Automatic Matting of Identification Photos

This paper proposes a framework for matting identification photos automatically. We firstly adopt image processing operations such as skin detection, k-means clustering, Grab cut segmentation and canny operator to generate a trimap with three regions, i.e., background, foreground and unknown regions...

Full description

Saved in:
Bibliographic Details
Published in2013 International Conference on Computer-Aided Design and Computer Graphics pp. 387 - 388
Main Authors Wenshuang Tan, Tiantian Fan, Xudong Chen, Yaobin Ouyang, Dong Wang, Guiqing Li
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.11.2013
Subjects
automatic trimap
Bayes methods
Bayesian matting
Educational institutions
Hair
identification photos
Image color analysis
image matting
Image segmentation
Laplace equations
Shape
Online AccessGet full text
DOI10.1109/CADGraphics.2013.60

Cover

More Information
Summary:This paper proposes a framework for matting identification photos automatically. We firstly adopt image processing operations such as skin detection, k-means clustering, Grab cut segmentation and canny operator to generate a trimap with three regions, i.e., background, foreground and unknown regions. Then, we improve the Bayesian matting by introducing an alpha regularization term. Experiments demonstrate that our system can achieve about 86% acceptance rate for real photo datasets.
DOI:10.1109/CADGraphics.2013.60