文档介绍：
基于权重学习的图像最大权对集匹配模型#
李玉鑑,尹创业,阳勇*
(北京工业大学计算机学院,北京 100124)
5
10
摘要:在图匹配模型中权重的设置对匹配性能有很大影响。直接计算的权重往往不符合匹配
图像的实际情况。本文参照二次分配问题的图匹配学习思想,给出了一阶和二阶最大权对集
模型的权重学习计算方法。一阶最大权对集模型直接采用图像特征点作为图的顶点,而二
阶最大权对集模型则采用某些特征点之间的连接边作为顶点,两个模型都可以通过
Kuhn-Munkras 算法求解。一阶最大权对集模型在本质上等价于二次分配问题的线性情况,
但二阶最大权对集模型是一个新模型。在 CMU House 数据库上的图像匹配实验结果表明,
从整体上看,二阶最大权对集模型优于一阶最大权对集模型,且两者在权重通过学习计算时
的性能也优于直接计算的情况。
关键词:计算机应用技术;图像匹配;权重学习;最大权对集;Kuhn-Munkras 算法
中图分类号:
15
Weight Learning-based Maximum Weight Matching Models
for Image Matching
LI Yujian, YIN Chuangye, YANG Yong
(Computer School, Beijing University of Technology, Beijing 100124)
20
25
30
35
40
Abstract: Weight setting has a great impact on performance of graph matching models. Weights by
direct calculation often produce unsatisfactory correspondences between real images. Based on the idea
of learning graph matching for quadratic assignment problems, this paper considers weight learning
methods for first- and second-order maximum weight matching models. In a first-order maximum
weight matching model, image feature points are regarded as vertices of a bipartite graph, whereas in a
second-order maximum weight matching model, edges connecting two feature points are viewed as
vertices. Both of the first- and second-order models can be solved by the Kuhn-Munkras algorithm.
The first-order maximum weight matching model is essenti