کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
538216 | 1450139 | 2015 | 16 صفحه PDF | دانلود رایگان |
![عکس صفحه اول مقاله: Saliency maps on image hierarchies Saliency maps on image hierarchies](/preview/png/538216.png)
• Model for salient object segmentation based on hierarchies of image partitions.
• High quality saliency maps.
• Detection of salient objects of different scales with accurate boundaries.
• Performance comparable to state-of-the-art techniques in terms of precision–recall.
In this paper we propose two saliency models for salient object segmentation based on a hierarchical image segmentation, a tree-like structure that represents regions at different scales from the details to the whole image (e.g. gPb-UCM, BPT). The first model is based on a hierarchy of image partitions. The saliency at each level is computed on a region basis, taking into account the contrast between regions. The maps obtained for the different partitions are then integrated into a final saliency map. The second model directly works on the structure created by the segmentation algorithm, computing saliency at each node and integrating these cues in a straightforward manner into a single saliency map. We show that the proposed models produce high quality saliency maps. Objective evaluation demonstrates that the two methods achieve state-of-the-art performance in several benchmark datasets.
Journal: Signal Processing: Image Communication - Volume 38, October 2015, Pages 84–99