Title :
Decorrelated Vectorial Total Variation
Author :
Ono, Shintaro ; Yamada, Isao
Author_Institution :
Dept. of Commun. & Comput., Tokyo Inst. of Technol. Eng., Tokyo, Japan
Abstract :
This paper proposes a new vectorial total variation prior (VTV) for color images. Different from existing VTVs, our VTV, named the decorrelated vectorial total variation prior (D-VTV), measures the discrete gradients of the luminance component and that of the chrominance one in a separated manner, which significantly reduces undesirable uneven color effects. Moreover, a higher-order generalization of the D-VTV, which we call the decorrelated vectorial total generalized variation prior (D-VTGV), is also developed for avoiding the staircasing effect that accompanies the use of VTVs. A noteworthy property of the D-VT(G)V is that it enables us to efficiently minimize objective functions involving it by a primal-dual splitting method. Experimental results illustrate their utility.
Keywords :
convex programming; generalisation (artificial intelligence); image colour analysis; D-VTGV; D-VTV; color effects; color images; decorrelated vectorial total generalized variation prior; decorrelated vectorial total variation prior; objective functions; primal-dual splitting method; Computer vision; Conferences; Gain; PSNR; Pattern recognition; Standards;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on
Conference_Location :
Columbus, OH
DOI :
10.1109/CVPR.2014.521