A novel image annotation model based on content representation with multi-layer segmentation

A novel image annotation model based on content representation with multi-layer segmentation
复制标题

一种基于多层分割内容表示的新型图像标注模型

DOI:
10.1007/s00521-014-1815-6
复制
发表时间:
2015-08
影响因子:
6
通讯作者:
Yuan Yubo
Yuan Yubo
中科院分区:
计算机科学3区
文献类型:
--
作者:
Zhang Jing;Zhao Yaxin;Li Da;Chen Zhihua;Yuan Yubo

文献摘要

参考文献

被引文献

相似文献

图像自动标注是基于语义的图像检索的一个重要问题,但由于语义鸿沟的原因,它仍然是一个具有挑战性的问题。在本文中,提出了一种由三个部分组成的新模型。第一个是多层图像分割,其中显着性分析和归一化剪切相结合,将图像分割成第一层的语义区域。而在第二层,语义区域被进一步分割成网格。第二个是基于区域的词袋(RBoW)模型的图像内容表示,它是 BoW 模型的变体。考虑到标签的相关性,我们采用二阶条件随机场作为模型的第三部分,以确保自动图像标注的准确性。实验结果表明,我们的基于多层分割的图像标注模型可以在多标记方面实现良好的性能,并且在 Corel 5K 和 Pascal VOC 2007 数据集上优于基于单层分割的模型和之前的算法。
Image automatic annotation is an important issue of semantic-based image retrieval, and it is still a challenging problem for the reason ofsemantic gap. In this paper, a novel model with three parts is proposed. The first one is multi-layer image segmentation, in which saliency analysis and normalized cut are combined to segment images into semantic regions in the first layer. While in the second layer, the semantic regions are segmented into grids further . The second one is image content representation by region-based bag-of-words (RBoW) model, which is the variant of BoW model. Considering the correlations of labels, we adopt second-order CRFs as the third part of our model to ensure the accuracy of automatic image annotation. Experimental results show that our multi-layer segmentation-based image annotation model can achieve promising performance for multi-labeling and outperform the model based on single-layer segmentation and previous algorithm on Corel 5K and Pascal VOC 2007 datasets .
DOI: 10.1016/j.patrec.2003.10.015
发表时间: 2004-02
期刊: Pattern Recognit. Lett.
影响因子: --
作者:
S. Park;Jae Won Lee;Sang-Kyoon Kim
通讯作者: S. Park;Jae Won Lee;Sang-Kyoon Kim
基于Rol-BoW的图像内容表示
DOI: 10.1016/j.jvcir.2014.10.007
发表时间: 2015
影响因子: 2.6
作者:
Zhang Jing;Li Da;Zhao Yaxin;Chen Zhihua;Yuan Yubo
通讯作者: Yuan Yubo
DOI: 10.1109/cvpr.2005.16
发表时间: 2005-06
期刊: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
影响因子: --
作者:
Li Fei-Fei-Li-Fei-Fei-48004138;P. Perona
通讯作者: Li Fei-Fei-Li-Fei-Fei-48004138;P. Perona
DOI: 10.1109/iccv.2009.5459266
发表时间: 2009-09
期刊: 2009 IEEE 12th International Conference on Computer Vision
影响因子: --
作者:
M. Guillaumin;Thomas Mensink;J. Verbeek;C. Schmid
通讯作者: M. Guillaumin;Thomas Mensink;J. Verbeek;C. Schmid
DOI: 10.1007/978-3-540-27814-6_64
发表时间: 2004-07
期刊: --
影响因子: --
作者:
Rui Shi;Huamin Feng;Tat-Seng Chua;Chin-Hui Lee
通讯作者: Rui Shi;Huamin Feng;Tat-Seng Chua;Chin-Hui Lee