Underwater scene search scheme via similarity measure and sparse representation for autonomous underwater vehicle

Underwater scene search turns out to be one of the most challenging topics in the underwater image analysis. In this paper, we present one underwater scene search scheme combined with similarity measure and sparse representation. The color histogram is first adopted to classify the candidate image patches for each kind of the underwater scene. At the same time, the feature similarity (FSIM) considers a full reference of the complementary terms, i.e., the phase congruency (PC) and the image gradient magnitude (GM), to reflect and generate the similarity map between the query image patch and the reference one. Sparse representation is then made full use of to represent the underwater image patches. It is shown in the simulation experiment that the proposed approach could achieve great performances in both robustness and effectiveness with good behaviors in underwater scene search tasks.