Point correspondence by a new third order graph matching algorithm

详细信息    查看全文

• 作者：Xu Yang^a ; ^{xu.yang@ia.ac.cn}Author Vitae ; Hong Qiao^a ; ^b ; ^c ; ^{hong.qiao@ia.ac.cn}Author Vitae ; Zhi-Yong Liu^a ; ^b ; ^c ; ^{zhiyong.liu@ia.ac.cn}Author Vitae
• 关键词：Graph matching ; Point correspondence ; High order constraints ; Adjacency tensor
• 刊名：Pattern Recognition
• 出版年：2017
• 出版时间：May 2017
• 年：2017
• 卷：65
• 期：Complete
• 页码：108-118
• 全文大小：1539 K
• 卷排序：65

文摘

An adjacency tensor based third order graph matching algorithm is proposed. It enjoys a much lower storage complexity than affinity tensor based high order algorithms. Instead of spectral decomposition based optimization, it adopts gradient based optimization. Experiments on synthetic and real-world data witness its state-of-the-art performance.