000190062 001__ 190062
000190062 005__ 20190316235737.0
000190062 037__ $$aREP_WORK
000190062 245__ $$aLow-Level Salient Region Detection Using Multi-Scale Filtering
000190062 269__ $$a2013
000190062 260__ $$c2013
000190062 300__ $$a9
000190062 336__ $$aReports
000190062 520__ $$aVarious computer visions tasks require a summary of visually important regions in an image. Thus, developing simple yet accurate salient region detection algorithms has become an important research topic. The currently best performing state-of-the-art saliency detection algorithms incorporate image segmentation for abstraction. However, errors introduced in this step of the algorithms are transferred to the final saliency map estimation. In order to avoid this problem, we propose a simple low-level salient region detection algorithm that uses multi-scale filters. We consider each possible combination of filtered image pairs as weak saliency maps and combine them according to their adaptively computed compactness and center prior. Our filterbased method successfully eliminates the texture in the background and gives relatively uniform salient regions for multi-colored objects. In addition, the combination of several multi-scale filters produces a full-resolution saliency output, which preserves object boundaries. We show that our algorithm outperforms the most recent state-of-the-art methods on a database of 1000 images with pixel-precision ground truths.
000190062 6531_ $$aimage saliency
000190062 6531_ $$amulti-scale filtering
000190062 6531_ $$alow-level
000190062 6531_ $$afrequency analysis
000190062 700__ $$0245739$$g200257$$aYildirim, Gökhan
000190062 700__ $$aSüsstrunk, Sabine$$g125681$$0241946
000190062 8564_ $$uhttps://infoscience.epfl.ch/record/190062/files/Low-Level%20Salient%20Region%20Detection%20Using%20Multi-Scale%20Filtering.pdf$$zPreprint$$s3111310$$yPreprint
000190062 8564_ $$uhttps://infoscience.epfl.ch/record/190062/files/supplementary_material.pdf$$s2098105
000190062 909C0 $$xU10429$$0252320$$pIVRL
000190062 909CO $$qGLOBAL_SET$$pIC$$ooai:infoscience.tind.io:190062$$preport
000190062 917Z8 $$x200257
000190062 937__ $$aEPFL-REPORT-190062
000190062 973__ $$aEPFL
000190062 980__ $$aREPORT