On measuring low-level self and relative saliency in photographic images

Abstract Measuring perceptual saliency of different regions in a scene is important for determining regions of interest (ROI). Color, texture and shape cues are good low-level features for detecting saliency. While self saliency refers to intrinsic attributes of a particular region, relative saliency is used to measure how salient a region is relative to its surrounding and thus needs to be defined within a spatial context. A few spatial context models are investigated in this study. In particular, we propose an auto-scaled, extended neighborhood-based context model to obtain reliable measurements of relative saliency features. Comparison of three context models has shown that the proposed model is capable of generating predicates more consistent with perceived saliency.