Survey on Image Saliency Detection Methods

Image saliency detection is one of the most active research topics in the field of computer vision. It focus on how to detect significant objects under the complex background, and to reduce the computational cost for getting high-resolution, clear boundary, the overall uniform significant objects. First, in this paper the state-of-the-art research on image saliency detection is analyzed and presented in detail. Then the related methods are classified into two types of space domain based, and frequency domain based, and the prototypical research methods are analyzed and tested in public image databases for image saliency detection. Finally, the development tendency of image saliency detection is predicted.