• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Machine Vision and Applications >Kernelized pyramid nearest-neighbor search for object categorization
【24h】

Kernelized pyramid nearest-neighbor search for object categorization

机译：核化金字塔最近邻搜索用于对象分类

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Nearest-neighbor-based image classification has drawn considerable attention in the past several years thanks to its simplicity and efficiency. Recently, a Kernelized version of Naive-Bayes Nearest-Neighbor (KNBNN) approach has been proposed to combine Nearest-Neighbor-based approaches with other bag-of-feature (BoF) based kernels. However, similar to an orderless BoF image representation, the KNBNN ignores global geometric correspondence. In this paper, our contributions are threefolded. First, we present a technique to exploit the global geometric correspondence in a kernelized NBNN classifier framework. We divide an image into increasingly fine sub-regions like the spatial pyramid matching (SPM) approach; Second, we introduce a pyramid nearest-neighbor kernel by measuring the local similarity in each pyramid window. Third, for better calibrating the outputs of each window, we fit a sigmoid function to add posterior probability to its SVM outputs, and then weight these outputs of all windows. The sigmoid parameters and weight values are learned in a class-dependent and window-dependent manner. By doing so, we learn a class-specific geometric correspondence. Finally, the proposed approach is evaluated on two public datasets: Scene-15 and Caltech-101. We reach 85.2 % recognition rate on Scene-15 and 73.3 % on Caltech-101 only using single descriptor. The experimental results show that our approach significantly outperforms existing techniques.
机译：基于近邻的图像分类在过去几年中由于其简单性和效率而备受关注。最近，已经提出了Naive-Bayes最近邻（KNBNN）方法的内核版本，以将基于最近邻的方法与其他基于功能包（BoF）的内核相结合。但是，类似于无序BoF图像表示，KNBNN忽略了全局几何对应。在本文中，我们的贡献是三重的。首先，我们提出一种在带内核的NBNN分类器框架中利用全局几何对应关系的技术。我们将图像划分为越来越精细的子区域，例如空间金字塔匹配（SPM）方法；其次，我们通过测量每个金字塔窗口中的局部相似性来引入金字塔最近邻内核。第三，为了更好地校准每个窗口的输出，我们拟合了一个S型函数以向其SVM输出添加后验概率，然后对所有窗口的这些输出进行加权。以类相关和窗口相关的方式学习S形参数和权重值。通过这样做，我们学习了特定于类别的几何对应关系。最后，在两个公共数据集上评估了提出的方法：Scene-15和Caltech-101。仅使用单个描述符，在Scene-15上的识别率就达到85.2％，在Caltech-101上的识别率达到73.3％。实验结果表明，我们的方法明显优于现有技术。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号