Name
Abstract | ||
|---|---|---|
The currently best performing state-of-the-art saliency detection algorithms incorporate heuristic functions to evaluate saliency. They require parameter tuning, and the relationship between the parameter value and visual saliency is often not well understood. Instead of using parametric methods we follow a machine learning approach, which is parameter free, to estimate saliency. Our method learns data-driven saliency-estimation functions and exploits the contributions of visual properties on saliency. First, we over-segment the image into superpixels and iteratively connect them to form hierarchical image segments. Second, from these segments, we extract biologically-plausible visual features. Finally, we use regression trees to learn the relationship between the feature values and visual saliency. We show that our algorithm outperforms the most recent state-of-the-art methods on three public databases. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/ICIP.2014.7025668 | Image Processing |
Keywords | Field | DocType |
image segmentation,iterative methods,learning (artificial intelligence),regression analysis,trees (mathematics),biologically-plausible visual feature,data-driven saliency-estimation function,hierarchical image segmentation,iterative method,machine learning approach,parametric tuning method,public database,regression tree,visual saliency detection algorithm,hierarchical regression,regression tree,saliency,superpixels | Computer vision,Decision tree,Parametric methods,Heuristic,Kadir–Brady saliency detector,Pattern recognition,Regression,Computer science,Salience (neuroscience),Artificial intelligence,Visual saliency | Conference |
ISSN | Citations | PageRank |
1522-4880 | 0 | 0.34 |
References | Authors | |
15 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Gökhan Yildirim | 1 | 16 | 3.06 |
| Appu Shaji | 2 | 1980 | 55.52 |
| Sabine Süsstrunk | 3 | 4984 | 207.02 |