摘要
针对单一的谱特征表示的局限性,提出了一种基于多谱特征表示的点模式匹配算法。利用图的不同矩阵的特征值序列作为特征点的描述子;借助多谱嵌入技术求解获得局部结构描述子的相似性;结合几何相容性,使用概率松弛的方法实现点模式匹配问题的求解。模拟数据和真实图像上的比较实验验证了该算法的有效性和稳健性。
Addressing the weakness of the single spectral representation, an algorithm is proposed for point pattern matching on the basis of multiple spectral representations. The eigenvalue series obtained by various matrix representations of graphs are used as the descriptor of feature point. The similarities between the given local structural descriptors are evaluated via the technique of multiview spectral embedding. Combined with the geometric consistency, point pattern matching problem is solved by using the method of probabilistic relaxation. Comparative experiments conducted on both synthetic data and real images verify the effectiveness and robustness of the proposed method.
出处
《光学学报》
EI
CAS
CSCD
北大核心
2013年第12期154-161,共8页
Acta Optica Sinica
基金
国家自然科学基金(11071002
61172127)
安徽省教育厅自然科学研究项目(KJ2011A008)
安徽大学211工程学术创新团队计划
关键词
机器视觉
匹配
谱图理论
局部结构描述子
machine vision
matching
spectral graph theory
local structural descriptor