Detection of oil leakage in SAR images using wavelet feature extractors and unsupervised neural classifiers

A new algorithm based on wavelets and neural networks is proposed For discr iminating oil leaks using synthetic aperture radar (SAR) images. Utilizing the advantages of wavelets and neural networks, the algorithm is speedy and effective to distinguish oil embedded in both sea clutter and land clutter . The iterative algorithm uses a wavelet feature extractor and two unsuperv ised neural classifiers. The first stage classifier can divide the pixels i n the SAR image into sea water, land and oil clusters. In the second stage, the classifier extracts oil pixels from previous oil cluster until matchin g the characteristics of the oil template. Using our proposed algorithm, th e oil cluster will be formed automatically, provided the desired oil templa te is defined in advance.