Classification algorithms for automatically detecting sea surface oil spills from spaceborne Synthetic Aperture Radars (SARs) can usually be regarded as part of a three-step processing framework, which briefly includes image segmentation, feature extraction, and target classification. This CNN is a proposed improvement on existing Machine Learning and image processing technologies.

Read or download the paper over here:

https://www.mdpi.com/2072-4292/12/6/1015