Abstract
Object or region based image processing can be performed more efficiently with information pertaining locations that are visually salient to human perception with the aid of a saliency map. The saliency map is a master topological map having the possible locations of objects or regions which a human perceived as important/salient. In this paper, a method to compute the saliency map in the wavelet transform domain is explored. Previous works involving saliency in this domain usually involves salient points, which are in fact accurate but they do not cover the area as a region and involve heavy repeated iterations. The method explored in this paper is compared to two state-of-art methods in which these methods involve the frequency domain. The presented method provides more accurate salient regions compared to the other two methods while retaining a resolution which the salient regions are visually identifiable.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010 |
| Pages | 692-695 |
| Number of pages | 4 |
| Volume | 1 |
| DOIs | |
| Publication status | Published - 01 Nov 2010 |
| Event | 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010 - Chengdu, China Duration: 09 Jul 2010 → 11 Jul 2010 |
Conference
| Conference | 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010 |
|---|---|
| Country | China |
| City | Chengdu |
| Period | 09/07/10 → 11/07/10 |
Fingerprint
Cite this
}
Bottom-up visual saliency map using wavelet transform domain. / Ngau, Christopher Wing Hong; Ang, Li Minn; Seng, Kah Phooi.
Proceedings - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010. Vol. 1 2010. p. 692-695 5564545.Research output: Book chapter/Published conference paper › Conference paper
TY - GEN
T1 - Bottom-up visual saliency map using wavelet transform domain
AU - Ngau, Christopher Wing Hong
AU - Ang, Li Minn
AU - Seng, Kah Phooi
PY - 2010/11/1
Y1 - 2010/11/1
N2 - Object or region based image processing can be performed more efficiently with information pertaining locations that are visually salient to human perception with the aid of a saliency map. The saliency map is a master topological map having the possible locations of objects or regions which a human perceived as important/salient. In this paper, a method to compute the saliency map in the wavelet transform domain is explored. Previous works involving saliency in this domain usually involves salient points, which are in fact accurate but they do not cover the area as a region and involve heavy repeated iterations. The method explored in this paper is compared to two state-of-art methods in which these methods involve the frequency domain. The presented method provides more accurate salient regions compared to the other two methods while retaining a resolution which the salient regions are visually identifiable.
AB - Object or region based image processing can be performed more efficiently with information pertaining locations that are visually salient to human perception with the aid of a saliency map. The saliency map is a master topological map having the possible locations of objects or regions which a human perceived as important/salient. In this paper, a method to compute the saliency map in the wavelet transform domain is explored. Previous works involving saliency in this domain usually involves salient points, which are in fact accurate but they do not cover the area as a region and involve heavy repeated iterations. The method explored in this paper is compared to two state-of-art methods in which these methods involve the frequency domain. The presented method provides more accurate salient regions compared to the other two methods while retaining a resolution which the salient regions are visually identifiable.
KW - Frequency-time domain
KW - Saliency map
KW - Salient region
KW - Wavelet transform
UR - http://www.scopus.com/inward/record.url?scp=77958601297&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77958601297&partnerID=8YFLogxK
U2 - 10.1109/ICCSIT.2010.5564545
DO - 10.1109/ICCSIT.2010.5564545
M3 - Conference paper
AN - SCOPUS:77958601297
SN - 9781424455386
VL - 1
SP - 692
EP - 695
BT - Proceedings - 2010 3rd IEEE International Conference on Computer Science and Information Technology, ICCSIT 2010
ER -