Salient Edges: A Multi Scale Approach

Finding the salient features of an image is required by many applications such as image re-targeting, automatic cropping, object tracking, video encoding, and selective sharpening. In this paper we present a novel method for detection of salient objects' edges which combines local and regional considerations. Our method uses multiple levels of detail, and does not favor one level over another as done in other multi-scale methods. The proposed local-regional multi-level approach detects edges of salient objects and can handle highly textured images, while maintaining a low computational cost. We show empirically that these are useful for improving image abstraction results. We further provide qualitative results together with quantitative evaluation which shows that the proposed method outperforms previous work on saliency detection.