• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International conference on neural information processing >Nearest Neighbor with Multi-feature Metric for Image Annotation
【24h】

Nearest Neighbor with Multi-feature Metric for Image Annotation

机译：带有用于图像注释的多指标的最近邻居

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Most of the Nearest Neighbor (NN) based image annotation (or classification) methods cannot achieve satisfactory performance. In this paper, we propose a novel Nearest Neighbor method based on a multi-feature distance metric, which takes full advantage of different and complementary features. We first establish a metric for each feature and assign a weight for every metric, and then linearly combine all of them together to form one distance metric, namely the multi-feature metric. After that, we construct an NN model based on "image-to-cluster" distances, which equals to the distances between an image and the clusters within an image category using our multi-feature based metric, and which is different from calculating Euclidean distances between two images. By introducing this multi-feature based distance metric, our NN based model can mitigate the semantic issues due to intra-class variations and inter-class similarities, and improve the image annotation performance. Experiments confirm the superiority of our model in comparison with both the traditional classifiers and the state of the art learning-based models.
机译：大多数基于最近邻居（NN）的图像注释（或分类）方法都无法获得令人满意的性能。在本文中，我们提出了一种基于多特征距离度量的新颖的最近邻方法，该方法充分利用了不同和互补的特征。我们首先为每个特征建立一个度量标准，并为每个度量标准分配权重，然后将所有特征线性组合在一起以形成一个距离度量标准，即多特征度量标准。之后，我们基于“图像到群集”的距离构造一个NN模型，该模型等于使用我们基于多特征的度量，等于图像与图像类别中的簇之间的距离，并且与计算欧几里得距离不同在两个图像之间。通过引入这种基于多特征的距离度量，我们基于神经网络的模型可以缓解由于类内变异和类间相似性引起的语义问题，并提高图像注释性能。与传统分类器和基于学习的先进模型相比，实验证实了我们模型的优越性。

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