A two-stage shape retrieval (TSR) method with global and local features
详细信息 查看全文
- 作者：Xiaqing Pan ; xiaqingp@usc.edu" class="auth_mail" title="E-mail the corresponding author ; Sachin Chachada ; C.-C. Jay Kuo
- 关键词：2D shape retrieval ; Shape representation ; MPEG-7 shape dataset ; Kimia99 dataset ; Tari1000 dataset
- 刊名：Journal of Visual Communication and Image Representation
- 出版年：2016
- 出版时间：July 2016
- 年：2016
- 卷：38
- 期：Complete
- 页码：753-762
- 全文大小：2826 K
文摘
- •
A two-stage shape retrieval (TSR) method to address the 2D shape retrieval problem is proposed.
- •
The cause of unreliable retrieval results in all state-of-the-art methods is identified.
- •
TSR decomposes the decision process into two stages: ICF and LMR.
- •
TSR removes irrelevant shapes by considering local and global features simultaneously.
- •
TSR outperforms all other methods on three popular datasets: MPEG-7, Kimia99 and Tari1000.