@article{filali_multi-scale_2016,

title = {Multi-scale salient object detection using graph ranking and global–local saliency refinement},

author = {I. Filali and M. S. Allili and N. Benblidia},

url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84982091007&doi=10.1016%2fj.image.2016.07.007&partnerID=40&md5=60dabe68b5cff4b5d00216d6a632e1cd},

doi = {10.1016/j.image.2016.07.007},

issn = {09235965},

year  = {2016},

date = {2016-01-01},

journal = {Signal Processing: Image Communication},

volume = {47},

pages = {380–401},

abstract = {We propose an algorithm for salient object detection (SOD) based on multi-scale graph ranking and iterative local–global object refinement. Starting from a set of multi-scale image decompositions using superpixels, we propose an objective function which is optimized on a multi-layer graph structure to diffuse saliency from image borders to salient objects. This step aims at roughly estimating the location and extent of salient objects in the image. We then enhance the object saliency through an iterative process employing random forests and local boundary refinement using color, texture and edge information. We also use a feature weighting scheme to ensure optimal object/background discrimination. Our algorithm yields very accurate saliency maps for SOD while maintaining a reasonable computational time. Experiments on several standard datasets have shown that our approach outperforms several recent methods dealing with SOD. © 2016 Elsevier B.V.},

note = {Publisher: Elsevier B.V.},

keywords = {Algorithms, Boundary information, Decision trees, Feature relevance, Iterative methods, Multi-layer graphs, Object detection, Object recognition, Random forests, Salient object detection},

pubstate = {published},

tppubtype = {article}

}