A graph-matching kernel for object categorization
A graph-matching kernel for object categorization
复制标题
DOI：
10.1109/iccv.2011.6126445
复制
发表时间：
2011-11
期刊：
影响因子：
--
通讯作者：
Olivier Duchenne;Armand Joulin;J. Ponce
中科院分区：
文献类型：
--
作者：
Olivier Duchenne;Armand Joulin;J. Ponce
本文探讨了类别级图像分类问题。基础图像模型是一个图，其节点对应一组密集的区域，边反映图像的底层网格结构，并作为弹簧在匹配过程中保证附近区域的几何一致性。提出了一种用于匹配与两幅图像相关联的图的快速近似算法。该算法用于构建一个适用于基于支持向量机的图像分类的核，并且在加州理工学院101、加州理工学院256和场景数据集上的实验表明，其性能与使用单一类型特征的现有方法相当或更优。
This paper addresses the problem of category-level image classification. The underlying image model is a graph whose nodes correspond to a dense set of regions, and edges reflect the underlying grid structure of the image and act as springs to guarantee the geometric consistency of nearby regions during matching. A fast approximate algorithm for matching the graphs associated with two images is presented. This algorithm is used to construct a kernel appropriate for SVM-based image classification, and experiments with the Caltech 101, Caltech 256, and Scenes datasets demonstrate performance that matches or exceeds the state of the art for methods using a single type of features.