Saliency Detection using regression trees on hierarchical image segments

Gokhan Yildirim, Appu Shaji, Sabine Susstrunk
2014 2014 IEEE International Conference on Image Processing (ICIP)  
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
more » ... liency. First, we over-segment the image into superpixels and iteratively connect them to form hierarchical image segments. Second, from these segments, we extract biologicallyplausible 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.
doi:10.1109/icip.2014.7025668 dblp:conf/icip/YildirimSS14 fatcat:mln6ut6f3jdmzdptxw3zfr3jma