Name
Abstract | ||
|---|---|---|
Though there are many computational models proposed for saliency detection, few of them take object boundary information into account. This paper presents a hierarchical saliency detection model incorporating probabilistic object boundaries, which is based on the observation that salient objects are generally surrounded by explicit boundaries and show contrast with their surroundings. We perform adaptive thresholding operation on ultrametric contour map, which leads to hierarchical image segmentations, and compute the saliency map for each layer based on the proposed robust center bias, border bias, color dissimilarity and spatial coherence measures. After a linear weighted combination of multi-layer saliency maps, and Bayesian enhancement procedure, the final saliency map is obtained. Extensive experimental results on three challenging benchmark datasets demonstrate that the proposed model outperforms eight state-of-the-art saliency detection models. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1142/S0218001417550102 | INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE |
Keywords | Field | DocType |
Saliency detection, center bias, object segmentation | Salience (neuroscience),Artificial intelligence,Thresholding,Probabilistic logic,Computer vision,Pattern recognition,Kadir–Brady saliency detector,Contour line,Computational model,Ultrametric space,Machine learning,Mathematics,Bayesian probability | Journal |
Volume | Issue | ISSN |
31 | 6 | 0218-0014 |
Citations | PageRank | References |
1 | 0.35 | 28 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Haijun Lei | 1 | 107 | 15.30 |
| Hai Xie | 2 | 9 | 5.30 |
| Wenbin Zou | 3 | 268 | 19.75 |
| Xiaoli Sun | 4 | 26 | 5.49 |
| Kidiyo Kpalma | 5 | 191 | 20.06 |
| Nikos Komodakis | 6 | 2301 | 108.03 |