【24h】

Approaches for interactive browsing of large image datasets

机译:交互式浏览大型图像数据集的方法

获取原文

摘要

With the number of digital images growing at a rapid rate, effective approaches for organising large image repositories are highly sought after. In this paper, we summarise a number of such approaches that allow for intuitive browsing of image databases. Based on visual features extracted from the images, complete image libraries can be visualised in such a way that similar images are located close to each other in the visualisation. This, coupled with appropriate browsing operations, allows for interactive exploration of even large scale image collections as demonstrated by the Hue Sphere Image Browser and Honeycomb Image Browser approaches.
机译:随着以快速速率增长的数字图像数量,高度追捧了组织大型图像存储库的有效方法。在本文中,我们总结了许多允许直观浏览图像数据库的这种方法。基于从图像中提取的视觉特征,可以以这样的方式可视化完整的图像库,使得类似图像在可视化中彼此靠近彼此靠近。与适当的浏览操作相耦合,允许甚至大规模图像集合的交互式探索,如色调球体图像浏览器和蜂窝图像浏览器方法所示。

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