首页> 外文会议>Signal Processing, Sensor Fusion, and Target Recognition XV >Automatic clustering based on an information-theoretic approach with application to spectral anomaly detection
【24h】

Automatic clustering based on an information-theoretic approach with application to spectral anomaly detection

机译:基于信息理论的自动聚类及其在光谱异常检测中的应用

获取原文
获取原文并翻译 | 示例

摘要

An information-theoretic method is described for automatically determining the best number of clusters. It is motivated by Rissanen's minimum description length principle that states the best representation is the one with the fewest bits. The method is evaluated using two different clustering algorithms: a mode finder based on scale-space algorithm, and a vector quantizer (VQ). Synthetic, single-and multi-band image clustering examples are presented. Clusterings produced by the mode finder are shown to better correspond to distinguishable surface categories in the scene than those produced by the VQ algorithm. VQ clusterings are evaluated within an anomaly detector, which detects manmade object/changes as spectral outliers within a set of background clusters. It is shown that the optimal VQ clustering (the one with the fewest bits) produces the best detection performance.
机译:描述了一种信息理论方法,用于自动确定最佳群集数。它受Rissanen的最小描述长度原则的启发,该原则指出,最好的表示形式是位数最少的表示形式。使用两种不同的聚类算法评估该方法:基于比例空间算法的模式查找器和矢量量化器(VQ)。给出了合成的,单频带和多频带图像聚类示例。与VQ算法产生的聚类相比,模式查找器产生的聚类显示出与场景中可区分的表面类别更好地对应。 VQ聚类在异常检测器中进行评估,该异常检测器将人造对象/变化检测为一组背景聚类中的光谱离群值。结果表明,最佳的VQ聚类(位数最少的聚类)产生最佳的检测性能。

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