【24h】

Non-interactive object extraction based on saliency detection

机译:基于显着性检测的非交互式对象提取

获取原文

摘要

In traditional content-based image retrieval (CBIR),it is very important to segment the regions of interest for retrieval.In order to realize the non-interactive target region segmentation,this paper proposes the object segmentation based on significance region detection.The Grab Cut segmentation algorithm is initialized through the detection of the significance region,and the interactive operation is removed.The segmentation precision of the algorithm proposed in this paper is 89.51%.
机译:在传统的基于内容的图像检索(CBIR)中,将感兴趣的区域分段为检索的感兴趣区域非常重要。为了实现非交互式目标区域分割,提出了基于显着区域检测的对象分割。抓取通过检测意义区域初始化切割分割算法,并且拆除交互式操作。本文提出的算法的分割精度为89.51%。

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