“…A number of computational models measure the saliency based on global, local and regional contrasts with different forms [6]- [11]. A variety of theories and methods, including information theory [12], [13], graph theory [14], [15], machine learning [16], [17], statistical model [18]- [20], Bayesian model [21], tree analysis [22] and frequency domain analysis [23]- [25], have been exploited to build saliency models. Recently, some saliency models such as [7], [11], [18], [22], and [26]- [28] benefit from measuring the saliency on the basis of region segmentation to effectively incorporate global information at region level, in order to improve the performance of salient region detection.…”