Integrating QDWD with pattern distinctness and local contrast for underwater saliency detection

In this paper, we propose a novel framework for underwater image saliency detection by exploiting Quaternionic Distance Based Weber Descriptor (QDWD), pattern distinctness, and local contrast. Our proposed algorithm incorporates quaternion number system and principal components analysis (PCA) simultaneously, so as to achieve superior performance. In our algorithm, QDWD, which was initially designed for detecting outliers in color images, is used to represent the directional cues in an underwater image. Then, PCA coordinate system is employed to compute pattern distinctness. Meanwhile, we utilize local contrast to further highlight salient regions and suppress background regions. Finally, by integrating QDWD, pattern distinctness, and local contrast, a reliable saliency map for underwater images can be computed and estimated. Experimental results, based on the publicly available OUC-VISION underwater image database, show that the proposed method can produce reliable and promising results, compared to other state-of-the-art saliency-detection models.