• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Second International Conference on Data Mining, 2nd >Influence of lossy compression on hyperspectral image classification accuracy
【24h】

Influence of lossy compression on hyperspectral image classification accuracy

机译：有损压缩对高光谱图像分类精度的影响

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 the relationship between compression rate and classification accuracy for hyperspectral images is studied. We construct several classification trees using CART and then, for various rates, we measure their classification accuracy after the input image has been compressed. We compare two kinds of classification trees: first, we construct one-stage trees, which classify the input image using only a single classification stage. Second, we construct multi-stage trees; these use a mixed class that delays classification of problematic pixels for which the accuracy achieved in the current stage is not enough. Then, for several compression rates, we study the classification accuracy evolution of such trees when a lossy compression method is applied to the input image before the classification stage. The JPEG standard for still image compression is taken as the basis lossy method. We then employ a three-dimensional extension of the JPEG standard in order to take advantage of band correlation. We also reduce the input image dimension using a basic analysis based on a previous classification tree, so that the best set of classification features is chosen. Our experiments show that it is possible to achieve high compression rates without degrading classification accuracy too much. Results indicate that multi-stage classification trees yield similar classification performance than one-stage trees at a reduced cost. In addition, it is also possible to obtain higher compression rates by means of a three-dimensional lossy compression method.
机译：本文研究了高光谱图像压缩率与分类精度之间的关系。我们使用CART构造几个分类树，然后针对各种比率，在压缩输入图像后测量其分类精度。我们比较了两种分类树：首先，我们构建一个阶段树，仅使用一个分类阶段就对输入图像进行分类。其次，我们构建多阶段树；它们使用混合类来延迟问题像素的分类，而在当前阶段所达到的精度还不够。然后，对于几种压缩率，我们研究了在分类阶段之前将有损压缩方法应用于输入图像时，此类树的分类精度演变。静止图像压缩的JPEG标准被视为基本的有损方法。然后，我们采用JPEG标准的三维扩展，以利用频带相关性。我们还使用基于先前分类树的基本分析来减少输入图像的尺寸，以便选择最佳的分类特征集。我们的实验表明，可以实现较高的压缩率而不会过度降低分类精度。结果表明，多级分类树以降低的成本产生了与一级树相似的分类性能。另外，还可以通过三维有损压缩方法获得更高的压缩率。

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