Abstract | ||
---|---|---|
We propose a new saliency detection model by combining global information from frequency domain analysis and local information from spatial domain analysis. In the frequency domain analysis, instead of modeling salient regions, we model the nonsalient regions using global information; these so-called repeating patterns that are not distinctive in the scene are suppressed by using spectrum smoothing. In spatial domain analysis, we enhance those regions that are more informative by using a center-surround mechanism similar to that found in the visual cortex. Finally, the outputs from these two channels are combined to produce the saliency map. We demonstrate that the proposed model has the ability to highlight both small and large salient regions in cluttered scenes and to inhibit repeating objects. Experimental results also show that the proposed model outperforms existing algorithms in predicting objects regions where human pay more attention. |
Year | DOI | Venue |
---|---|---|
2011 | 10.5244/C.25.86 | PROCEEDINGS OF THE BRITISH MACHINE VISION CONFERENCE 2011 |
Field | DocType | Citations |
Domain analysis,Frequency domain,Computer vision,Visual cortex,Pattern recognition,Salience (neuroscience),Computer science,Global information,Communication channel,Smoothing,Artificial intelligence,Salient | Conference | 28 |
PageRank | References | Authors |
1.08 | 8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jian Li | 1 | 49 | 6.61 |
Martin D. Levine | 2 | 2039 | 454.84 |
Xiangjing An | 3 | 226 | 12.15 |
Hangen He | 4 | 307 | 23.86 |