- Tytuł:
- A two-layer neural system for reduced-reference visual quality assessment
- Autorzy:
-
Redi, J.
Gastaldo, P.
Zunino, R. - Powiązania:
- https://bibliotekanauki.pl/articles/91584.pdf
- Data publikacji:
- 2011
- Wydawca:
- Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
- Tematy:
-
reduced-reference system
image
visual quality assessmen
luminance distribution
visual distortions
support vector machines
SVM - Opis:
- Real-time assessment of visual quality can be efficiently supported by reduced-refe-rence paradigms, which require a very limited amount of information on the original signal, easily embeddable in the signal itself. In this paper, a reduced-reference system for image quality assessment is proposed, based on a small sized numerical description of images encoding the luminance distribution and its variations due to visual distortions. The assessment paradigm is implemented exploiting machine learning tools and articulates in two phases: first, a Support Vector Machines-based classifier identifies the kind of distortion affecting the image; then, the actual quality level of the distorted image is computed by a specifically trained SVM regressor. The general validity of the approach is supported by experimental validations based on subjective quality data.
- Źródło:
-
Journal of Artificial Intelligence and Soft Computing Research; 2011, 1, 1; 27-41
2083-2567
2449-6499 - Pojawia się w:
- Journal of Artificial Intelligence and Soft Computing Research
- Dostawca treści:
- Biblioteka Nauki