Abstract
Image quality assessment is a complex problem due to subjective nature of human visual perception. One of possible ways to take into consideration user's subjectivism is to develop interactive system which could learn the properties of user's visual perception. In this paper we present a novel way to do this via interactive neuroevolution approach. The key feature of this approach is training of artificial neural network to evaluate image quality on the base of interaction with user. Obtained solutions can then be used for image quality assessment for various automated image and video processing techniques.
| Original language | English |
|---|---|
| Title of host publication | GraphiCon 2007 - International Conference on Computer Graphics and Vision, Proceedings |
| Publication status | Published - 2007 |
| Event | 17th International Conference on Computer Graphics and Vision, GraphiCon 2007 - Moscow, Russian Federation Duration: 23 Jun 2007 → 27 Jun 2007 |
Other
| Other | 17th International Conference on Computer Graphics and Vision, GraphiCon 2007 |
|---|---|
| Country | Russian Federation |
| City | Moscow |
| Period | 23.6.07 → 27.6.07 |
Fingerprint
Keywords
- Image quality assessment
- Interactive evolution
- Neuroevolution
ASJC Scopus subject areas
- Computer Graphics and Computer-Aided Design
- Computer Vision and Pattern Recognition
Cite this
No-reference image quality assessment through interactive neuroevolution. / Tsoy, Yury R.; Spitsyn, Vladimir G.; Chernyavsky, Alexander V.
GraphiCon 2007 - International Conference on Computer Graphics and Vision, Proceedings. 2007.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - No-reference image quality assessment through interactive neuroevolution
AU - Tsoy, Yury R.
AU - Spitsyn, Vladimir G.
AU - Chernyavsky, Alexander V.
PY - 2007
Y1 - 2007
N2 - Image quality assessment is a complex problem due to subjective nature of human visual perception. One of possible ways to take into consideration user's subjectivism is to develop interactive system which could learn the properties of user's visual perception. In this paper we present a novel way to do this via interactive neuroevolution approach. The key feature of this approach is training of artificial neural network to evaluate image quality on the base of interaction with user. Obtained solutions can then be used for image quality assessment for various automated image and video processing techniques.
AB - Image quality assessment is a complex problem due to subjective nature of human visual perception. One of possible ways to take into consideration user's subjectivism is to develop interactive system which could learn the properties of user's visual perception. In this paper we present a novel way to do this via interactive neuroevolution approach. The key feature of this approach is training of artificial neural network to evaluate image quality on the base of interaction with user. Obtained solutions can then be used for image quality assessment for various automated image and video processing techniques.
KW - Image quality assessment
KW - Interactive evolution
KW - Neuroevolution
UR - http://www.scopus.com/inward/record.url?scp=84871270112&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84871270112&partnerID=8YFLogxK
M3 - Conference contribution
BT - GraphiCon 2007 - International Conference on Computer Graphics and Vision, Proceedings
ER -