caa a22 4500 605447128 CHVBK 20210128100130.0 cr unu---uuuuu 210128e20151101xx s 000 0 eng 10.1007/s11042-014-2144-6 doi (NATIONALLICENCE)springer-10.1007/s11042-014-2144-6 Bottom-up saliency estimation using sparse representation and structural redundancy reduction [Elektronische Daten] [Yan Long, DongJian He, Huaibo Song] As we all know that image saliency estimation is an important technique in many computer vision applications. We study bottom-up saliency estimation method based on sparse representation and structural redundancy reduction. Firstly, we learn a set of basis functions using independent component analysis on a large set of natural images and obtain image sparse coefficients. Secondly, we compute the Shannon entropy of the image sparse coefficients to represent its pixels information which build up the image information map. Finally, we discard the structural redundancy of the information map to yield the image saliency map. The performance of the proposed model is studied on natural scenes and psychophysical patterns, and evaluated with ground-truth data. The evaluation proves that the proposed model is highly consistent with the subjective visual attention. Springer Science+Business Media New York, 2014 Saliency estimation nationallicence Non-local means nationallicence Sparse representation nationallicence Redundancy reduction nationallicence Long Yan College of Mechanical and Electronic Engineering, Northwest A&F University, 712100, Yangling Shaanxi, China aut He DongJian College of Mechanical and Electronic Engineering, Northwest A&F University, 712100, Yangling Shaanxi, China aut Song Huaibo College of Mechanical and Electronic Engineering, Northwest A&F University, 712100, Yangling Shaanxi, China aut Multimedia Tools and Applications Springer US; http://www.springer-ny.com 74/21(2015-11-01), 9647-9663 1380-7501 74:21<9647 2015 74 11042 https://doi.org/10.1007/s11042-014-2144-6 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s11042-014-2144-6 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Long Yan College of Mechanical and Electronic Engineering, Northwest A&F University, 712100, Yangling Shaanxi, China aut NATIONALLICENCE 700 1- He DongJian College of Mechanical and Electronic Engineering, Northwest A&F University, 712100, Yangling Shaanxi, China aut NATIONALLICENCE 700 1- Song Huaibo College of Mechanical and Electronic Engineering, Northwest A&F University, 712100, Yangling Shaanxi, China aut NATIONALLICENCE 773 0- Multimedia Tools and Applications Springer US; http://www.springer-ny.com 74/21(2015-11-01), 9647-9663 1380-7501 74:21<9647 2015 74 11042