arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1710.04097cs.CV
收藏

用于图像搜索的局部氡描述子

Local Radon Descriptors for Image Search

Amirkabir University of Technology(阿米尔卡比尔理工大学);University of Waterloo(滑铁卢大学);Deakin University(迪肯大学)

Morteza Babaie, H. R. Tizhoosh, Amin Khatami, M. E. Shiri

摘要:

Radon变换及其逆运算是医学成像中的重要技术。最近,Radon变换在基于内容的医学图像检索等应用中又引起了人们的兴趣。然而,到目前为止,所有的研究都使用Radon变换作为一个全球或准全球的图像描述符,通过提取整个图像或大子图像的投影。本文试图表明,密集采样产生的局部Radon投影直方图具有更高的区分能力比全球之一。在本文中,我们介绍了本地氡描述符(LRD),并将其应用到IRMA数据集,其中包含14,410 X射线图像以及INRIA假日数据集与1,990图像。我们的研究结果表明,使用LRD与其全球版本的检索性能显着改善。我们还证明,LRD可以提供与LBP和HOG等成熟描述符相当的结果。

英文摘要:

Radon transform and its inverse operation are important techniques in medical imaging tasks. Recently, there has been renewed interest in Radon transform for applications such as content-based medical image retrieval. However, all studies so far have used Radon transform as a global or quasi-global image descriptor by extracting projections of the whole image or large sub-images. This paper attempts to show that the dense sampling to generate the histogram of local Radon projections has a much higher discrimination capability than the global one. In this paper, we introduce Local Radon Descriptor (LRD) and apply it to the IRMA dataset, which contains 14,410 x-ray images as well as to the INRIA Holidays dataset with 1,990 images. Our results show significant improvement in retrieval performance by using LRD versus its global version. We also demonstrate that LRD can deliver results comparable to well-established descriptors like LBP and HOG.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑