Naslov
Inpainting color images in learned dictionary

Autori
Filipović, Marko ; Kopriva, Ivica ; Cichocki, Andrzej

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

Izvornik
Proceedings of the 20th European Signal Processing Conference (EUSIPCO 2012) / - : EURASIP, 2012, 66-70

Skup
20th European Signal Processing Conference (EUSIPCO 2012)

Mjesto i datum
Bukurešt, Rumunjska, 27.08.2012. - 31.08.2012

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Learned Dictionary; Independent Component Analysis; Color Image; Inpainting

Sažetak
Sparse representation of natural images over redundant dictionary enables solution of the inpainting problem. A major challenge, in this regard, is learning of a dictionary that is well adapted to the image. Efficient methods are developed for grayscale images represented in patch space by using, for example, K-SVD or independent component analysis algorithms. Here, we address the problem of patch space-based dictionary learning for color images. To this end, an image in RGB color space is represented as a collection of vectorized 3D patch tensors. This leads to the state-of-the-art results in inpainting random and structured patterns of missing values as it is demonstrated in the paper.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA