Cover Image

A geometric approach for color image regularization

We present a new vectorial total variation method that addresses the problem of color consistent image filtering. Our approach is inspired from the double-opponent cell representation in the human visual cortex. Existing methods of vectorial total variation regularizers have insufficient (or no) cou...

Full description

Saved in:
Bibliographic Details
Main Authors: Åström, Freddie (Author) , Schnörr, Christoph (Author)
Format: Article (Journal)
Language:English
Published: 27 October 2017
In: Computer vision and image understanding
Year: 2017, Volume: 165, Pages: 43-59
ISSN:1090-235X
DOI:10.1016/j.cviu.2017.10.013
Online Access:Verlag, Volltext: http://dx.doi.org/10.1016/j.cviu.2017.10.013
Verlag, Volltext: http://www.sciencedirect.com/science/article/pii/S1077314217301765
Get full text
Author Notes:Freddie Åström, Christoph Schnörr

MARC

LEADER 00000caa a2200000 c 4500
001 1580183581
003 DE-627
005 20220814223909.0
007 cr uuu---uuuuu
008 180820s2017 xx |||||o 00| ||eng c
024 7 |a 10.1016/j.cviu.2017.10.013  |2 doi 
035 |a (DE-627)1580183581 
035 |a (DE-576)510183581 
035 |a (DE-599)BSZ510183581 
035 |a (OCoLC)1341017049 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 28  |2 sdnb 
100 1 |a Åström, Freddie  |e VerfasserIn  |0 (DE-588)1153903539  |0 (DE-627)1015504132  |0 (DE-576)500624267  |4 aut 
245 1 2 |a A geometric approach for color image regularization  |c Freddie Åström, Christoph Schnörr 
264 1 |c 27 October 2017 
300 |a 17 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Gesehen am 20.08.2018 
520 |a We present a new vectorial total variation method that addresses the problem of color consistent image filtering. Our approach is inspired from the double-opponent cell representation in the human visual cortex. Existing methods of vectorial total variation regularizers have insufficient (or no) coupling between the color channels and thus may introduce color artifacts. We address this problem by introducing a novel coupling between the color channels related to a pullback-metric from the opponent space to the data (RGB color) space. Our energy is a non-convex, non-smooth higher-order vectorial total variation approach and promotes color consistent image filtering via a coupling term. For a convex variant, we show well-posedness and existence of a solution in the space of vectorial bounded variation. For the higher-order scheme we employ a half-quadratic strategy, which model the non-convex energy terms as the infimum of a sequence of quadratic functions. In experiments, we elaborate on traditional image restoration applications of inpainting, deblurring and denoising. Regarding the latter, we consider two noise scenarios i) intensity and chromaticity (the color representation of the double-opponent space) are corrupted by uniform noise and ii) only the chromaticity is corrupted with noise. In the latter case, we demonstrate state of the art restoration quality with respect to structure coherence and color consistency. 
650 4 |a Color image restoration 
650 4 |a Double-opponent space 
650 4 |a Image analysis 
650 4 |a Non-convex regularization 
650 4 |a Split-Bregman 
650 4 |a Vectorial total variation 
700 1 |a Schnörr, Christoph  |e VerfasserIn  |0 (DE-588)1023033348  |0 (DE-627)717351017  |0 (DE-576)168404540  |4 aut 
773 0 8 |i Enthalten in  |t Computer vision and image understanding  |d San Diego, Calif. : Elsevier, 1995  |g 165(2017), Seite 43-59  |h Online-Ressource  |w (DE-627)254637876  |w (DE-600)1462895-8  |w (DE-576)103373063  |x 1090-235X  |7 nnas  |a A geometric approach for color image regularization 
773 1 8 |g volume:165  |g year:2017  |g pages:43-59  |g extent:17  |a A geometric approach for color image regularization 
856 4 0 |u http://dx.doi.org/10.1016/j.cviu.2017.10.013  |x Verlag  |x Resolving-System  |3 Volltext 
856 4 0 |u http://www.sciencedirect.com/science/article/pii/S1077314217301765  |x Verlag  |3 Volltext 
951 |a AR 
992 |a 20180820 
993 |a Article 
994 |a 2017 
998 |g 1023033348  |a Schnörr, Christoph  |m 1023033348:Schnörr, Christoph  |d 110000  |d 110200  |d 110000  |d 110400  |d 700000  |d 708000  |e 110000PS1023033348  |e 110200PS1023033348  |e 110000PS1023033348  |e 110400PS1023033348  |e 700000PS1023033348  |e 708000PS1023033348  |k 0/110000/  |k 1/110000/110200/  |k 0/110000/  |k 1/110000/110400/  |k 0/700000/  |k 1/700000/708000/  |p 2  |y j 
998 |g 1153903539  |a Åström, Freddie  |m 1153903539:Åström, Freddie  |d 700000  |d 708070  |e 700000PA1153903539  |e 708070PA1153903539  |k 0/700000/  |k 1/700000/708070/  |p 1  |x j 
999 |a KXP-PPN1580183581  |e 3022599064 
BIB |a Y 
SER |a journal 
JSO |a {"language":["eng"],"note":["Gesehen am 20.08.2018"],"type":{"media":"Online-Ressource","bibl":"article-journal"},"origin":[{"dateIssuedKey":"2017","dateIssuedDisp":"27 October 2017"}],"title":[{"title":"A geometric approach for color image regularization","title_sort":"geometric approach for color image regularization"}],"person":[{"given":"Freddie","role":"aut","display":"Åström, Freddie","family":"Åström"},{"given":"Christoph","role":"aut","family":"Schnörr","display":"Schnörr, Christoph"}],"id":{"doi":["10.1016/j.cviu.2017.10.013"],"eki":["1580183581"]},"relHost":[{"disp":"A geometric approach for color image regularizationComputer vision and image understanding","part":{"volume":"165","extent":"17","text":"165(2017), Seite 43-59","pages":"43-59","year":"2017"},"type":{"bibl":"periodical","media":"Online-Ressource"},"note":["Gesehen am 06.01.2021"],"origin":[{"dateIssuedKey":"1995","publisher":"Elsevier ; Acad. Pr.","publisherPlace":"San Diego, Calif. ; Orlando, Fla.","dateIssuedDisp":"1995-"}],"titleAlt":[{"title":"CVIU"},{"title":"CVGIP"},{"title":"CVGIP / Image understanding"}],"title":[{"title":"Computer vision and image understanding","subtitle":"CVIU","title_sort":"Computer vision and image understanding"}],"language":["eng"],"physDesc":[{"extent":"Online-Ressource"}],"recId":"254637876","pubHistory":["61.1995 - 117.2013; Vol. 118.2014 -"],"id":{"zdb":["1462895-8"],"eki":["254637876"],"issn":["1090-235X"]}}],"recId":"1580183581","physDesc":[{"extent":"17 S."}],"name":{"displayForm":["Freddie Åström, Christoph Schnörr"]}} 
SRT |a ASTROEMFREGEOMETRICA2720 

Similar Items