark model and compared with the four-layer CNN model using data augmentation. Finally, the performance of the final CNN model using the VGG-16 pre-trained model is compared with the previous model. This paper shows how to improve the benchmark model and propose the final CNN model.

Statistics
Cite this article