...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Optical engineering >Image classification with multiple feature channels
【24h】

Image classification with multiple feature channels

机译：具有多个功能通道的图像分类

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

In this paper, we propose a framework for image classifica-tion. An image is represented by multiple feature channels which are computed by the bag-of-words model and organized in a spatial pyra-mid. The main difference among feature channels resides in what type of base descriptor in the bag-of-words model is extracted. The over-all features achieve different levels of the trade-off between discrimina-tive power and invariance. Support vector machines with kernels based on histogram intersection distance and x~2 distance are used to obtain a posteriori probabilities of the image in each feature channel. Then, four data fusion strategies are proposed to combine intermediate results from multiple feature channels. Experimental results show that almost all the proposed strategies can significantly improve the classification accuracy as compared with the single cue methods and, especially, prod-max per-forms best in all experiments. The framework appears to be general and capable of handling diverse classification problems due to the multiple-feature-channel-based representation. Also, it is demonstrated that the proposed method achieves higher, or comparable, classification accura-cies with less computational cost as compared with other multiple cue methods on challenging benchmark datasets.
机译：在本文中，我们提出了图像分类的框架。图像由多个特征通道表示，这些通道由词袋模型计算并组织在空间金字塔中。特征通道之间的主要区别在于在词袋模型中提取哪种类型的基本描述符。总体特征实现了判别力和不变性之间的不同折衷水平。使用基于直方图相交距离和x〜2距离的核的支持向量机获得每个特征通道中图像的后验概率。然后，提出了四种数据融合策略来组合来自多个特征通道的中间结果。实验结果表明，与单线索方法相比，几乎所有提出的策略都可以显着提高分类准确性，尤其是在所有实验中，prod-max性能最高。由于基于多功能通道的表示，该框架似乎通用并且能够处理各种分类问题。而且，证明了与具有挑战性的基准数据集上的其他多种提示方法相比，所提出的方法以较低的计算成本实现了更高或相当的分类精度。

著录项

  • 来源
    《Optical engineering》 |2011年第5期|p.057210.1-057210.9|共9页
  • 作者

    Fuxiang Lu; Xiaokang Yang; Weiyao Lin; Rui Zhang; Songyu Yu;

  • 作者单位

    Shanghai Jiao Tong University Institute of Image Communication and Information Processing Shanghai, 200240, China Lanzhou University School of Information Science and Engineering Lanzhou, 730000, China;

    Jiao Tong University Institute of Image Communication and Information Processing Shanghai, 200240, China;

    Jiao Tong University Institute of Image Communication and Information Processing Shanghai, 200240, China;

    Jiao Tong University Institute of Image Communication and Information Processing Shanghai, 200240, China;

    Jiao Tong University Institute of Image Communication and Information Processing Shanghai, 200240, China;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    image classification; object categorization; scene categorization; feature channel; spatial pyramid; visual descriptor;

    机译：图像分类;对象分类;场景分类;功能频道;空间金字塔视觉描述符;

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