Dynamic curve color model for image matting

Sunyoung Cho, Hyeran Byun

Research output: Contribution to journalArticle

Abstract

Image matting is the process of estimating the foreground and background elements from a single image with limited user input. To solve this severely under-constrained problem, there exist various methods to construct color models for an image. Most previous color models can fail to estimate accurate mattes for complex images of nonlinear color distributions due to their simple color models. In this paper, we present a new dynamic curve color model for image matting that can handle nonlinear color distributions. We show that the colors of a local region can be fit to a curve when the local region includes three types of colors - foreground, background, and unknown mixed colors. Based on these colors in the local region, we adaptively construct a curve color model using a quadratic Bézier curve model. Our curve model allows the derivation of a new closed-form matting equation for estimating alpha values of colors forming a curve. We show that our method estimates alpha mattes more accurately than recent existing methods through visual and quantitative comparisons.

Original languageEnglish
Pages (from-to)920-933
Number of pages14
JournalPattern Recognition Letters
Volume33
Issue number7
DOIs
Publication statusPublished - 2012 May 1

Fingerprint

Color

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Cho, Sunyoung ; Byun, Hyeran. / Dynamic curve color model for image matting. In: Pattern Recognition Letters. 2012 ; Vol. 33, No. 7. pp. 920-933.
@article{b8020bb944ce470294f820f950437f0c,
title = "Dynamic curve color model for image matting",
abstract = "Image matting is the process of estimating the foreground and background elements from a single image with limited user input. To solve this severely under-constrained problem, there exist various methods to construct color models for an image. Most previous color models can fail to estimate accurate mattes for complex images of nonlinear color distributions due to their simple color models. In this paper, we present a new dynamic curve color model for image matting that can handle nonlinear color distributions. We show that the colors of a local region can be fit to a curve when the local region includes three types of colors - foreground, background, and unknown mixed colors. Based on these colors in the local region, we adaptively construct a curve color model using a quadratic B{\'e}zier curve model. Our curve model allows the derivation of a new closed-form matting equation for estimating alpha values of colors forming a curve. We show that our method estimates alpha mattes more accurately than recent existing methods through visual and quantitative comparisons.",
author = "Sunyoung Cho and Hyeran Byun",
year = "2012",
month = "5",
day = "1",
doi = "10.1016/j.patrec.2011.04.012",
language = "English",
volume = "33",
pages = "920--933",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",
number = "7",

}

Dynamic curve color model for image matting. / Cho, Sunyoung; Byun, Hyeran.

In: Pattern Recognition Letters, Vol. 33, No. 7, 01.05.2012, p. 920-933.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Dynamic curve color model for image matting

AU - Cho, Sunyoung

AU - Byun, Hyeran

PY - 2012/5/1

Y1 - 2012/5/1

N2 - Image matting is the process of estimating the foreground and background elements from a single image with limited user input. To solve this severely under-constrained problem, there exist various methods to construct color models for an image. Most previous color models can fail to estimate accurate mattes for complex images of nonlinear color distributions due to their simple color models. In this paper, we present a new dynamic curve color model for image matting that can handle nonlinear color distributions. We show that the colors of a local region can be fit to a curve when the local region includes three types of colors - foreground, background, and unknown mixed colors. Based on these colors in the local region, we adaptively construct a curve color model using a quadratic Bézier curve model. Our curve model allows the derivation of a new closed-form matting equation for estimating alpha values of colors forming a curve. We show that our method estimates alpha mattes more accurately than recent existing methods through visual and quantitative comparisons.

AB - Image matting is the process of estimating the foreground and background elements from a single image with limited user input. To solve this severely under-constrained problem, there exist various methods to construct color models for an image. Most previous color models can fail to estimate accurate mattes for complex images of nonlinear color distributions due to their simple color models. In this paper, we present a new dynamic curve color model for image matting that can handle nonlinear color distributions. We show that the colors of a local region can be fit to a curve when the local region includes three types of colors - foreground, background, and unknown mixed colors. Based on these colors in the local region, we adaptively construct a curve color model using a quadratic Bézier curve model. Our curve model allows the derivation of a new closed-form matting equation for estimating alpha values of colors forming a curve. We show that our method estimates alpha mattes more accurately than recent existing methods through visual and quantitative comparisons.

UR - http://www.scopus.com/inward/record.url?scp=84858443507&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858443507&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2011.04.012

DO - 10.1016/j.patrec.2011.04.012

M3 - Article

AN - SCOPUS:84858443507

VL - 33

SP - 920

EP - 933

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

IS - 7

ER -