Weighted color and texture sample selection for image matting

Color information is leveraged by color sampling-based matting methods to find the best known samples for foreground and background color of unknown pixels. Such methods do not perform well if there is an overlap in the color distribution of foreground and background regions because color cannot dis...

Full description

Saved in:
Bibliographic Details
Main Authors: Shahrian, Ehsan, Rajan, Deepu
Other Authors: School of Computer Engineering
Format: Conference or Workshop Item
Language:English
Published: 2013
Subjects:
Online Access:https://hdl.handle.net/10356/98423
http://hdl.handle.net/10220/12501
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-98423
record_format dspace
spelling sg-ntu-dr.10356-984232020-05-28T07:41:42Z Weighted color and texture sample selection for image matting Shahrian, Ehsan Rajan, Deepu School of Computer Engineering IEEE Conference on Computer Vision and Pattern Recognition (2012 : Providence, Rhode Island, US) DRNTU::Engineering::Computer science and engineering Color information is leveraged by color sampling-based matting methods to find the best known samples for foreground and background color of unknown pixels. Such methods do not perform well if there is an overlap in the color distribution of foreground and background regions because color cannot distinguish between these regions and hence, the selected samples cannot reliably estimate the matte. Similarly, alpha propagation based matting methods may fail when the affinity among neighboring pixels is reduced by strong edges. In this paper, we overcome these two problems by considering texture as a feature that can complement color to improve matting. The contribution of texture and color is automatically estimated by analyzing the content of the image. An objective function containing color and texture components is optimized to choose the best foreground and background pair among a set of candidate pairs. Experiments are carried out on a benchmark data set and an independent evaluation of the results show that the proposed method is ranked first among all other image matting methods. 2013-07-29T08:33:03Z 2019-12-06T19:55:07Z 2013-07-29T08:33:03Z 2019-12-06T19:55:07Z 2012 2012 Conference Paper Shahrian, E., & Rajan, D. (2012). Weighted color and texture sample selection for image matting. 2012 IEEE Conference on Computer Vision and Pattern Recognition. https://hdl.handle.net/10356/98423 http://hdl.handle.net/10220/12501 10.1109/CVPR.2012.6247741 en © 2012 IEEE.
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering
spellingShingle DRNTU::Engineering::Computer science and engineering
Shahrian, Ehsan
Rajan, Deepu
Weighted color and texture sample selection for image matting
description Color information is leveraged by color sampling-based matting methods to find the best known samples for foreground and background color of unknown pixels. Such methods do not perform well if there is an overlap in the color distribution of foreground and background regions because color cannot distinguish between these regions and hence, the selected samples cannot reliably estimate the matte. Similarly, alpha propagation based matting methods may fail when the affinity among neighboring pixels is reduced by strong edges. In this paper, we overcome these two problems by considering texture as a feature that can complement color to improve matting. The contribution of texture and color is automatically estimated by analyzing the content of the image. An objective function containing color and texture components is optimized to choose the best foreground and background pair among a set of candidate pairs. Experiments are carried out on a benchmark data set and an independent evaluation of the results show that the proposed method is ranked first among all other image matting methods.
author2 School of Computer Engineering
author_facet School of Computer Engineering
Shahrian, Ehsan
Rajan, Deepu
format Conference or Workshop Item
author Shahrian, Ehsan
Rajan, Deepu
author_sort Shahrian, Ehsan
title Weighted color and texture sample selection for image matting
title_short Weighted color and texture sample selection for image matting
title_full Weighted color and texture sample selection for image matting
title_fullStr Weighted color and texture sample selection for image matting
title_full_unstemmed Weighted color and texture sample selection for image matting
title_sort weighted color and texture sample selection for image matting
publishDate 2013
url https://hdl.handle.net/10356/98423
http://hdl.handle.net/10220/12501
_version_ 1681058115633545216