Underwater image sparse representation based on bag-of-words and compressed sensing

In this paper, a novel approach based on bag-ofwords and compressed sensing has been proposed for the sparse representation of the underwater images. Properties in the water, such as the limited range, non-uniform lighting, low contrast, diminished colors, has been taken into consideration for underwater image sparse representation. Our method is a simple and computationally efficient extension of an orderless bag-ofwords model, and it shows consistently and significantly improved performance on underwater image representation tasks.