Naslov
Color Dog: Guiding the Global Illumination Estimation to Better Accuracy

Autori
Banić, Nikola ; Lončarić, Sven

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
VISAPP 2015: Proceedings of the 10th International Conference on Computer Vision Theory and Applications - (Volume 1) / Braz, José ; Battiato, Sebastiano ; Imai, Francisco - : Scitepress, 2015, 129-135

ISBN
978-989-758-089-5

Skup
10th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

Mjesto i datum
Berlin, Njemačka, 11.03.2015. - 14.03.2015

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
clustering ; color constancy ; illumination estimation ; image enhancement ; white balancing

Sažetak
An important part of image enhancement is color constancy, which aims to make image colors invariant to illumination. In this paper the Color Dog (CD), a new learning-based global color constancy method is proposed. Instead of providing one, it corrects the other methods' illumination estimations by reducing their scattering in the chromaticity space by using a its previously learning partition. The proposed method outperforms all other methods on most high-quality benchmark datasets. The results are presented and discussed.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA