Abstract
An image and video retargeting algorithm using an adaptive scaling function is proposed in this work. We first construct an importance map which uses multiple features: gradient, saliency, and motion difference. Then, we determine an adaptive scaling function, which represents a scaling factor of each column in the source image. Finally, the target image is constructed with a weighted average filter using those scaling factors. Moreover, we extend this algorithm to video sequence. Simulation results demonstrate that the proposed algorithm provides better results than conventional retargeting methods.
| Original language | English |
|---|---|
| Title of host publication | European Signal Processing Conference |
| Pages | 819-823 |
| Number of pages | 5 |
| Publication status | Published - 2009 |
| Event | 17th European Signal Processing Conference, EUSIPCO 2009 - Glasgow, United Kingdom Duration: 2009 Aug 24 → 2009 Aug 28 |
Other
| Other | 17th European Signal Processing Conference, EUSIPCO 2009 |
|---|---|
| Country | United Kingdom |
| City | Glasgow |
| Period | 09/8/24 → 09/8/28 |
ASJC Scopus subject areas
- Signal Processing
- Electrical and Electronic Engineering
Cite this
Image and video retargeting using adaptive scaling function. / Kim, Jin Hwan; Kim, Jun Seong; Kim, Chang-Su.
European Signal Processing Conference. 2009. p. 819-823.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Image and video retargeting using adaptive scaling function
AU - Kim, Jin Hwan
AU - Kim, Jun Seong
AU - Kim, Chang-Su
PY - 2009
Y1 - 2009
N2 - An image and video retargeting algorithm using an adaptive scaling function is proposed in this work. We first construct an importance map which uses multiple features: gradient, saliency, and motion difference. Then, we determine an adaptive scaling function, which represents a scaling factor of each column in the source image. Finally, the target image is constructed with a weighted average filter using those scaling factors. Moreover, we extend this algorithm to video sequence. Simulation results demonstrate that the proposed algorithm provides better results than conventional retargeting methods.
AB - An image and video retargeting algorithm using an adaptive scaling function is proposed in this work. We first construct an importance map which uses multiple features: gradient, saliency, and motion difference. Then, we determine an adaptive scaling function, which represents a scaling factor of each column in the source image. Finally, the target image is constructed with a weighted average filter using those scaling factors. Moreover, we extend this algorithm to video sequence. Simulation results demonstrate that the proposed algorithm provides better results than conventional retargeting methods.
UR - http://www.scopus.com/inward/record.url?scp=84863752124&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84863752124&partnerID=8YFLogxK
M3 - Conference contribution
SP - 819
EP - 823
BT - European Signal Processing Conference
ER -