Color-texture cosegmentation based on nonlinear compact multi-scale structure tensor and TV-flow
详细信息 查看全文
- 作者：Shoudong Han ; shoudonghan@hust.edu.cn" class="auth_mail" title="E-mail the corresponding author ; Wei Xu ; Wenbing Tao ; Yang Chen
- 关键词：Color-texture image segmentation ; Texture modeling ; Structure tensor ; Total variation flow ; Cosegmentation
- 刊名：Signal Processing
- 出版年：2017
- 出版时间：February 2017
- 年：2017
- 卷：131
- 期：Complete
- 页码：456-471
- 全文大小：11813 K
文摘
- listitem" id="list_li0005">
- •
The nonlinear compact multi-scale structure tensor (NCMSST) is constructed.
- •
A powerful texture descriptor is designed by integrating NCMSST and TV-flow.
- •
Just similarity of color and texture is considered rather than global consistency.
- •
A penalty term is included to adaptively balance possible local inconsistencies.
- •
A graph cuts based color-texture cosegmentation method is proposed.