文献类型：期刊文献

英文题名：A novel image annotation model based on content representation with multi-layer segmentation

作者：Zhang, Jing[1,2];Zhao, Yaxin[1];Li, Da[1];Chen, Zhihua[1];Yuan, Yubo[1]

机构：[1]E China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China;[2]Nanjing Univ, State Key Lab Novel Software Technol, Nanjing 210008, Jiangsu, Peoples R China

年份：2015

卷号：26

期号：6

起止页码：1407

外文期刊名：NEURAL COMPUTING & APPLICATIONS

收录：;EI(收录号：20150200417266);WOS:【SCI-EXPANDED(收录号:WOS:000358327400011)】；

基金：The authors would like to offer sincere thanks to reviewers. Their comments and suggestions are very important to improve the presentation and technical sounds. The authors also would like to offer sincere thanks to Fangli Ying, Lei Jiang, Yun Liu, Yongwei Gao and Guanghui Dai at the East China University of Science and Technology for their reading this paper carefully and the useful suggestions in the images retrieval. This research has been supported by the National Nature Science Foundation of China (Grants 61370174, 61402174) and also partly supported by Nature Science Foundation of Shanghai Province of China (11ZR1409600).

语种：英文

外文关键词：Multi-label; Image content representation; Multi-layer segmentation; Bag-of-words; Conditional random fields; Image annotation

摘要：Image automatic annotation is an important issue of semantic-based image retrieval, and it is still a challenging problem for the reason of semantic 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 .