跳到主要导航 跳到搜索 跳到主要内容

Receptive field based image modeling method for interactive segmentation

  • Bin Yang*
  • , Qi Yang Zhao
  • , Rui Zhang
  • , Bao Lin Yin
  • *此作品的通讯作者
  • Beihang University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

In current interactive segmentation algorithms, image models are constructed and simplified to be independent of spatial features of images. This conflicts with receptive field hypothesis of human vision systems, and causes over-segmentation and under-segmentation. Based on receptive field hypothesis, the paper establishes an image modeling method in which spatial distances are taken into account, and a conservative factor is introduced into the image energy function to improve the segmentation veracity. It is shown by experiments that the method is more accurate than its counterparts.

源语言英语
主期刊名Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09
DOI
出版状态已出版 - 2009
活动2009 2nd International Congress on Image and Signal Processing, CISP'09 - Tianjin, 中国
期限: 17 10月 200919 10月 2009

出版系列

姓名Proceedings of the 2009 2nd International Congress on Image and Signal Processing, CISP'09

会议

会议2009 2nd International Congress on Image and Signal Processing, CISP'09
国家/地区中国
Tianjin
时期17/10/0919/10/09

指纹

探究 'Receptive field based image modeling method for interactive segmentation' 的科研主题。它们共同构成独一无二的指纹。

引用此