Automatic Matting of Identification Photos

Wenshuang Tan,Tiantian Fan,Xudong Chen,Yaobin Ouyang,Dong Wang,Guiqing Li

Computer-Aided Design and Computer Graphics（2013）

引用 5|浏览0

暂无评分

摘要

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.

查看译文

关键词

acceptance rate,identification photos,canny operator,pattern clustering,bayesian matting,bayes methods,trimap,image processing operation,image segmentation,skin detection,mathematical operators,k-means clustering,grabcut segmentation,automatic identification photo matting,real photo datasets,image matting,unknown region,object detection,image processing operations,automatic trimap,alpha regularization term,automatic matting,matting identification photo,shape

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要