Grassmann matching kernels for scene representation and recognition
Grassmann matching kernels for scene representation and recognition
复制标题
DOI：
10.1109/ijcnn.2017.7966416
复制
发表时间：
2017-05
期刊：
影响因子：
--
通讯作者：
B. Raytchev;M. Koujiba;Toru Tamaki;K. Kaneda
中科院分区：
文献类型：
--
作者：
B. Raytchev;M. Koujiba;Toru Tamaki;K. Kaneda
本文提出了一种基于区域子空间概念的场景表示和识别方法。每个图像被预先分割成语义上有意义的区域，并从每个这样的区域中以不同的尺度提取局部特征。区域子空间是从每个区域内的局部特征集计算的低维线性子空间。我们还定义了格拉斯曼匹配核（GMK），它扩展了格拉斯曼核，能够同时匹配多个子空间。我们称之为结果方法，它通过一组区域子空间来表示图像场景，并通过格拉斯曼匹配内核，区域子空间（SoR）在不同类别中进行匹配，并在15场景数据集上进行说明。
In this paper we propose a new method for scene representation and recognition based on the concept of Region Subspaces. Each image is pre-segmented into semantically meaningful regions and local features are extracted at different scales from each such region. The Region Subspaces are the low-dimensional linear subspaces calculated from the set of local features inside each region. We also define Grassmann Matching Kernels (GMK), which extend Grassmann Kernels to be able to match simultaneously multiple subspaces. We call the resulting method, which represents image scenes through a set of Region Subspaces and matches them across different categories through the Grassmann Matching Kernel, Subspaces-of-Regions (SoR) and illustrate it on the 15-Scene dataset.