首页> 外文会议>International Conference on Electrical Engineering and Informatics >The spatial relation features for describing objects relationships within image
【24h】

The spatial relation features for describing objects relationships within image

机译:用于描述图像内对象关系的空间关系特征

获取原文
获取外文期刊封面目录资料

摘要

Spatial features has gained attention in CBIR researches as a mean to represent image properties. These features, presented via Spatial Relation Features (SRF) such left, right, on and in can provide fine queries to locate object location as well as its relation with other object within an image. Although spatial features play an important, yet, there is still less effort done to collect them in proper manner which yield difficulties to use them for spatial-based image processing research. In order to overcome this lack, we presented our library research work in finding the SRF that have been used in computer science research for describing object's spatial relationships within image. Our work managed to produce collection of SRF found in prior literatures which are later listed and described in proper tables. Apart from that, we also described categories that are used to group these SRF in fine arrangement based on their usage. After updated the SRF list, we manage to derive 24 set of SRF recorded under three categories namely topology, orientation and metric.
机译:在CBIR的研究中,空间特征是表示图像属性的含义。通过空间关系特征(SRF)如左,右侧,ON和IN呈现的这些功能可以提供精细查询来定位对象位置以及与图像内的其他对象的关系。虽然空间特征播放了一个重要的功能,但仍有更少的努力来以适当的方式收集它们,从而产生对空间的图像处理研究使用它们的困难。为了克服这种缺乏,我们向我们介绍了在计算机科学研究中使用的SRF,以描述对象在图像内的空间关系中使用的SRF。我们的工作成功地在现有文献中发现的SRF集合,稍后在适当的表中列出和描述。除此之外,我们还会根据其使用,描述了用于将这些SRF分组的类别。更新了SRF列表后,我们可以在三个类别下录制24组SRF即拓扑,方向和度量。

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