arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.07008stat.MLcs.CVcs.LGcs.NE
收藏

分段分级监督

Segmentation hiérarchique faiblement supervisée

Mines ParisTech(巴黎高等矿业学院)

Amin Fehri, Santiago Velasco-Forero, Fernand Meyer

摘要:

图像分割是将图像按照一定的准则划分为一组有意义的区域的过程。分层分割已经成为这方面的一个主要趋势,因为它有利于在不同尺度上出现重要区域。另一方面,许多方法允许我们具有关于图像中感兴趣结构的位置的先验信息。在本文中,我们提出了一个通用的分层分割方法,考虑到任何先验的空间信息,并输出一个分层分割,强调轮廓或感兴趣的区域,同时保留图像中的重要结构。该方法的弱监督分割问题的应用。

英文摘要:

Image segmentation is the process of partitioning an image into a set of meaningful regions according to some criteria. Hierarchical segmentation has emerged as a major trend in this regard as it favors the emergence of important regions at different scales. On the other hand, many methods allow us to have prior information on the position of structures of interest in the images. In this paper, we present a versatile hierarchical segmentation method that takes into account any prior spatial information and outputs a hierarchical segmentation that emphasizes the contours or regions of interest while preserving the important structures in the image. An application of this method to the weakly-supervised segmentation problem is presented.

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。

↑