Seafloor Characterization Using Texture

Texture analysis is performed on multibeam sonar imagery. A set of fourteen texture features is computed using co-occurrence matrices to form the feature space. The dimensionality of the feature space is reduced by extracting the principal components from the original feature space. Classification of the image is performed on the principal components using K-Means algorithm. Results indicate that seafloor bottom types can be characterized by analyzing the texture of the bathymetric sonar images. Hydrography, Bathymetry, Optical properties, Remote sensing, Reverberation.