Pregled bibliografske jedinice broj: 728168
Color Cat : Remembering Colors for Illumination Estimation
Color Cat : Remembering Colors for Illumination Estimation // IEEE signal processing letters, 22 (2015), 6; 651-655 doi:10.1109/LSP.2014.2366973 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 728168 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Color Cat : Remembering Colors for Illumination Estimation
Autori
Banić, Nikola ; Lončarić, Sven
Izvornik
IEEE signal processing letters (1070-9908) 22
(2015), 6;
651-655
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
chromaticity ; color constancy ; illumination estimation ; image enhancement ; linear regression ; white balancing
Sažetak
Having images look the same regardless of the scene illumination is a desirable feature called color constancy. In this paper the Color Cat (CC), a novel fast and accurate learning-based method for achieving computational color constancy is proposed. It learns and then uses the relationship between transformed color histograms and the regularity in the possible illumination colors. The proposed method is tested on a publicly available color constancy dataset and it is shown to outperform most of the other color constancy methods in terms of accuracy and computation cost. The results are presented and discussed. The source code is available at http://www.fer.unizg.hr/ipg/resources/color_constancy/.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Projekti:
036-0362214-1989 - Inteligentne metode obrade i analize slika (Lončarić, Sven, MZO ) ( CroRIS)
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb
Citiraj ovu publikaciju:
Časopis indeksira:
- Current Contents Connect (CCC)
- Web of Science Core Collection (WoSCC)
- Science Citation Index Expanded (SCI-EXP)
- SCI-EXP, SSCI i/ili A&HCI
- Scopus