Graph-Based Salient Region Detection through Linear Neighborhoods

Figure 3

The framework of the two-phase saliency detection model. (a) Input image and (b) the ground truth labelled by humans. ((c) and (d)) The saliency maps generated by the first phase and second phase of graph labelling based saliency model, respectively.

(a) Input image

(b) Ground truth

(c) Saliency map for first phase

(d) Saliency map for second phase