Loading...
Please wait, while we are loading the content...
Similar Documents
Statistical Textural Distinctiveness for Salient Region Detection in Natural Images
| Content Provider | CiteSeerX |
|---|---|
| Author | Scharfenberger, Christian Wong, Er Fergani, Khalil Zelek, John S. Clausi, David A. |
| Abstract | A novel statistical textural distinctiveness approach for robustly detecting salient regions in natural images is pro-posed. Rotational-invariant neighborhood-based textural representations are extracted and used to learn a set of rep-resentative texture atoms for defining a sparse texture model for the image. Based on the learnt sparse texture model, a weighted graphical model is constructed to characterize the statistical textural distinctiveness between all represen-tative texture atom pairs. Finally, the saliency of each pixel in the image is computed based on the probability of occur-rence of the representative texture atoms, their respective statistical textural distinctiveness based on the constructed graphical model, and general visual attentive constraints. Experimental results using a public natural image dataset and a variety of performance evaluation metrics show that the proposed approach provides interesting and promising results when compared to existing saliency detection meth-ods. 1. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Natural Image Statistical Textural Distinctiveness Salient Region Detection Representative Texture Atom Rep-resentative Texture Atom Sparse Texture Model Novel Statistical Textural Distinctiveness Approach Weighted Graphical Model General Visual Attentive Constraint Saliency Detection Meth-ods Learnt Sparse Texture Model Performance Evaluation Metric Respective Statistical Textural Distinctiveness Rotational-invariant Neighborhood-based Textural Representation Salient Region Constructed Graphical Model Experimental Result Public Natural Image Dataset Promising Result Represen-tative Texture Atom Pair |
| Content Type | Text |
