刊名:Journal of Visual Communication and Image Representation
出版年:2017
出版时间:February 2017
年:2017
卷:43
期:Complete
页码:138-151
全文大小:5296 K
卷排序:43
文摘
Proposed method is based on sample reconstruction and FLDA. Feature descriptors used to represent superpixel for dictionary building. Proposed method is robust to quantity and location of labels. Segmentation problem is cast into multi-classification problem.