Underwater image feature extraction and matching based on visual saliency detection

Computer vision has become the tool of two-dimensional image recognition and analysis, which mainly means extracting image features. But the problem of robustness and real-time property in complex scenarios makes feature extraction become a challenging task. Visual attention is an important psychological adjustment mechanism in the process of human visual information management, under the guidance of visual attention, human can quickly select the most important, useful and relevant to the current behavior interested visual information from a number of visual information. This paper applies the visual detection to underwater image feature extraction to work out the robustness problem, which is conducive to a more stable and closer to human cognitive mechanism feature extraction algorithm. In addition, in the process of underwater images pretreatment, we apply dark channel prior to the underwater images preprocessing process to remove haze and enhance the contrast of underwater images. The results also show that the robustness and the property of real-time of feature extraction based on visual saliency detection and dark color image defogging algorithm has been greatly improved.