Non-parametric natural image matting
Non-parametric natural image matting
Natural image matting is an extremely challenging image processing problem due to its ill-posed nature. It often requires skilled user interaction to aid definition of foreground and background regions. Current algorithms use these predefined regions to build local foreground and background colour models. In this paper we propose a novel approach which uses non-parametric statistics to model image appearance variations. This technique overcomes the limitations of previous parametric approaches which are purely colour-based and thereby unable to model natural image structure. The proposed technique consists of three successive stages: (i) background colour estimation, (ii) foreground colour estimation, (iii) alpha estimation. Colour estimation uses patch-based matching techniques to efficiently recover the optimum colour by comparison against patches from the known regions. Quantitative evaluation against ground truth demonstrates that the technique produces better results and successfully recovers fine details such as hair where many other algorithms fail. ©2009 IEEE.
Alpha matte, Composite, Non-parametric statistics, Trimap, Estimation, Image analysis, Imaging systems, Background region, Colour models, Ground truth, Ill posed, Image processing problems, Matching techniques, Model images, Natural image matting, Natural images, Non-parametric, Other algorithms, Parametric approach, Quantitative evaluation, User interaction, Color
3213-3216
Sarim, M.
1242380f-3b23-491b-ab75-85daccc93f92
Hilton, Adrian
12782a55-4c4d-4dfb-a690-62505f6665db
Guillemaut, J.-Y.
fcaefbd8-8ba1-4c43-978c-0b5d432a3285
Kim, H.
2c7c135c-f00b-4409-acb2-85b3a9e8225f
2009
Sarim, M.
1242380f-3b23-491b-ab75-85daccc93f92
Hilton, Adrian
12782a55-4c4d-4dfb-a690-62505f6665db
Guillemaut, J.-Y.
fcaefbd8-8ba1-4c43-978c-0b5d432a3285
Kim, H.
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Sarim, M., Hilton, Adrian, Guillemaut, J.-Y. and Kim, H.
(2009)
Non-parametric natural image matting.
16th IEEE International Conference on Image Processing (ICIP).
07 - 10 Nov 2010.
.
(doi:10.1109/ICIP.2009.5414367).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Natural image matting is an extremely challenging image processing problem due to its ill-posed nature. It often requires skilled user interaction to aid definition of foreground and background regions. Current algorithms use these predefined regions to build local foreground and background colour models. In this paper we propose a novel approach which uses non-parametric statistics to model image appearance variations. This technique overcomes the limitations of previous parametric approaches which are purely colour-based and thereby unable to model natural image structure. The proposed technique consists of three successive stages: (i) background colour estimation, (ii) foreground colour estimation, (iii) alpha estimation. Colour estimation uses patch-based matching techniques to efficiently recover the optimum colour by comparison against patches from the known regions. Quantitative evaluation against ground truth demonstrates that the technique produces better results and successfully recovers fine details such as hair where many other algorithms fail. ©2009 IEEE.
This record has no associated files available for download.
More information
Published date: 2009
Additional Information:
Cited By :7
Export Date: 30 April 2020
Venue - Dates:
16th IEEE International Conference on Image Processing (ICIP), 2010-11-07 - 2010-11-10
Keywords:
Alpha matte, Composite, Non-parametric statistics, Trimap, Estimation, Image analysis, Imaging systems, Background region, Colour models, Ground truth, Ill posed, Image processing problems, Matching techniques, Model images, Natural image matting, Natural images, Non-parametric, Other algorithms, Parametric approach, Quantitative evaluation, User interaction, Color
Identifiers
Local EPrints ID: 440565
URI: http://eprints.soton.ac.uk/id/eprint/440565
PURE UUID: 6759f31e-00ca-47ee-9f54-97ebefa543c0
Catalogue record
Date deposited: 07 May 2020 16:37
Last modified: 17 Mar 2024 04:01
Export record
Altmetrics
Contributors
Author:
M. Sarim
Author:
Adrian Hilton
Author:
J.-Y. Guillemaut
Author:
H. Kim
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics