Abstract | ||
---|---|---|
Confusing visual appearance and scattered small-scale patterns commonly exist in natural images, which forms a challenge for prior saliency detection methods. Inspired by the sensitivity to edge information of Human Visual Systems, we propose a universal edge-oriented framework to improve the performance of existing salient detection methods. Firstly, edge probability map is extracted from images and utilized to get edge-based over segmentation. Secondly, merging segments by a hierarchical model to generate edge regions. Finally, the proposed framework turns saliency detection to assign a saliency value to each edge region. Experimental results demonstrate the effectiveness of our framework. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/BIBE.2017.00-23 | 2017 IEEE 17th International Conference on Bioinformatics and Bioengineering (BIBE) |
Keywords | Field | DocType |
edge-oriented,universal framework,saliency detection | Pattern recognition,Computer science,Visualization,Segmentation,Salience (neuroscience),Feature extraction,Image segmentation,Artificial intelligence,Hierarchical database model,Machine learning,Salient,Visual appearance | Conference |
ISBN | Citations | PageRank |
978-1-5386-1325-2 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qingzhen Xu | 1 | 26 | 4.69 |
Fengyun Wang | 2 | 17 | 2.06 |
Yongyi Gong | 3 | 0 | 1.01 |
Zhoutao Wang | 4 | 16 | 1.32 |